Skip to content
Projets

flyingdoog/awesome-graph-explainability-papers

Voir sur GitHub

flyingdoog/awesome-graph-explainability-papers has 821 GitHub stars and 75 forks. GitHot measured +1 stars in 24 hours and +2 in 7 days. Last checked 2026-11-20 01:34 UTC. Last push 2026-11-12.

Comment ces chiffres sont mesurés

Progression mesurée des étoiles

in 24h
+1
in 7 days
+2
in 15 days
Historique en cours
in 1 month
Historique en cours

Variations nettes sur des périodes qui se chevauchent, pas des totaux quotidiens. Les mesures absentes restent vides. Les étoiles indiquent l’intérêt, pas la qualité.

À propos

Papers about explainability of GNNs

Apprentissage automatique

README.md

Original

Awesome Graph Explainability Papers

A curated list of papers on the explainability and interpretability of Graph Neural Networks (GNNs).

Awesome 987 papers last updated 2026-11 PRs welcome

Contents

Section Entries
Surveys 11
Platforms 6
Year 2026 315
Year 2025 297
Year 2024 124
Year 2023 114
Year 2022 65
Year 2021 44
Year 2020 and Before 17

Browse by topic: bytopics.md.

How to read the entries. [Venue yy] gives the venue and the two-digit year, [Arxiv yy.mm] marks an arXiv-only preprint (year and month of its first submission), and [Preprint yy] other non-peer-reviewed releases. In 2024-2026 the entries are grouped by venue: Nature-family journals first, then TPAMI, NeurIPS, ICML, ICLR, AAAI, KDD and all other venues, with arXiv preprints newest first.

Contributions are welcome: please open a pull request or an issue.

Surveys

  1. [ACM computing survey 25] Explaining the Explainers in Graph Neural Networks: a Comparative Study [paper]
  2. [Proceedings of the IEEE 24] Trustworthy Graph Neural Networks: Aspects, Methods and Trends [paper]
  3. [Preprint 24] Graph-Based Explainable AI: A Comprehensive Survey [paper]
  4. [IEEE Data Eng Bull 23] A Survey on Explainability of Graph Neural Networks [paper]
  5. [ACM computing survey] A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challenges [paper]
  6. [TPAMI 22] Explainability in graph neural networks: A taxonomic survey. Yuan Hao, Yu Haiyang, Gui Shurui, Ji Shuiwang. [paper]
  7. [Arxiv 22] A Survey of Explainable Graph Neural Networks: Taxonomy and Evaluation Metrics [paper]
  8. [Arxiv 22] A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protection [paper]
  9. [Big Data 22] A Survey of Explainable Graph Neural Networks for Cyber Malware Analysis [paper]
  10. [Machine Intelligence Research 24] A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability [paper]
  11. [Book 23] Generative Explanation for Graph Neural Network: Methods and Evaluation [paper]

Platforms

  1. PyTorch Geometric [Document] [Blog]
  2. DIG: A Turnkey Library for Diving into Graph Deep Learning Research [paper] [Code]
  3. GraphXAI: Evaluating Explainability for Graph Neural Networks [paper] [Code]
  4. GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networks [paper] [Code]
  5. GNNExplainer and PGExplainer [paper] [Code]
  6. BAGEL: A Benchmark for Assessing Graph Neural Network Explanations [paper] [Code]

Year 2026

  1. [Nature Communications 26] Interpretable graph-based models on multimodal biomedical data integration: a technical review and benchmarking [paper]
  2. [Nature Communications 26] SpaCEy links spatial tissue patterns to clinical outcomes using explainable graph neural networks [paper]
  3. [npj AI 26] Unified counterfactual explainer for graph neural networks [paper]
  4. [npj Digital Medicine 26] xGNN4MI: explainability of graph neural networks in 12-lead electrocardiography for cardiovascular disease classification [paper]
  5. [TPAMI 26] Out-of-Distribution-Resistant Evaluations for Explanations of Graph Neural Networks [paper]
  6. [TPAMI 26] Addressing Structural Distribution Shift in Explanations for Graph Neural Networks [paper]
  7. [TPAMI 26] A Novel Approach to GNN Explainability: Distilling Knowledge With Inter-Layer Alignment [paper]
  8. [TPAMI 26] Consensus-Driven Distillation for Trustworthy Explanations in Self-Interpretable GNNs [paper]
  9. [NeurIPS 26] A Generalized Tikhonov Layer for Interpretable-by-design Graph Neural Networks [paper]
  10. [NeurIPS 26] BeamWitness: Rooted Subgraph Beam Search for Selective Graph Representation Learning [paper]
  11. [NeurIPS 26] GraphUAT: Uncertainty Attribution in Graph Neural Networks [paper]
  12. [NeurIPS 26] Learning Continuously Evolving Spatio-Temporal Explanations for Traffic Flow Forecasting [paper]
  13. [NeurIPS 26] NORMA: Norm-Guided Explanation Subgraph Discovery [paper]
  14. [NeurIPS 26] Robust Surrogate Modeling for Explainable Graph Neural Networks [paper]
  15. [NeurIPS 26] SSDGExplainer: Structure-Semantic Dual-Guided Explainer for Graph Neural Networks [paper]
  16. [NeurIPS 26] B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data [paper]
  17. [ICML 26] Multi-scale Explainer for Graph Neural Networks [paper]
  18. [ICML 26] ST-TGExplainer: Disentangling Stability and Transition Patterns for Temporal GNN Interpretability [paper]
  19. [ICML 26] TN-SHAP-G: Graph-Structured Tensor Network Surrogates for Shapley Values and Interactions [paper]
  20. [ICML 26] Towards the Explainability of Temporal Graph Networks via Memory Backtracking and Topological Attribution [paper]
  21. [ICML 26] Watermarking Graph Neural Networks via Explanations for Ownership Protection [paper]
  22. [ICLR 26] GNN Explanations that do not Explain and How to find Them [paper]
  23. [ICLR 26] Self-Consistency Improves the Trustworthiness of Self-Interpretable GNNs [paper]
  24. [ICLR 26] ATEX-CF: Attack-Informed Counterfactual Explanations for Graph Neural Networks [paper]
  25. [ICLR 26] Certified Evaluation of Model-Level Explanations for Graph Neural Networks [paper]
  26. [ICLR 26] SuperMAN: Interpretable and Expressive Networks over Temporally Sparse Heterogeneous Data [paper]
  27. [AAAI 26] Generating In-Distribution Counterfactual Explanation for Graph Neural Networks [paper]
  28. [AAAI 26] Interpretable and Robust Behavior Abstraction via Environment-Disentangled Heterogeneous Graph [paper]
  29. [AAAI 26] Explaining Temporal Graph Neural Network via Quantum-Inspired Evolutionary Algorithm [paper]
  30. [AAAI 26] Self-Interpretable Subgraph Neural Network with Deep Reinforcement Walk Exploration [paper]
  31. [AAAI 26] CastX: Cohort-Level Causal Inference Meets Statistical Testing for Faithful and Reliable GNN Explanations [paper]
  32. [AAAI 26] Enhancing Chemical Explainability Through Counterfactual Masking [paper]
  33. [AAAI 26] ExPath: Targeted Pathway Inference for Biological Knowledge Bases via Graph Learning and Explanation [paper]
  34. [AAAI 26] Framework GNN-AID: Graph Neural Network Analysis Interpretation and Defense [paper]
  35. [KDD 26] Do Explanations Increase the Risk of Decision Logic Leakage? Explanation-Guided Stealing of Graph Models. [paper]
  36. [KDD 26] CATGX: Causal-Aware Temporal Graph Explanation via Scalable Motif Sampling and Adjustment [paper]
  37. [KDD 26] Counterfactual Analysis on Large Graphs [paper]
  38. [KDD 26] Out-of-Distribution Robust Explainer for Graph Neural Networks [paper]
  39. [KDD 26] ProgNet: Program-Grounded Evidence Composition for Interpretable Graph Classification [paper]
  40. [WWW 26] Explainable Graph Sparsification with Shapley Values [paper]
  41. [WWW 26] SGExplainer: Balanced Path-based Signed Graph Neural Network Explanation for Link Sign Prediction [paper]
  42. [WWW 26] Identification of Influential Node Group in Attributed Graph through Explaining Graph Neural Network [paper]
  43. [WWW 26] Discrete Diffusion-Based Model-Level Explanation of Heterogeneous GNNs with Node Features [paper]
  44. [WWW 26] Explaining Synergistic Effects in Social Recommendations [paper]
  45. [WWW 26] SliceGX: Layer-wise GNN Explanation with Model-slicing [paper]
  46. [WWW 26] CausalSKyHop: Knowledge-Aware Causal Explanation of Dynamic GNNs via Higher-Order Semantic Reasoning [paper]
  47. [WWW 26] Robust Heterogeneous Graph Neural Network Explainer with Graph Information Bottleneck [paper]
  48. [WWW 26] Difference-based Sample Selection for Federated Graph Rationalization [paper]
  49. [ACL 26] From nodes to narratives: Explaining graph neural networks with llms and graph context [paper]
  50. [TIFS 26] Learning Subgraph-Based Normality for Interpretable Graph-Level Anomaly Detection [paper]
  51. [TIFS 26] Learning Higher-Order Dependencies in Malware Control-Flow Graphs With Hypergraph-Level Explanations [paper]
  52. [TMLR 26] AIMing for Standardised Explainability Evaluation in GNNs: A Framework and Case Study on Graph Kernel Networks [paper]
  53. [TMLR 26] Explainable Graph Learning for Particle Accelerator Operations [paper]
  54. [TMLR 26] Explaining Graph Neural Networks for Node Similarity on Graphs [paper]
  55. [TMLR 26] Confidence-Aware Explanations for 3D Molecular Graphs via Energy-Based Masking [paper]
  56. [AISTATS 26] Archetypal Graph Generative Models: Explainable and Identifiable Communities via Anchor-Dominant Convex Hulls [paper]
  57. [TKDE 26] Learning From Graph-Graph Relationship: A New Perspective on Graph-Level Anomaly Detection [paper]
  58. [TKDE 26] Contrastive Fidelity-Maximised Explanations for Graph-Based Rumour Detection [paper]
  59. [TKDE 26] CoRas: Cooperative Rationale Selection for Graph Rationale Learning in Out-of-Distribution Graphs [paper]
  60. [TKDE 26] Enhancing Graph Neural Network Explainers Using a Distribution Shift Consistency-Guided Generator [paper]
  61. [TKDE 26] Explainable Anomaly Detection in Dynamic Heterogeneous Graphs via Relation Evolution [paper]
  62. [TKDE 26] Self-Explaining Graph Neural Network for Link Prediction Based on Path-Aware Prototype Learning [paper]
  63. [TKDE 26] Towards Faithful Class-level Self-explainability in Graph Neural Networks by Subgraph Dependencies [paper]
  64. [CIKM 26] CausalExplainer: Causal Explanations for Temporal Graph Neural Networks [paper]
  65. [CIKM 26] Context-Aware Subgraph Explanations for Multi-Task GNNs [paper]
  66. [CIKM 26] Counterfactual Explanations for Hypergraph Neural Networks [paper]
  67. [CIKM 26] Generating Intervention Hypotheses using Explainable Explanations on Graphs: G2I, a Two-Stage Greedy Framework [paper]
  68. [IJCAI 26] Local Geometry Improves Explanation Robustness for Graph Neural Networks [paper]
  69. [IJCAI 26] Semifactual Explanations for GNN-based Classification: Formal Foundations, Complexity and Computation [paper]
  70. [UAI 26] A Probabilistic Circuit Framework for Interpretable Graph PU Learning [paper]
  71. [UAI 26] FraudGNAM: Inherently Interpretable Spectral GNN for Graph Fraud Detection [paper]
  72. [UAI 26] Interpretable Spatial-Temporal Forecasting via Additive Neural Decomposition and Knowledge Distillation [paper]
  73. [WSDM 26] Forget and Explain: Transparent Verification of GNN Unlearning [paper]
  74. [WSDM 26] GNN Explainers 2.0: User-centric and Data-driven Insights [paper]
  75. [Arxiv 26.11] A Comparative Study of Importance Attribution to Columns in Deep Learning over Relational Databases [paper]
  76. [Arxiv 26.11] Graph Symbolic Distillation: Decoding Graph Data into Interpretable Formulas across Materials and Chemistry [paper]
  77. [Arxiv 26.11] TopoSHAP: Shapley for Explainable and Efficient Topological Deep Learning [paper]
  78. [Arxiv 26.11] What Does It Mean to Remove an Edge? Intervention-Aware Fidelity for Graph Neural Network Explanations [paper]
  79. [Arxiv 26.10] Accurate and Auditable ECG Classification via Visibility Graph Neural Networks [paper]
  80. [Arxiv 26.10] Beyond Trained Models: Compiling GNNs for a Sound Explainer Benchmark [paper]
  81. [Arxiv 26.10] Graph Additive Models disentangling feature, topology, and interactions [paper]
  82. [Arxiv 26.10] MPGE: A Multi-Perspective Graph Explainer for Molecular Classification Explanation [paper]
  83. [Arxiv 26.10] ProtoGTX: Prototype-Aligned Graph Transformer for Explainable Whole-Slide Image Analysis [paper]
  84. [Arxiv 26.10] WOMBAT: Whitebox Oracle for Molecular Benchmarking and Attribution Testing [paper]
  85. [Arxiv 26.09] An Accurate and Interpretable Hyper Graph Neural Network for GBM Survival Prediction [paper]
  86. [Arxiv 26.09] Controllable GNN Explanations via Multi-Metric Preference Selection [paper]
  87. [Arxiv 26.09] Explaining spatial information flow in short-term traffic forecasting models using a gated graph attention network [paper]
  88. [Arxiv 26.09] From Explanations to Interventions: Execution-Guided Counterfactual Synthesis in Temporal Graphs [paper]
  89. [Arxiv 26.09] HARMONIA: Interpretable Graph Learning through Mixtures of Neural Bases [paper]
  90. [Arxiv 26.09] RACE: Relation-Level Counterfactual Explanations for Heterogeneous Graph Neural Networks [paper]
  91. [Arxiv 26.09] Where Privacy Belongs: Placement Diagnosis and Certified Selection for Private Counterfactual Explanations on Graphs [paper]
  92. [Arxiv 26.08] Amortised Post-Hoc Explanation with Exact Preservation for Dynamic Graph Anomaly Detectors [paper]
  93. [Arxiv 26.08] Dual Spatial-Temporal Attribution: Architecture-Aligned Post-Hoc Explainability for Recurrent Graph Anomaly Detection [paper]
  94. [Arxiv 26.08] Faithful, Sufficient and Understandable: Rethinking Graph Counterfactual Explanations via Discrete Diffusion Inversion [paper]
  95. [Arxiv 26.08] MolLedger: An Additive Graph Neural Network with Chemically Grounded ADME Attributions [paper]
  96. [Arxiv 26.08] NICE: Scale-Stable Perturbations for Graph Neural Network Explanations via Noise Corruption [paper]
  97. [Arxiv 26.08] Self-Explainable Multi-Label Graph Neural Network for Correlated Evidence Attribution [paper]
  98. [Arxiv 26.08] VINCENT: Validated Interaction Network for Cross-drug Explanation of Therapeutics [paper]
  99. [Arxiv 26.07] A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs [paper]
  100. [Arxiv 26.07] Automorphism-Induced Non-Canonicity in Top-k Explanations of Graph Neural Networks [paper]
  101. [Arxiv 26.07] Towards Faithful Graph Explanations with Synergistic Edge Effects via Granular Balls [paper]
  102. [Arxiv 26.07] path_boost: A Python Package for Interpretable Graph-Level Prediction using Path-Based Gradient Boosting [paper]
  103. [Arxiv 26.06] Beyond Soft Masks: Hard-Perturbation Mixup Explainer for Robust GNN Explainability [paper]
  104. [Arxiv 26.06] CIExplainer++: Generating Causal and Interpretable Explanations for Graph Neural Networks [paper]
  105. [Arxiv 26.06] Explaining Temporal Graph Neural Networks via Feature-induced Information Flow [paper]
  106. [Arxiv 26.06] HiSE: A Lightweight Hierarchical Semantic Explainer for Heterogeneous Graph Neural Networks [paper]
  107. [Arxiv 26.05] B-cos GNNs: Faithful Explanations through Dynamic Linearity [paper]
  108. [Arxiv 26.05] Can Subgraph Explanations Be Weaponized to Steal Graph Neural Networks? [paper]
  109. [Arxiv 26.05] Ex-GraphRAG: Interpretable Evidence Routing for Graph-Augmented LLMs [paper]
  110. [Arxiv 26.05] Graph Reconstruction from Differentially Private GNN Explanations [paper]
  111. [Arxiv 26.05] Graph neural network explanations reveal a topological signature of disease-associated hubs in biological networks [paper]
  112. [Arxiv 26.05] Structural Interpretations of Protein Language Model Representations via Differentiable Graph Partitioning [paper]
  113. [Arxiv 26.05] From Model to Data (M2D): Shifting Complexity from GNNs to Graphs for Transparent Graph Learning [paper]
  114. [Arxiv 26.05] Model-Level GNN Explanations via Rule-to-Graph Readout for Logit Reconstruction [paper]
  115. [Arxiv 26.05] A Cognitive Explainer for Fetal ultrasound images classifier Based on Medical Concepts] Cognitive Explainers of Graph Neural Networks Based on Medical Concepts [paper]
  116. [Arxiv 26.05] GRAFT: Auditing Graph Neural Networks via Global Feature Attribution [paper]
  117. [Arxiv 26.05] Why Self-Inconsistency Arises in GNN Explanations and How to Exploit It [paper]
  118. [Arxiv 26.04] Concept Graph Convolutions: Message Passing in the Concept Space [paper]
  119. [Arxiv 26.04] Explainable AI for Jet Tagging: A Comparative Study of GNNExplainer, GNNShap, and GradCAM for Jet Tagging in the Lund Jet Plane [paper]
  120. [Arxiv 26.04] Explaining Temporal Graph Predictions With Shapley Values [paper]
  121. [Arxiv 26.04] Exploring Concept Subspace for Self-explainable Text-Attributed Graph Learning [paper]
  122. [Arxiv 26.04] Subgraph Concept Networks: Concept Levels in Graph Classification [paper]
  123. [Arxiv 26.04] XGRAG: A Graph-Native Framework for Explaining KG-based Retrieval-Augmented Generation [paper]
  124. [Arxiv 26.03] Beyond Edge Deletion: A Comprehensive Approach to Counterfactual Explanation in Graph Neural Networks [paper]
  125. [Arxiv 26.03] ORACAL: A Robust and Explainable Multimodal Framework for Smart Contract Vulnerability Detection with Causal Graph Enrichment [paper]
  126. [Arxiv 26.03] Revealing Combinatorial Reasoning of GNNs via Graph Concept Bottleneck Layer [paper]
  127. [Arxiv 26.03] Poisoning the Inner Prediction Logic of Graph Neural Networks for Clean-Label Backdoor Attacks [paper]
  128. [Arxiv 26.02] Beyond Message Passing: A Symbolic Alternative for Expressive and Interpretable Graph Learning [paper]
  129. [Arxiv 26.02] CFRecs: Counterfactual Recommendations on Real Estate User Listing Interaction Graphs [paper]
  130. [Arxiv 26.02] PIME: Prototype-based Interpretable MCTS-Enhanced Brain Network Analysis for Disorder Diagnosis [paper]
  131. [Arxiv 26.02] Is Meta-Path Attention an Explanation? Evidence of Alignment and Decoupling in Heterogeneous GNNs [paper]
  132. [Arxiv 26.02] Quantifying Explanation Quality in Graph Neural Networks using Out-of-Distribution Generalization [paper]
  133. [Arxiv 26.01] Parallelizing Node-Level Explainability in Graph Neural Networks [paper]
  134. [Arxiv 26.01] Structural Graph Neural Networks with Anatomical Priors for Explainable Chest X-ray Diagnosis [paper]
  135. [Arxiv 26.01] GCFX: Generative Counterfactual Explanations for Deep Graph Models at the Model Level [paper]
  136. [Arxiv 26.01] FSX: Message Flow Sensitivity Enhanced Structural Explainer for Graph Neural Networks [paper]
  137. [Arxiv 26.01] Transparent Malware Detection With Granular Assembly Flow Explainability via Graph Neural Networks [paper]
  138. [ICDM Demo 26] Declarative Explanations for Graph Neural Networks: A Demonstration [paper]
  139. [SETN 26] A Comparative Study of Counterfactual Explainers for Graph Neural Networks Enabling Multiple Types of Graph Edit [paper]
  140. [ENIAC 26] From Abductive Explanations to Global Logical Rules for Node Classification in SGCs [paper]
  141. [ECML PKDD 26] Measuring What Matters: A Unified Evaluation Framework for GNN Explainability [paper]
  142. [ECML PKDD 26] CQD-SHAP: Explainable Complex Query Answering via Shapley Values [paper]
  143. [ECML PKDD 26] Combating Spurious Correlations in Graph Interpretability via Self-Reflection [paper]
  144. [ECML PKDD 26] Optimal Transport Prototypes and Symbolic Logic Combination for Self-Explainable Graph Neural Networks [paper]
  145. [ECML PKDD 26] PLEX: Edge-Aware Logic-Based Self-Explainable Graph Neural Networks with Polyadic Predicates [paper]
  146. [ECML PKDD 26] Stabilizing Graph Explanations Under Spurious Correlations via Self-reflection [paper]
  147. [ICML Workshop 26] When Graph Tokens Sink: A Mechanistic Analysis of Graph Language Models [paper]
  148. [Mach. Learn. Knowl. Extr. 26] Routing-Aware Explanations for Mixture of Experts Graph Models in Malware Detection [paper]
  149. [Mach. Learn. Knowl. Extr. 26] Enhancing GNN Explanations for Malware Detection with Dual Subgraph Matching [paper]
  150. [Preprint 26] Explainability in Dynamic Graph Anomaly Detection: X-TADDY [paper]
  151. [Preprint 26] GNN Explainers 2.0: A Paradigm for User-Oriented, Data-Guided Explanations [paper]
  152. [Preprint 26] Explainable yet Confidential: Graph-Based Disclosure Control for Trustworthy Explanations of Relational AI Models [paper]
  153. [Preprint 26.09] Explainable graph neural networks for early prediction of in-hospital mortality: a case study (Preprint) [paper]
  154. [Information Processing & Management 26] PAGSL: Path-Augmenting Graph Structure Learning for explainable scholar recommendation [paper]
  155. [Scientific Reports 26] Generating explainable hypotheses for drug repurposing with graph neural networks [paper]
  156. [ICASSP 26] Prototype-Based Information Bottleneck for Explainable Heterogeneous Temporal Graph Neural Networks [paper]
  157. [ICASSP 26] EEG-SeeGraph: Interpreting functional connectivity disruptions in dementias via sparse-explanatory dynamic EEG-graph learning [paper]
  158. [ICASSP 26] GCE-UQ: Quantifying and Decomposing Uncertainty in Graph Counterfactual Explanations [paper]
  159. [ICASSP 26] Prototype-Based Graph Information Bottleneck for Whole Slide Image Analysis via Task-Relevant Subgraph Extraction [paper]
  160. [XAI 26] TACENR: Task-Agnostic Contrastive Explanations for Node Representations [paper]
  161. [Expert Systems 26] CausGNN: A Causal-Based Explanation Framework for Graph Neural Networks [paper]
  162. [Computing 26] GECo: a community-based graph neural network explainer [paper]
  163. [Neurocomputing 26] GNN-EGG: Graph neural network explanations via graph generation [paper]
  164. [Journal of Complex Networks 26] Assessing the explainability of Graph Neural Networks in random graphs classification task Get [paper]
  165. [IUI 26] Optimal Explanations: A Quantitative Model of Human Error in Causal Graph Interpretation [paper]
  166. [Applied Intelligence] An explainable graph neural network framework for illicit financial transaction detection [paper]
  167. [SSRN Electronic Journal] NEXUS-IDS: From Structural to Semantic Explainability in Flow-Node Graph Neural Networks for IoT Intrusion Detection [paper]
  168. [ENGINEERING Chemical Engineering] AdapGNN: enhancing the explainability of GNN models in molecular properties prediction [paper]
  169. [Information Science 26] Post-hoc explainability of graph neural networks: A comprehensive survey [paper]
  170. [IEEE Transactions on Systems, Man, and Cybernetics: Systems] GroupEx: Toward Group-Level Explanations of Graph Neural Networks [paper]
  171. [Reliability Engineering & System Safety] Temporal causal graph-based attention gated recurrent unit for interpretable fault diagnosis in nuclear power plants [paper]
  172. [CCNCPS 26] Reliability-aware and Explainability-Driven Evaluation of Graph Neural Networks on Citation Networks [paper]
  173. [Pattern Recognition 26] Enhancing graph learning interpretability through modulating cluster information flow [paper]
  174. [Pattern Recognition 26] DisenGE: Learning multiple collaborative subgraphs for faithful Graph neural network explanation [paper]
  175. [BioData Mining 26] Explainable AI-driven graph-based neural networks for mucopolysaccharidoses diagnosis [paper]
  176. [Data Science and Engineering] Generating Counterfactual Temporal Motifs: Unraveling the Mysteries of Temporal Graph Neural Networks [paper]
  177. [International Journal of Geo-Information] BD-GNN: Integrating Spatial and Administrative Boundaries in Property Valuation Using Graph Neural Networks [paper]
  178. [Asia and South Pacific Design Automation Conference 26] GALA: An Explainable GNN-based Approach for Enhancing Oracle-Less Logic Locking Attacks Using Functional and Behavioral Features [paper]
  179. [IEEE Transactions on Computational Social Systems] Causal Graph Learning for Face-Based Interpretable Hierarchical Diagnosis of Depression [paper]
  180. [IEEE Transactions on Reliability] KGC-Explainer: Toward Explainable Knowledge Graph Completion [paper]
  181. [Cybersecurity 26] XGA-E: an explainability-enhanced graph neural network for network traffic anomaly detection [paper]
  182. [VLSID 26] Hardware Trojan Detection and Interpretation Using Graph Neural Networks [paper]
  183. [Neurosymbolic AI Journal] Towards Semantic Understanding of Graph Neural Network Layers Embedding with Functional Semantic Activation Mapping [paper]
  184. [Natural Resources Research] GTF: A New Interpretable Graph Neural Network for Geochemical Anomaly Detection in Mineral Prospectivity Mapping [paper]
  185. [QC+AI 26] QGSHAP: Quantum Acceleration for Faithful GNN Explanations [paper]
  186. [DSAA 26] Explainability of Molecular Graph Neural Network [paper]
  187. [Neural Netw 26] BAED: a New Paradigm for Few-shot Graph Learning with Explanation in the Loop [paper]
  188. [3SCEA 26] C'est Bon: Contrastive Explanation for Multi-Class Graph Neural Networks [paper]
  189. [AAAI SS 26] xLightGCN: Explainable Graph Neural Network Based Recommendation Systems with Most Influential Peers [paper]
  190. [AAAI Workshop 26] CausalGraphX: A Counterfactual Graph Neural Network Framework for Explainable Systemic Risk Assessment [paper]
  191. [ACM MM 26] From Multimodal Observation to Interpretable Suggestions: Counterfactual Time-Expanded Relational Modeling of Surgical Teams [paper]
  192. [ACM Sustainability Week 26] Assessing Explanations of Graph Neural Networks for Dynamic Stability Assessment of Power Grids [paper]
  193. [ACM Sustainability Week 26] Toward Explainable GNN-Based Dynamic Stability Assessment via Joint Feature Attribution [paper]
  194. [ACM TCH 26] Explainable Graph Neural Networks: Understanding Brain Connectivity and Biomarkers in Dementia [paper]
  195. [ADMA 26] LLM-Guided Explanation Generation for Knowledge Graph Embedding-Based Node Classification [paper]
  196. [AI 26] BioGraphEX: Multi-Level Explainability in Graph Neural Networks for Trustworthy Biomedical AI [paper]
  197. [AJMSE 26] CF-TGNN: Counterfactual Explainable Temporal Graph Neural Networks for Supply Chain Disruption Prediction [paper]
  198. [ANNPR 26] Counterfactual Explanations for Graph Neural Networks in Patient Outcome Prediction [paper]
  199. [ARES 26] Distilling GNNs Into Symbolic Equations for Explainable Anomaly Detection [paper]
  200. [Artificial Intelligence Chemistry 26] Feature attribution in graph neural networks and its connection to chemical group contributions [paper]
  201. [BMJ Digital Health & AI 26] Explainable temporal graph-based CNNs for predicting hip replacement risk using EHR data [paper]
  202. [BigDIA 26] TAP-LLM: An Executable Attribution Framework for Temporal Event Graph Prediction [paper]
  203. [Bioinformatics 26] A case-based explainable graph neural network framework for mechanistic drug repositioning [paper]
  204. [Biomedical Signal Processing and Control 26] BrainIB++: Leveraging Graph Neural Networks and Information Bottleneck for Functional Brain Biomarkers in Schizophrenia [paper]
  205. [CIIT 26] Explainable Robotic Applications and Usage of Graph Neural Networks [paper]
  206. [CJA 26] A scene graph explanation framework for interpretable hyperspectral scene classification [paper]
  207. [CMC 26] Interpretable Smart Contract Vulnerability Detection with LLM-Augmented Hilbert-Schmidt Information Bottleneck [paper]
  208. [CONCEPTS 26] Interpretable GNN with Stable Concepts as Neurons [paper]
  209. [CSCWD 26] Rethinking the Rationalization: A Two-Step Decomposition for Graph Rationalization [paper]
  210. [ChemRxiv 26.10] Explainable Graph Neural Networks Reveal Molecular Features Associated with Umami Taste [paper]
  211. [ChemRxiv 26.10] Structural Resolution in Feature Attribution Analysis of Molecular Graph Neural Networks [paper]
  212. [ChemRxiv 26.11] FLAME: Fluorinated-motif Learning and Attribution for Molecular Explainability Applied to PFAS [paper]
  213. [Computer and Decision Making 26] The Explainability–Robustness Collision in Graph Neural Network Intrusion Detection: A Critical Survey [paper]
  214. [DEXA 26] XKG-IDS: Symbolic Graph Learning for Intrinsically Explainable IoT Intrusion Detection [paper]
  215. [DL 26] LPX-AbPoint: Abduction and Pinpointing for Explaining Link Predictions on DL Knowledge Graphs [paper]
  216. [DX 26] An Explainable GNN Framework for Component-Level Anomaly Diagnosis [paper]
  217. [EAI AIRO 26] XHBot: eXplainable Heterophily-aware Graph Neural Networks for Social Bot Detection [paper]
  218. [EDBT/ICDT Workshops 26] Counterfactual Explanations for Equivariant Graph Neural Networks: CE-EGNN for Molecular Property Regression [paper]
  219. [EDBT/ICDT-W 26] LogiX-Me: Logic-based Self-Explainable Message Passing GNN [paper]
  220. [EIEDP 26] ViCE-HGNN: a visual interactive system for explanation of heterogeneous graph neural networks [paper]
  221. [ESANN 26] Graph Diffusion Counterfactual Explanation [paper]
  222. [ESWA 26] Community-strength-based fairness in GNN explanations for heterogeneous link prediction [paper]
  223. [ESWA 26] DEX: Debiasing GNN explanations on imbalanced graphs [paper]
  224. [ESWA 26] X-GAD: Explainable graph-level anomaly detection via inter-graph anomalies [paper]
  225. [Electronics 26] GAFR-Net: A Graph Attention and Fuzzy-Rule Network for Interpretable Breast Cancer Image Classification [paper]
  226. [Electronics 26] LibXSub: A Framework for Detecting Binary Third-Party Library Reuse Regions Based on Explanatory Subgraphs [paper]
  227. [EuroVis 26] Topology-Aware Visual Analysis of GNN Explanations in Dynamic Graphs [paper]
  228. [FUDMA J Sci 26] Trustworthy Spatio-Temporal Graph Learning for Urban Event Forecasting: A Systematic Survey of Explainability, Fairness, and Their Intersection [paper]
  229. [Front. Med. 26] GCOA-Net: a graph-regularized cross-omics attention network for interpretable breast cancer molecular subtype classification [paper]
  230. [ICANN 26] Graph Neural Network Interpretation of Burst Initiation for In Silico Cortical Networks [paper]
  231. [ICCBR 26] Interpretable Graph-Level Anomaly Detection via Contrast with Normal Prototypes [paper]
  232. [ICCSIC 26] SCOPE-GNN: Semantic Causal OrPhicx Explanation for Graph Neural Networks using LLMs [paper]
  233. [ICDCA 26] X-GraphIDS: Explainable Graph Neural Network-Based Intrusion Detection System [paper]
  234. [ICDE 26] Explaining GNN Negatives Globally and Locally [paper]
  235. [ICDE 26] Interpreting Graph Inference with Skyline Explanations [paper]
  236. [ICEE 26] A Hybrid Explainability Framework for Graph-Based Movie Recommendation Using PinSAGE [paper]
  237. [ICIRCA 26] E-GraphSAGE with Explainability: Edge-Centric Graph Neural Networks for IoT Intrusion Detection across Heterogeneous Datasets [paper]
  238. [ICISS 26] Explainable Graph Neural Networks for Alzheimer's Disease Diagnosis Using Multi Modal MRI Data [paper]
  239. [ICITSIF 26] Explainable Graph Neural Networks for Drug Repurposing: Methods, Biological Interpretability, and Clinical Insights [paper]
  240. [ICPR 26] DotGreedX: Combining Scoring-Based Technique and Greedy Search for GNN Explainability [paper]
  241. [ICPR 26] GraphExplainer: Explaining nodes, edges and attributes of Graph Neural Network predictions [paper]
  242. [ICPR 26] Inherently Interpretable Graph Neural Networks via B-cos Alignment [paper]
  243. [ICSCAN 26] Explainable Graph Neural Framework for Transparent Cyber-Threat Detection [paper]
  244. [IEEE Access 26] QIEA-TGX+: Post-Hoc Explainer for Temporal Graph Neural Networks With Quantum-Inspired Evolutionary Algorithm [paper]
  245. [IEEE Access 26] GINTRIP: Interpretable Temporal Graph Regression using Information bottleneck and Prototype-based method [paper]
  246. [IEEE IoT 26] Multibranch Dendritic Computing for Federated Graph Neural Networks: Maintaining Interpretability Under Privacy Constraints [paper]
  247. [IEEE IoT-J 26] HetGAT-XAI: An Explainable Heterogeneous Graph Attention Network for IoT Intrusion Detection with Node-Type Attribution Analysis [paper]
  248. [IEEE TSG 26] Hybrid Attention-Augmented Self-Interpretable Channel-Grouped Graph Convolutional Network for Robust Distribution Network Fault Diagnosis [paper]
  249. [IET Conf. Proc. 26] Chemically-aware explainable graph neural network framework for drug-target interaction prediction [paper]
  250. [IIoTBDSC 26] A GNN-based vulnerability explanation method with learnable edge-type weights [paper]
  251. [IJCARS 26] ProtoFlow: interpretable and robust surgical workflow modeling with learned dynamic scene graph prototypes [paper]
  252. [IJCNN 26] GIN-Graph: A Generative Interpretation Network for Model-Level Explanation of Graph Neural Networks [paper]
  253. [IJMS 26] Explainable AI for Network Pharmacology: A Critical Framework for Interpreting Multi-Target Drug Discovery on Biological Graphs [paper]
  254. [IS 26] EXPLAIN-SOC: An Explainable Graph-Driven Framework for Threat Attribution and Security Operations Center Automation [paper]
  255. [ISR 26] Interpretable Recommendations and Parameter-Grounded LLM Explanations with Multigraph Attention [paper]
  256. [ISWC 26] CountTRuCoLa: Rule Learning for Interpretable Temporal Knowledge Graph Forecasting [paper]
  257. [ISWC 26] How Graphs Ground Large Language Models Counterfactuals for Subgraph Verbalizations [paper]
  258. [ITEGAM-JETIA 26] Explainable Recommendation in Graph Neural Networks Using Propagation Path Analysis and Counterfactual Graph Editing [paper]
  259. [IWCMC 26] Black-Box Operational Transparency: Gradient-Based Explainability for GNN-Based Network Performance Prediction [paper]
  260. [In Silico Res. Biomed. 26] Towards explainable molecular taste prediction using graph neural networks [paper]
  261. [In Silico Research in Biomedicine 26] Evaluating the role of attention-based message passing in explainable molecular toxicity prediction [paper]
  262. [Information Sciences 26] A unified self-explainable graph neural network framework for multi-level graph tasks [paper]
  263. [J Biomed Inform 26] Interpretable Graph Convolutional Networks for cardiovascular disease risk prediction in patients with Type 2 Diabetes Mellitus [paper]
  264. [J Chem Theory Comput 26] PoroNet: An Intrinsically Interpretable Pore Graph Neural Network for Resolving Pore-Level Adsorption in Metal–Organic Frameworks [paper]
  265. [J Cheminformatics 26] Systematic validation of graph neural network explanations against adverse outcome pathway reactive centers for skin sensitization [paper]
  266. [J Vis 26] GraphExVis: visual analytics for GNN interpretability and trustworthiness via local explanations [paper]
  267. [J. Cybersecur. Priv. 26] XGCN-GAT: An Explainable and Robustness-Aware Hybrid Graph Neural Network Framework for Android Malware Detection [paper]
  268. [JACS 26] FragNet: A Graph Neural Network for Molecular Property Prediction with Four Levels of Interpretability [paper]
  269. [JCIM 26] Explainability Methods from Machine Learning Detect Important Drugs' Atoms in Drug-Target Interactions [paper]
  270. [JCIM 26] Symmetry-Sensitive Analysis of Molecular Graph Neural Network Models [paper]
  271. [JCIM 26] TradePool: A Novel Interpretable Framework for Quantifying Atomic Attribution Values in Molecular Property Prediction [paper]
  272. [JCIM 26] Validating and Correcting Graph Neural Network Attention for Drug-Induced Liver Injury Prediction [paper]
  273. [KBS 26] Bridging dynamics and semantics: A unified perspective on explainable Graph Neural Networks based stream reasoning [paper]
  274. [KBS 26] Prototype learning with structural-semantic alignment for interpretable molecular relational learning [paper]
  275. [KR-DC 26] A framework for Counterfactual Explainability in Graph Neural Networks [paper]
  276. [Knowledge-Based Systems 26] GBExplainer: Generalizing adaptive-granularity explanations with granular balls for graph neural networks [paper]
  277. [MICCAI 26] BrainSTR: Spatio-Temporal Contrastive Learning for Interpretable Dynamic Brain Network Modeling [paper]
  278. [Mach Learn 26] From Latent to Lucid: Transforming Knowledge Graph Embeddings into Interpretable Structures with KGEPrisma [paper]
  279. [Mach Learn 26] On the Minimization of Graph Counterfactual Explanations: Theory and a Local Bounded Search Algorithm [paper]
  280. [Mach Learn Sci Technol 26] NuGraph2 with explainability: post-hoc explanations for geometric neural network predictions [paper]
  281. [Machines 26] Stochastic Mask Causal Graph Network for Industrial System Fault Diagnosis [paper]
  282. [NLDL 26] Predictive and Explanatory Uncertainties in Graph Neural Networks: A Case Study in Molecular Property Prediction [paper]
  283. [NLDL 27] Fragment-Level Graph Encoding for Interpretable Molecular Property Prediction [paper]
  284. [NeurIPS Workshop 26] Mechanistic Interpretability of Atmospheric Rivers in GraphCast [paper]
  285. [NeurIPS Workshop 26] Value or Attention: Investigating Layer-wise Relevance Propagation for Graph Attention Networks [paper]
  286. [Neurosymbolic AI 26] Knowledge Graphs and Explainable Artificial Intelligence (AI) for Drug Repurposing on Rare Diseases [paper]
  287. [OJ-COMS 26] SHAP-GSD: Temporal Multi-Granular Explanation Method for Graph Neural Networks in Network Intrusion Detection [paper]
  288. [PAKDD 26] Estimating Subgraph Importance with Structural Prior Domain Knowledge [paper]
  289. [Physiology & Behavior 26] From features to functional maps: An attention based framework for explainable memory-related brain network analysis [paper]
  290. [Procedia CS 26] Improving Explainability of Graph Neural Networks through Multi-Objective Evolutionary Computation [paper]
  291. [Procedia CS 26] Text-GCFExplainer: Global Counterfactual Explainer for Graph Neural Networks on Textual data [paper]
  292. [Research Square 26.11] SOFIA: Quantifying Sampling-Induced Explanation Instability in Graph Neural Networks [paper]
  293. [SAC 26] A Counterfactual and Reinforcement Learning-based Model-Agnostic Explanation Model on Knowledge Graphs [paper]
  294. [SEMANTiCS 26] Explaining RGNN Predictions on Knowledge Graphs via LRP [paper]
  295. [SSRN 26] Zero-Degradation Post-Hoc Explanations with Identity Pass-Through for Recurrent Graph Anomaly Detection [paper]
  296. [SSRN 26.08] CLExplainer: Generating Multi-Granularity GNN Explanations in Latent Semantic Space via Granular-Ball Computing [paper]
  297. [Sci Rep 26] Accumulated local effects and graph neural networks for link prediction [paper]
  298. [Sci Rep 26] Explainable artificial intelligence reveals divergent learning in pharmacophore-based hierarchical pooling graph neural networks [paper]
  299. [Symmetry 26] Causality-Aware and Explainable Self-Supervised Spatio-Temporal Graph Learning for Hardware Trojan Detection [paper]
  300. [TCAD 26] DSGK: Dynamic Subgraph Aggregation Graph Kernel Convolution Network for Interpretable Hotspot Detection [paper]
  301. [TCE 26] DSTEGNN: A Dynamic Spatio-Temporal Explainer Graph Neural Network for Securing Consumer Devices Against Malware Attacks [paper]
  302. [TII 26] CCG-IDS: A Causal Counterfactual Graph-Based Intrusion Detection System for Industrial IoT [paper]
  303. [TIST 26] ECLAIR: Explainable Causal Learning for Robust GNNs with Disentangled Uncertainty via Interventional Reasoning [paper]
  304. [VLDB 26] Database Views as Explanations for Relational Deep Learning [paper]
  305. [VLDB 26] DistShap: Scalable GNN Explanations with Distributed Shapley Values [paper]
  306. [VLSI-SoC 26] Self-Interpretable Hardware Trojan Detection on Gate-Level Netlists with Sufficient and Necessary GNN Explanations [paper]
  307. [WCCCT 26] Explainable Link Prediction for Continuous Dynamic Networks [paper]
  308. [bioRxiv 26.10] Interpreting Graph Neural Networks for Antibacterial Drug Repurposing against Acinetobacter baumannii [paper]
  309. [medRxiv 26.09] PCGS: biomarker and risk group identification for Pediatric Cancers via explainable Graph neural networks with Shapley values [paper]
  310. [Usenix Security 26] Cutting the Fuse: Actionable APT Attack Blocking in Provenance-based IDS [paper]
  311. [LOG 26] RAW-Explainer: Post-hoc Explanations of Path Reasoning Graph Neural Networks for Knowledge Graph Completion [paper]
  312. [DMKD 26] A method for the systematic generation of graph XAI benchmarks via Weisfeiler-Leman coloring [paper]
  313. [Ecol Model 26] Interpretability of Graph Neural Networks to Assess Effects of Global Change Drivers on Ecological Networks [paper]
  314. [The Innovation 26] CIDER: Counterfactual-Invariant Diffusion-based GNN Explainer for Causal Subgraph Inference [paper]
  315. [Geodata and AI 26] Explainable Global Wildfire Prediction Models using Graph Neural Networks [paper]

Year 2025

  1. [NMI 25] Towards unveiling sensitive and decisive patterns in explainable AI with a case study in geometric deep learning [paper]
  2. [NeurIPS 25] Robust Explanations of Graph Neural Networks via Graph Curvatures [paper]
  3. [NeurIPS 25] GnnXemplar: Exemplars to Explanations - Natural Language Rules for Global GNN Interpretability [paper]
  4. [NeurIPS 25] On Logic-based Self-Explainable Graph Neural Networks [paper]
  5. [NeurIPS 25] Interpretable and Parameter Efficient Graph Neural Additive Models with Random Fourier Features [paper]
  6. [NeurIPS 25] Sound Logical Explanations for Mean Aggregation Graph Neural Networks [paper]
  7. [ICML 25] On Explaining Equivariant Graph Networks via Improved Relevance Propagation [paper]
  8. [ICML 25] TopInG: Topologically Interpretable Graph Learning via Persistent Rationale Filtration [paper]
  9. [ICML 25] RISE: Radius of influence based subgraph extraction for 3d molecular graph explanation [paper]
  10. [ICML 25] Actionable Interpretability via Causal Hypergraphs: Unravelling Batch Size Effects in Deep Learning [paper]
  11. [ICML 25] CoDy: Counterfactual Explainers for Dynamic Graphs [paper]
  12. [ICML 25] Redundancy undermines the trustworthiness of self-interpretable GNNs [paper]
  13. [ICML 25] Beyond topological self-explainable GNNs: A formal explainability perspective [paper]
  14. [ICML 25] COMRECGC: Global Graph Counterfactual Explainer through Common Recourse [paper]
  15. [ICML 25] Graph Inverse Style Transfer for Counterfactual Explainability [paper]
  16. [ICML 25] WILTing Trees: Interpreting the Distance Between MPNN Embeddings [paper]
  17. [ICLR 25] Exact Computation of Any-Order Shapley Interactions for Graph Neural Networks [paper]
  18. [ICLR 25] How do large language models understand graph patterns? a benchmark for graph pattern comprehension [paper]
  19. [ICLR 25] From GNNs to Trees: Multi-Granular Interpretability for Graph Neural Networks [paper]
  20. [ICLR 25] Paradigm Shift of GNN Explainer from Label Space to Prototypical Representation Space [paper]
  21. [ICLR 25] Training-free Counterfactual Explanation for Temporal Graph Model Inference [paper]
  22. [ICLR 25] MuseGNN: Forming Scalable, Convergent GNN Layers that Minimize a Sampling-Based Energy [paper]
  23. [ICLR 25] Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNs [paper]
  24. [ICLR 25] Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks [paper]
  25. [ICLR 25] Towards Explaining the Power of Constant-depth Graph Neural Networks for Linear Programming [paper]
  26. [ICLR 25] Explanations of GNN on Evolving Graphs via Axiomatic Layer edges [paper]
  27. [ICLR 25] MAGE: Model-Level Graph Neural Networks Explanations via Motif-based Graph Generation [paper]
  28. [ICLR] LogicXGNN: Grounded Logical Rules for Explaining Graph Neural Networks [paper]
  29. [ICLR 25] BrainOOD: Out-of-distribution Generalizable Brain Network Analysis [paper]
  30. [ICLR 25] Towards Synergistic Path-based Explanations for Knowledge Graph Completion: Exploration and Evaluation [paper]
  31. [AAAI 25] Higher Order Structures For Graph Explanations [paper]
  32. [AAAI 25] Self-Explainable Graph Transformer for Link Sign Prediction [paper]
  33. [AAAI 25] Faithful and Accurate Self-Attention Attribution for Message Passing Neural Networks via the Computation Tree Viewpoint [paper]
  34. [AAAI 25] Graph Segmentation and Contrastive Enhanced Explainer for Graph Neural Networks [paper]
  35. [AAAI 25] Rule-Guided Graph Neural Networks for Explainable Knowledge Graph Reasoning [paper]
  36. [KDD 25] Explaining gnn explanations with edge gradients [paper]
  37. [KDD 25] Harnessing influence function in explaining graph neural networks [paper]
  38. [KDD 25] Global interpretable graph-level anomaly detection via prototype [paper]
  39. [KDD 25] Causal-aware graph neural architecture search under distribution shifts [paper]
  40. [KDD 25] 3dgraphx: Explaining 3d molecular graph models via incorporating chemical priors [paper]
  41. [KDD 25] Incorporating Retrieval-based Causal Learning with Information Bottlenecks for Interpretable Molecular Graph Learning [paper]
  42. [KDD 25] Is your explanation reliable: Confidence-aware explanation on graph neural networks [paper]
  43. [KDD 25] Finding Counterfactual Evidences for Node Classification [paper]
  44. [VLDB 25] eXpath: Explaining Knowledge Graph Link Prediction with Ontological Closed Path Rules [paper]
  45. [ACL 25] GraphNarrator: Generating Textual Explanations for Graph Neural Networks [paper]
  46. [TMLR 25] Hierarchical Language Model Design For Interpretable Graph Reasoning [paper]
  47. [TMLR 25] Explaining Node Embeddings [paper]
  48. [TMLR 25] Evaluating explainability techniques on discrete-time graph neural networks [paper]
  49. [TMLR 25] [RE] GNNBoundary: Towards Explaining Graph Neural Networks through the Lens of Decision Boundaries [paper]
  50. [TMLR 25] A Self-Explainable Heterogeneous GNN for Relational Deep Learning [paper]
  51. [TMLR 25] Disentangled and Self-Explainable Node Representation Learning [paper]
  52. [TMLR 25] Faithful Interpretation for Graph Neural Networks [paper]
  53. [TMLR 25] Global Graph Counterfactual Explanation: A Subgraph Mapping Approach [paper]
  54. [TMLR 25] Statistical Test for Saliency Maps of Graph Neural Networks via Selective Inference [paper]
  55. [TIFS 25] Identifying Backdoored Graphs in Graph Neural Network Training: An Explanation-Based Approach with Novel Metrics [paper]
  56. [TIFS 25] Interpretable Defense Against Structural Adversarial Attacks on Android Malware Detection [paper]
  57. [WWW 25] SEHG: bridging interpretability and prediction in self-explainable heterogeneous graph neural networks [paper]
  58. [WWW 25] Empowering Federated Graph Rationale Learning with Latent Environments [paper]
  59. [WWW 25] LP-DIXIT: Evaluating Explanations for Link Predictions on Knowledge Graphs using Large Language Models [paper]
  60. [ICDE 25] Revelio: Revealing Important Message Flows in Graph Neural Networks [paper]
  61. [TKDE 25] GAFExplainer: Global view explanation of graph neural networks through attribute augmentation and fusion embedding [paper]
  62. [TKDE 25] A Multi-Objective Explanation Framework for Graph Neural Networks [paper]
  63. [TOIS 25] SoREX: Towards Self-Explainable Social Recommendation with Relevant Ego-Path Extraction [paper]
  64. [WSDM 25] Impo: Interpretable memory-based prototypical pooling [paper]
  65. [IJCAI 25] Explainable graph neural networks via structural externalities [paper]
  66. [IJCAI 25] DGExplainer: Explaining Dynamic Graph Neural Networks via Relevance Back-propagation [paper]
  67. [IJCAI 25] Explainable Graph Representation Learning via Graph Pattern Analysis [paper]
  68. [IJCAI 25] Towards comprehensive and prerequisite-free explainer for graph neural networks [paper]
  69. [IJCAI 25] Rewarding Explainability in Drug Repurposing with Knowledge Graphs [paper]
  70. [ICDM 25] Explanations Go Linear: Post-Hoc Explainability for Tabular Data with Interpretable Meta-Encoding [paper]
  71. [CIKM 25] Assessing Natural Language Explanations of Relational Graph Neural Networks [paper]
  72. [CIKM 25] CHEM: Causally and Hierarchically Explaining Molecules [paper]
  73. [TNNLS 25] CiRLExplainer: Causality-Inspired Explainer for Graph Neural Networks via Reinforcement Learning [paper]
  74. [TNNLS 25] Gen-graphex: Generative in-distribution graph explanations for time-efficient model-level interpretability of gnns [paper]
  75. [TKDD 25] DyExplainer: Explainable Dynamic Graph Neural Networks [paper]
  76. [TKDD 24] Efficient GNN Explanation via Learning Removal-based Attribution [paper]
  77. [TKDD 25] Towards Prototype-Based Self-Explainable Graph Neural Network [paper]
  78. [ACM TIST 25] Help Me Screen: Analyzing and Predicting the Success of Start-ups in Dynamic Venture Capital Networks [paper]
  79. [ACM TIST 25] Gcfexplainer: Global counterfactual explainer for graph neural networks [paper]
  80. [Engineering Applications of Artificial Intelligence] Dual Explanations via Subgraph Matching for Malware Detection [paper]
  81. [Information Sciences 25] On the Consistency of GNN Explanations for Malware Detection [paper]
  82. [TETCI 25] Interpretable and Adaptive Graph Contrastive Learning With Information Sharing for Biomedical Link Prediction [paper]
  83. [ACM Computing Surveys] Can Graph Neural Networks be Adequately Explained? A Survey [paper]
  84. [IEEE TNSRE] Finding Neural Biomarkers for Motor Learning and Rehabilitation using an Explainable Graph Neural Network [paper]
  85. [Springer FCS] Learning from shortcut: a shortcut-guided approach for explainable graph learning [paper]
  86. [NN] Local interpretable spammer detection model with multi-head graph channel attention network [paper]
  87. [Applied Intelligence] KnowGNN: a knowledge-aware and structure-sensitive model-level explainer for graph neural networks [paper]
  88. [Measurement Science and Technology] Tree structure guided graph neural networks for soft sensing and anomaly regulation [paper]
  89. [Data Science for Transportation] Exploring the Potential and Utility of Graph Neural Networks in Crash Analysis and Safety Assessment [paper]
  90. [IEEE Access] MOOC Dropout Prediction Using Explainable Relational Graph Convolution [paper]
  91. [IEEE Access 25] Noise-Robust and Interpretable EEG Classification of Hyperactive Disorders Using Graph Convolutional Network [paper]
  92. [IEEE Access 25] Explainable Document Classification via Concept Whitening and Stable Graph Patterns [paper]
  93. [IEEE Access 25] Explainable Graph Neural Networks for Power Grid Fault Detection [paper]
  94. [ICDMW 25] A Research and Development Portfolio of GNN Centric Malware Detection, Explainability, and Dataset Curation [paper]
  95. [Journal of Statistical Theory and Applications 25] BetaExplainer: A Probabilistic Method to Explain Graph Neural Networks [paper]
  96. [Machine Learning 25] MBExplainer: Multilevel bandit-based explanations for downstream models with augmented graph embeddings [paper]
  97. [Sci Rep 25] Fraud detection and explanation in medical claims using GNN architectures [paper]
  98. [Sci Rep 25] Interpretable deep learning of single-cell and epigenetic data reveals novel molecular insights in aging [paper]
  99. [Sci Rep 25] Drug discovery and mechanism prediction with explainable graph neural networks [paper]
  100. [Sci Rep 25] Mixture-of-Experts Graph Transformers for Interpretable Particle Collision Detection [paper]
  101. [ICCBD+AI 25] Learning Explanations of Graph Neural Networks via Multi-granularity Subgraph Masking [paper]
  102. [ITSC 25] An Ante-Hoc Explainable Graph Attention Network for Routing Optimization [paper]
  103. [PRICAI 25] Interpretable Brain Network Analysis for Psychiatric Diagnosis Using Fuzzy Logic [paper]
  104. [Comput Ind Eng 25] HeteroX: An interpretable Dual-tier Heterogeneous Graph for sustainable investment decisions [paper]
  105. [Comput Mater Continua 25] Graph-Based Intrusion Detection with Explainable Edge Classification Learning [paper]
  106. [CIoTSC 25] Explainable Book Recommendations via Graph Convolutional Networks [paper]
  107. [CyberSciTech 25] CFExplainerTG: Counterfactual Explanation for Temporal Graph Neural Networks in Cybersecurity [paper]
  108. [Concurr Comput Pract Exp 25] GTCExplainer: Interpretable Graph Convolutional Networks for Molecular Activity Prediction [paper]
  109. [Mach Learn 25] Bridging XAI and spectral analysis to investigate the inductive biases of deep graph networks [paper]
  110. [Mach Learn 25] An end-to-end explainability framework for spatio-temporal predictive modeling [paper]
  111. [Mach Learn 25] Self explainable graph convolutional recurrent network for spatio-temporal forecasting [paper]
  112. [Data Min Knowl Discov 25] Leveraging internal representations of GNNs with Shapley values [paper]
  113. [Pattern Recogn. 25] Trace2Vec: Detecting complex multi-step attacks with explainable graph neural network [paper]
  114. [J King Saud Univ Comput Inf Sci 25] DHGNN: A dynamic heterogeneous graph neural network for interpretable inventor collaboration prediction [paper]
  115. [DSPP 25] An Efficient Explainability Framework for Graph Neural Networks [paper]
  116. [ASP-DAC 25] Understand and Detect: Lithographic Hotspot Detection by the Interpretable Graph Attention Network [paper]
  117. [CDVE 25] Towards Interpretable GNNs: A Feasibility Study on Subgraph-Level Explanation Classification [paper]
  118. [KBS 25] Fair path explanations for heterogeneous link prediction from a community perspective [paper]
  119. [KBS 25] Explainability-Based Adversarial Attack on Graphs Through Edge Perturbation [paper]
  120. [KBS 25] Understanding the Robustness of Graph Neural Networks against Adversarial Attacks [paper]
  121. [SMC 25] MIP-Explainer: An Explainability Method for Graph Neural Networks Based on Mutual Information [paper]
  122. [Discov Artif Intell 26] GraphAware: Interpretable machine learning on graphs [paper]
  123. [Neurocomputing 25] STD-Explain: Generalizing explanations for spatio-temporal graph convolutional networks based on spatio-temporal decoupled perturbation [paper]
  124. [Neurocomputing 25] Explaining Graph Neural Networks with Mixed-Integer Programming [paper]
  125. [TPDS 25] XDGNN: Efficient Distributed GNN Training via Explanation-Guided Subgraph Expansion [paper]
  126. [J Softw Evol Process 25] Towards Explainable Code Readability Classification With Graph Neural Networks [paper]
  127. [REW 25] Research on Requirement Vulnerability Detection Method Based on Graph Neural Network and Counterfactual Explanation [paper]
  128. [Appl Soft Comput 25] A multi-hop Shapley-based framework for graph convolutional network node classification explanation [paper]
  129. [Appl Soft Comput 25] Auto-configured explainable graph neural networks for multi-site pollution prediction [paper]
  130. [PLOS Complex Syst 25] Determining graphlet explanations for machine learning on graphs [paper]
  131. [TNSM 25] Explainable GNN-Based Approach to Fault Forecasting in Cloud Service Debugging [paper]
  132. [ICETCI 25] Making Sense of Communities: A Survey on XAI Techniques in Graph Community Detection [paper]
  133. [Appl Intell 25] EGNet: explainable graph neural network with similarity explanation for medication recommendation [paper]
  134. [Appl Intell 25] Pgcnn: an interpretable graph convolutional neural network for predicting the mechanical properties of Ti-6Al-4V alloy [paper]
  135. [RIME 25] X-node: Self-explanation is all we need [paper]
  136. [RIME 25] X-node: Self-explanation is all we need [paper]
  137. [Pattern Recognit 26] Explanation-guided backdoor defense for ID and OOD attacks in graph neural networks [paper]
  138. [J Signal Process Syst 25] HGExplainer: Toward Interpretable Heterogeneous Graph Neural Networks via Meta-path Perturbation [paper]
  139. [ECML PKDD 25] Faithful Explanations for Graph Classification Using Logic [paper]
  140. [ECML PKDD 25] A True-to-the-Model Benchmark for Edge-Level Attributions of GNN Explainers [paper]
  141. [J Chem Inf Model 25] Explainable graph neural networks in chemistry: Combining attribution and uncertainty quantification [paper]
  142. [TCCN 25] Geek-explainer: an efficient interpretation method for graph neural networks in SDN [paper]
  143. [Neural Netw 25] Learning model-level explanations of graph neural networks via subgraph order embedding space [paper]
  144. [Neural Netw 25] Community-influencing path explanation for link prediction in heterogeneous graph neural network [paper]
  145. [Neural Netw 25] Explainable multiplex graph propagational network with multimodal neuroimage integration for dementia subtype diagnosis [paper]
  146. [IJCNN 25] Visual Analytics for Explainable AI with Spatio-Temporal Data: A Comparative Study [paper]
  147. [IJCNN 25] CRoCExplainer: A Tool to Explain Graph Learning with Improved Connectedness Representation. [paper]
  148. [Thesis 25] Towards Explainable AI on Graph Neural Networks: XAIG [paper]
  149. [Thesis] Explainable Deep Graph Learning: From Feature Attribution to Relational Reasoning [paper]
  150. [Thesis] Explainable GNNs in Biomedicine [paper]
  151. [Thesis 25] ConceptGNNExplainer: A Self-Supervised Framework for Concept-Based Explanations of Graph Neural Network Predictions [paper]
  152. [Thesis 25] Rules and Distributions for Explainable Machine Learning [paper]
  153. [Thesis 25] Understanding Neural Burst Patterns Through Graph Neural Network Explainability in Simulated Neuronal Networks [paper]
  154. [Thesis 25] Structural Interpretability for Deep Learning in Quantum Chemistry [paper]
  155. [Thesis 25] Fast and Accurate Explanations of Graph Neural Networks [paper]
  156. [Thesis 25] Enhancing Drug Repositioning With Interpretable Graph Neural Network Models on Biomedical Knowledge Graphs [paper]
  157. [Thesis 25] Graph Neural Networks for Interpretable Biomedical Data Analysis in Genomics and Structural Biology [paper]
  158. [Inf Process Manag 25] Augmented graph information bottleneck with type-aware periodicity heterogeneity for explainable crime prediction [paper]
  159. [FAccT 25] C2explainer: Customizable mask-based counterfactual explanation for graph neural networks [paper]
  160. [Inf Fusion 25] Explaining spatio-temporal graph convolutional networks with spatio-temporal constraints perturbation for action recognition [paper]
  161. [Inf Fusion 25] InsGNN: Interpretable spatio-temporal graph neural networks via information bottleneck [paper]
  162. [Inf Fusion 25] GL-BKGNN: Graphlet-based Bi-Kernel Interpretable Graph Neural Networks [paper]
  163. [Inf Fusion 25] InsGNN: Interpretable spatio-temporal graph neural networks via information bottleneck [paper]
  164. [Inf Fusion 25] Explainable knowledge graph embeddings for industrial process monitoring & control [paper]
  165. [Inf Fusion 25] Heterogeneous Graph Neural Networks with Post-hoc Explanations for Multi-modal and Explainable Land Use Inference [paper]
  166. [Inf Fusion 25] RSRule: Relation-level semantic-driven rule learning for explainable extrapolation on temporal knowledge graphs [paper]
  167. [TVCG 25] SLInterpreter: An Exploratory and Iterative Human-AI Collaborative System for GNN-Based Synthetic Lethal Prediction [paper]
  168. [ICC 25] Towards Self-Explainable Information Cascade Popularity Prediction [paper]
  169. [Modelling 25] TE-G-SAGE: Explainable Edge-Aware Graph Neural Networks for Network Intrusion Detection [paper]
  170. [ICCNC 25] AMSVGAE-Based Causal Inference for Interpretable Graph Neural Networks [paper]
  171. [JCad 25] A Visual Recommendation Analysis System Based on the Interpretable Graph Neural Network [paper]
  172. [OpenReview 25] DR-CFGNN: A Completion-Aware Framework for Counterfactual Explainability in Graph Neural Networks [paper]
  173. [OpenReview 25] LaCore: Laplacian Cohesive Subgraphs for Graph Representation Learning [paper]
  174. [OpenReview 25] Self-Guided Explanation for Graph Neural Networks with Semi-Supervision [paper]
  175. [OpenReview 25] Self-explainable Molecular Property Prediction via Multi-view Hypergraph Learning [paper]
  176. [OpenReview 25] Interpretable Hypergraph Neural Additive Networks [paper]
  177. [OpenReview 25] Interpretable Graph Embeddings: Feature-Level Decomposition for Trustworthy Graph Neural Networks [paper]
  178. [OpenReview 25] TAME: A Task-Agnostic Framework for Robust Graph Neural Network Explanations via Structural Mixup [paper]
  179. [OpenReview 25] MatchEx: Model-Level GNN Explanations with Multi-Granular Insights [paper]
  180. [OpenReview 25] Interactive and Explainable Graph Neural Networks with Uncertainty Awareness and Adaptive Human Feedback [paper]
  181. [OpenReview 25] SynHING: Synthetic Heterogeneous Information Network Generation for Graph Learning and Explanation [paper]
  182. [Arxiv 25.12] Enhancing Explainability of Graph Neural Networks Through Conceptual and Structural Analyses and Their Extensions [paper]
  183. [Arxiv 25.11] ARM-Explainer -- Explaining and improving graph neural network predictions for the maximum clique problem using node features and association rule mining [paper]
  184. [Arxiv 25.10] Interpreting GNN-based IDS Detections Using Provenance Graph Structural Features [paper]
  185. [Arxiv 25.09] SEASONED: Semantic-Enhanced Self-Counterfactual Explainable Detection of Adversarial Exploiter Contracts [paper]
  186. [Arxiv 25.08] NAEx: A Plug-and-Play Framework for Explaining Network Alignment [paper]
  187. [Arxiv 25.08] Explainable Attention-Guided Stacked Graph Neural Networks for Malware Detection [paper]
  188. [Arxiv 25.08] From Binary to Continuous: Stochastic Re-Weighting for Robust Graph Explanation [paper]
  189. [Arxiv 25.06] FIGNN: Feature-Specific Interpretability for Graph Neural Network Surrogate Models [paper]
  190. [Arxiv 25.06] GNNAnatomy: Systematic Generation and Evaluation of Multi-Level Explanations for Graph Neural Networks [paper]
  191. [Arxiv 25.05] LM^2otifs: An Explainable Framework for Machine-Generated Texts Detection [paper]
  192. [Arxiv 25.05] MetaGMT: Improving Actionable Interpretability of Graph Multilinear Networks via Meta-Learning Filtration [paper]
  193. [Arxiv 25.03] Identifying evidence subgraphs for financial risk detection via graph counterfactual and factual reasoning [paper]
  194. [Arxiv 25.02] Recent advances in malware detection: Graph learning and explainability [paper]
  195. [NeurIPS Workshop 25] Superposition in Graph Neural Networks [paper]
  196. [NeurIPS Workshop 25] FireGNN: Neuro-Symbolic Graph Neural Networks with Trainable Fuzzy Rules for Interpretable Medical Image Classification [paper]
  197. [NeurIPS Workshop 25] MINAR: Mechanistic Interpretability for Neural Algorithmic Reasoning [paper]
  198. [KDD Workshop 25] Z-rex: human-interpretable GNN explanations for real estate recommendations [paper]
  199. [bioRxiv 25.12] A Concept-Driven Disentanglement Framework for Interpretable Graph Neural Networks in Structure-Function Coupling [paper]
  200. [Neural Networks] On the probability of necessity and sufficiency of explaining Graph Neural Networks: A lower bound optimization approach [paper]
  201. [Preprint 25] Faithful and Diverse Subgraph as Explanation for Large Probabilistic Graphical Models [paper]
  202. [Preprint 25] Game theoretic explainers for graph neural networks [paper]
  203. [Preprint ] Method for Explaining Regression Prediction Results Using Machine Learning on Temporal Graph Data [paper]
  204. [Neural Comput Appl 25] Explainability graph neural networks with nearest neighbor estimate interpretations [paper]
  205. [Neural Comput Appl 25] GraphXAI: a survey of graph neural networks (GNNs) for explainable AI (XAI) [paper]
  206. [DASFAA 25] Meta Relation Assisted Explanatory Model for Heterogeneous Graph Neural Networks [paper]
  207. [DASFAA 25] Enhancing Explanations of Graph Neural Networks via Bridging Model-Level and Instance-Level Explainers [paper]
  208. [ACM Trans Inf Syst 25] CaGE: A causality-inspired graph neural network explainer for recommender systems [paper]
  209. [WIREs DMKD 25] Exploring Causal Learning Through Graph Neural Networks: An In‐Depth Review [paper]
  210. [Big Data Res 25] Explainable malware detection through integrated graph reduction and learning techniques [paper]
  211. [Brief Bioinform 25] Interpretable high-order knowledge graph neural network for predicting synthetic lethality in human cancers [paper]
  212. [TDSC 25] SIGFinger: A subtle and interactive GNN fingerprinting scheme via spatial structure inference perturbation [paper]
  213. [Curr Bioinform 25] A graphlet-based explanation generator for graph neural networks over biological datasets [paper]
  214. [Inf Sci 25] Towards self-interpretable review spammer group detection [paper]
  215. [Mach Intell Res 25] Counterfactual learning on graphs: A survey [paper]
  216. [Autom Constr 25] Automatic clash avoidance in steel reinforcement design using explainable graph neural networks and rebar embedding learning [paper]
  217. [IEEE JBHI 25] ExplainMIX: explaining drug response prediction in directed graph neural networks with multi-omics fusion [paper]
  218. [ACM TORS 25] Joint Factual and Counterfactual Explanations for Top-k GNN-based Recommendations [paper]
  219. [J Comput Biol 25] Building explainable graph neural network by sparse learning for the drug-protein binding prediction [paper]
  220. [J Comput Inf Syst 25] Attributing stealth cyberattacks via Temporal probabilistic graph neural networks [paper]
  221. [XAI 25] Explaining vision gnns: A semantic and visual analysis of graph-based image classification [paper]
  222. [XAI 25] Exploring Ensemble Strategies for Graph Counterfactual Explanations [paper]
  223. [XAI 25] GraphXAIN: Narratives to Explain Graph Neural Networks [paper]
  224. [XAI 25] Improving Counterfactual Truthfulness for Molecular Property Prediction through Uncertainty Quantification [paper]
  225. [XAI 25] Interpretable Link Prediction via Neural-Symbolic Reasoning [paper]
  226. [ICSTW 25] Structural Backdoor Attack on IoT Malware Detectors via Graph Explainability [paper]
  227. [IEEE Trans Comput Soc Syst 25] MLFormer: Unleashing Efficiency Without Attention for Multimodal Knowledge Graph Embedding [paper]
  228. [PeerJ Comput Sci 25] TurkSentGraphExp: an inherent graph aware explainability framework from pre-trained LLM for Turkish sentiment analysis [paper]
  229. [Electronics 25] Post Hoc Multi-Granularity Explanation for Multimodal Knowledge Graph Link Prediction [paper]
  230. [TCSS 25] Contrastive Token-Level Explanations for Graph-Based Rumor Detection [paper]
  231. [EPJ Data Sci 25] A new approach to estimate neighborhood socioeconomic status using supermarket transactions and GNNs [paper]
  232. [ICBCB 25] Graph Neural Networks Based Explainability of Drug-Target Interactions [paper]
  233. [ICAACE 25] CStaG: A Causality-Inspired Stable Generative Model for the Interpretation of Graph Neural Networks [paper]
  234. [Procedia Comput Sci 25] Enhancing Stock Market Prediction with Temporal Graph Neural Networks and Large Language Model-Based Explainability [paper]
  235. [CEUR 25] Quantitative Assessment of GNN Counterfactual Explanation Robustness and Reproducibility under Adversarial Influence [paper]
  236. [CEUR 25] ActiMine-GNN: Activation Mining and Interpretability in Graph Neural Networks [paper]
  237. [CEUR 25] An Empirical Study of the Consistency between Protocols for Evaluating Explanations of Predicted Links in Knowledge Graphs [paper]
  238. [ResearchGate 25] GraphX-Forecast: A Unified Survey on the Synergy of GNNs, Uncertainty, and XAI for Multi-Horizon Time Series Forecasting [paper]
  239. [Informed Machine Learning 25] On the Interplay of Subset Selection and Informed Graph Neural Networks [paper]
  240. [AISTATS 25] Natural Language Counterfactual Explanations for Graphs Using Large Language Models [paper]
  241. [AAMAS 25] Evaluating and Improving Graph-based Explanation Methods for Multi-Agent Coordination [paper]
  242. [ACM Comput Surv 25] Review of Explainable Graph-Based Recommender Systems [paper]
  243. [AJCAI 25] Graph-based Integrated Gradients for Explaining Graph Neural Networks [paper]
  244. [ANSyA 25] Neurosymbolic Methods for Explainable Graph Neural Networks: A Survey [paper]
  245. [Acta Infologica 25] Explainable Graph Neural Networks in Intensive Care Unit Mortality Prediction: Edge-Level and Motif-Level Analysis [paper]
  246. [Artif Intell Med 25] DRExplainer: Quantifiable Interpretability in Drug Response Prediction with Directed Graph Convolutional Network [paper]
  247. [Artif Intell Med 25] PhenoLinker: Phenotype-gene link prediction and explanation using heterogeneous graph neural networks [paper]
  248. [BMC Bioinformatics 25] Unveiling molecular moieties through hierarchical Grad-CAM graph explainability [paper]
  249. [CHIL 25] Self-Explaining Hypergraph Neural Networks for Diagnosis Prediction [paper]
  250. [CMMR 25] MUSE-Explainer: Counterfactual Explanations for Symbolic Music Graph Classification Models [paper]
  251. [COLING 25] Discrete Subgraph Sampling for Interpretable Graph based Visual Question Answering [paper]
  252. [COMPSAC 25] Smart Contract Reentrancy Vulnerability Localization Using Explainable Graph Neural Networks [paper]
  253. [CSCWD 25] PGAid: An Interpreter for Provenance-Based Intrusion Detection Based on DeepAid [paper]
  254. [CVIDL 25] Towards Self-Interpretable Graph Neural Networks via Augmentation-Contrastive Learning [paper]
  255. [CVPL 25] DeepFRI Demystified: Interpretability vs. Accuracy in AI Protein Function Prediction [paper]
  256. [Chaos 25] Explainable AI for analyzing the decision of GNNs at predicting dynamic stability of complex oscillator networks [paper]
  257. [DSC 25] Path-Based Explanation for Temporal Knowledge Graph Completion [paper]
  258. [Digital Discovery 25] ACES-GNN: can graph neural network learn to explain activity cliffs? [paper]
  259. [ESWC 25] Path of Time: Explanations for Temporal Knowledge Graph Completion through Chronological Regulation [paper]
  260. [EXPLIMED@ECAI 25] Massive Activations in Graph Neural Networks: Decoding Attention for Domain-Dependent Interpretability [paper]
  261. [Eng. Appl. Artif. Intell. 25] A novel two-stage variables contribution analysis method toward explainable graph convolutional network-based industrial fault diagnosis [paper]
  262. [GCWCN 25] Enabling Explainable NLP Through Graph Neural Network Architectures [paper]
  263. [HPCC 25] Counterfactual GraphLIME-Enabled Explainable Adversarial Defense for Graph-Based Intrusion Detection Using Residual GAN-FGSM Framework [paper]
  264. [ICAI 25] Explain Graph Node Classification via Counterfactual Memorization [paper]
  265. [ICAMIDA 25] Advancements in Explainable AI for Graph Neural Networks [paper]
  266. [ICBBB 25] Exploring Cancer Genomics with Graph Convolutional Networks: A Comparative Explainability Study with Integrated Gradients and SHAP [paper]
  267. [ICONIP 25] Interpretable Smart Contract Vulnerability Detection with Graph Information Bottleneck [paper]
  268. [IFSA-NAFIPS 25] Explainable Fuzzy GNNs for Leak Detection in Water Distribution Networks [paper]
  269. [IJACSA 25] Graph Neural Networks with Shapley-Value Explanations for Hierarchical Recommendation Systems [paper]
  270. [IJCAI workshop 25] Interpreting CFD Surrogates through Sparse Autoencoders [paper]
  271. [IJCKG 25] KGRAG-Ex: Explainable Retrieval-Augmented Generation with Knowledge Graph-based Perturbations [paper]
  272. [IPTA 25] A Multi-Method Explainability Evaluation of a Graph-Based Neural Network for Alertness Detection [paper]
  273. [IV 25] InteractiveGNNExplainer: A Visual Analytics Framework for Multi-Faceted Understanding and Probing of Graph Neural Network Predictions [paper]
  274. [InCIT 25] LiteXGNN: A Lightweight Explainable Graph Neural Network for Malware Detection with Control Flow Graph Explainability [paper]
  275. [J Biomed Inform 25] A graph neural network explainability strategy driven by key subgraph connectivity [paper]
  276. [JCC 25] MMGCF: Generating Counterfactual Explanations for Molecular Property Prediction via Motif Rebuild [paper]
  277. [JCIM 25] Path-Based Graph Neural Network for Drug Synergy Prediction and Interpretation [paper]
  278. [JOCN 25] Interpretable optical network fault detection and localization with multi-task graph prototype learning [paper]
  279. [JURIX 25] Towards Interpretable Hierarchical Graph Neural Networks in Criminal Law [paper]
  280. [KR 25] Logical Expressivity and Explanations for Monotonic GNNs with Scoring Functions [paper]
  281. [MICCAI 25] Causality-Inspired Graph Neural Network for Interpretable Strabismus Subtype Classification [paper]
  282. [MLST 25] Interpretation of chemical reaction yields with graph neural additive network [paper]
  283. [MedIA 25] Graph-based prototype inverse-projection for identifying cortical sulcal pattern abnormalities in congenital heart disease [paper]
  284. [MedIA 25] MetaExplainer: Revisit domain generalization of functional connectome analyses from the perspective of explainability [paper]
  285. [NLDL 25] Graph Counterfactual Explainable AI via Latent Space Traversal [paper]
  286. [NeSy 25] Distilling KGE black boxes into interpretable NeSy models [paper]
  287. [NeSy 25] Do graph neural network states contain graph properties? [paper]
  288. [Phys Chem Chem Phys 25] Explainable GNN-derived structure–property relationships in interstitial-alloy materials [paper]
  289. [Research 25] Molecular Merged Hypergraph Neural Network for Explainable Solvation Gibbs Free Energy Prediction [paper]
  290. [SIS 25] EGNAN: An Enhanced Method for Interpretable Graph Neural Networks [paper]
  291. [SOCO 25] Explainable Graph Neural Networks for Omics-Based Cancer Classification [paper]
  292. [SOFSEM 25] Knowledge Neurons in the Knowledge Graph-based Link Prediction Models [paper]
  293. [SPW 25] Ignoring Directionality Leads to Compromised Graph Neural Network Explanations [paper]
  294. [Sustain Energy Grids Netw 25] Edge-level explainable graph neural networks with network centric features for transmission line failure prediction in power grids [paper]
  295. [TBD 25] scProGraph: A Cell Bagging Strategy for Cell Type Annotation With Gene Interaction-Aware Explainability [paper]
  296. [TCBBIO 25] DGX: Uncovering General Behavior of Deep Graph Models With Model-Level Explanation [paper]
  297. [Vis Comput Ind Biomed Art 25] Visual explainable artificial intelligence for graph-based visual question answering and scene graph curation [paper]

Year 2024

  1. [TPAMI 24] Towards Inductive and Efficient Explanations for Graph Neural Networks [paper]
  2. [TPAMI 24] PAGE: Prototype-Based Model-Level Explanations for Graph Neural Networks [paper]
  3. [NeurIPS 24] RegExplainer: Generating Explanations for Graph Neural Networks in Regression Task [paper]
  4. [NeurIPS 24] GraphTrail: Translating GNN Predictions into Human-Interpretable Logical Rules [paper]
  5. [ICML 24] Generating In-Distribution Proxy Graphs for Explaining Graph Neural Networks [paper]
  6. [ICML 24] Predicting and Interpreting Energy Barriers of Metallic Glasses with Graph Neural Networks [paper]
  7. [ICML 24] Graph Neural Network Explanations are Fragile [paper]
  8. [ICML 24] How Interpretable Are Interpretable Graph Neural Networks? [paper]
  9. [ICML 24] Feature Attribution with Necessity and Sufficiency via Dual-stage Perturbation Test for Causal Explanation [paper]
  10. [ICML 24] Explaining Graph Neural Networks via Structure-aware Interaction Index [paper]
  11. [ICML 24] EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Time [paper]
  12. [ICLR 24] GraphChef: Decision-Tree Recipes to Explain Graph Neural Networks [paper]
  13. [ICLR 24] GOAt: Explaining Graph Neural Networks via Graph Output Attribution [paper]
  14. [ICLR 24] Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networks [paper]
  15. [ICLR 24] GNNX-BENCH: Unravelling the Utility of Perturbation-based GNN Explainers through In-depth Benchmarking [paper]
  16. [ICLR 24] UNR-Explainer: Counterfactual Explanations for Unsupervised Node Representation Learning Models [paper]
  17. [AAAI 24] Generating Diagnostic and Actionable Explanations for Fair Graph Neural Networks [paper]
  18. [AAAI 24] Stratifed GNN Explanations through Sufficient Expansion [paper]
  19. [AAAI 24] Factorized Explainer for Graph Neural Networks [paper]
  20. [AAAI 24] Self-Interpretable Graph Learning with Sufficient and Necessary Explanations
  21. [AAAI 24] Explainable Origin-Destination Crowd Flow Interpolation via Variational Multi-Modal Recurrent Graph Auto-Encoder [paper]
  22. [TMLR 24] InduCE: Inductive Counterfactual Explanations for Graph Neural Networks [paper]
  23. [TMLR 24] Graphon-Explainer: Generating Model-Level Explanations for Graph Neural Networks using Graphons [paper]
  24. [PLDI 24] PL4XGL: A Programming Language Approach to Explainable Graph Learning [paper]
  25. [Usenix Security 24] INSIGHT: Attacking Industry-Adopted Learning Resilient Logic Locking Techniques Using Explainable Graph Neural Network [paper]
  26. [SIGMOD 24] View-based Explanations for Graph Neural Networks [paper]
  27. [ACM SIGMOD Record] The Road to Explainable Graph Neural Networks [paper]
  28. [Thesis UCLA] Explainable Artificial Intelligence for Graph Data [paper]
  29. [Thesis UVA] Algorithmic Fairness in Graph Machine Learning: Explanation, Optimization, and Certification [paper]
  30. [KDD 24] SEFraud: Graph-based Self-Explainable Fraud Detection via Interpretative Mask Learning [paper]
  31. [KDD 24] Self-Explainable Temporal Graph Networks based on Graph Information Bottleneck [paper]
  32. [KDD 24] Unveiling Global Interactive Patterns across Graphs: Towards Interpretable Graph Neural Networks [paper]
  33. [ICDE 24] Generating Robust Counterfactual Witnesses for Graph Neural Networks [paper]
  34. [ICDE 24] SES: Bridging the Gap Between Explainability and Prediction of Graph Neural Networks [paper]
  35. [ICSE 24] Coca: Improving and Explaining Graph Neural Network-Based Vulnerability Detection Systems [paper]
  36. [AISTATS 24] Two Birds with One Stone: Enhancing Uncertainty Quantification and Interpretability with Graph Functional Neural Process [paper]
  37. [WWW 24] Game-theoretic Counterfactual Explanation for Graph Neural Networks [paper]
  38. [WWW 24] EXGC: Bridging Efficiency and Explainability in Graph Condensation [paper]
  39. [WWW 24] Adversarial Mask Explainer for Graph Neural Networks [paper]
  40. [WWW 24] Globally Interpretable Graph Learning via Distribution Matching [paper]
  41. [WWW 24] GNNShap: Scalable and Accurate GNN Explanation using Shapley Values [paper]
  42. [IEEE TDSC 24] TrustGuard: GNN-based Robust and Explainable Trust Evaluation with Dynamicity Support [paper]
  43. [ISSTA 24] Graph Neural Networks for Vulnerability Detection: A Counterfactual Explanation [paper]
  44. [ECCV 24] Graph Neural Network Causal Explanation via Neural Causal Models [paper] [OpenReview]
  45. [TNNLS 24] BrainIB: Interpretable Brain Network-based Psychiatric Diagnosis with Graph Information Bottleneck [paper]
  46. [TKDE 24] On Regularization for Explaining Graph Neural Networks: An Information Theory Perspective [paper]
  47. [TAI 24] Learning Counterfactual Explanation of Graph Neural Networks via Generative Flow Network [paper]
  48. [TAI 24] Traffexplainer: A Framework towards GNN-based Interpretable Traffic Prediction [paper]
  49. [TMC 24] HGExplainer: Heterogeneous Graph Explainer for IoT Device Identification [paper]
  50. [LOG 24] xAI-Drop: Don't Use What You Cannot Explain [paper]
  51. [LOG 24] MOSE-GNN: A Motif-Based Self-Explaining Graph Neural Network for Molecular Property Prediction [[paper]]
  52. [IEEE TMI 24] Multi-Modal Diagnosis of Alzheimer’s Disease using Interpretable Graph Convolutional Networks [paper]
  53. [IEEE IoT 24] EXVul: Toward Effective and Explainable Vulnerability Detection for IoT Devices [paper]
  54. [IEEE Transactions on Fuzzy Systems] Towards Embedding Ambiguity-Sensitive Graph Neural Network Explainability [paper]
  55. [IEEE JBHI] Interpretable Dynamic Directed Graph Convolutional Network for Multi-Relational Prediction of Missense Mutation and Drug Response [paper]
  56. [IDEAL 24] Causal Explanation of Graph Neural Networks [paper]
  57. [BIBM 24] Seizure Onset Zone Localization Method based on GNN Explanation [paper]
  58. [BIBM 24] DDTExplainer: Mining Drug-Disease Therapeutic Mechanisms based on GNN Explainability [paper]
  59. [CIKM 24] EDGE: Evaluation Framework for Logical vs. Subgraph Explanations for Node Classifiers on Knowledge Graphs [paper]
  60. [ECML PKDD 24] Towards Few-shot Self-explaining Graph Neural Networks [paper]
  61. [ECML PKDD 24] BAGEL: A Benchmark for Assessing Graph Neural Network Explanations [paper]
  62. [SDM 24] XGExplainer: Robust Evaluation-based Explanation for Graph Neural Networks [paper]
  63. [DASFAA 24] Multi-objective Graph Neural Network Explanatory Model with Local and Global Information Preservation [paper]
  64. [DMKD 24] On GNN explanability with activation rules [paper]
  65. [KBS 24] Shapley-based graph explanation in embedding space [paper]
  66. [KBS 24] GEAR: Learning graph neural network explainer via adjusting gradients [paper]
  67. [IEEE TNSM 24] Ensemble Graph Attention Networks for Cellular Network Analytics: From Model Creation to Explainability [paper]
  68. [IEEE TNSE 24] GAXG: A Global and Self-adaptive Optimal Graph Topology Generation Framework for Explaining Graph Neural Networks [paper]
  69. [IEEE TETCI 24] GF-LRP: A Method for Explaining Predictions Made by Variational Graph Auto-Encoders [paper]
  70. [AAAI workshop] Semi-Supervised Graph Representation Learning with Human-centric Explanation for Predicting Fatty Liver Disease [paper]
  71. [XAI 24] Global Concept Explanations for Graphs by Contrastive Learning [paper]
  72. [XAI 24] Evaluating Neighbor Explainability for Graph Neural Networks [paper]
  73. [Arxiv 24.12] GISExplainer: On Explainability of Graph Neural Networks via Game-theoretic Interaction Subgraphs [paper]
  74. [Arxiv 24.11] Rethinking Node Representation Interpretation through Relation Coherence [paper]
  75. [Arxiv 24.10] Explaining Hypergraph Neural Networks: From Local Explanations to Global Concepts [paper]
  76. [Arxiv 24.10] Explainable Graph Neural Networks Under Fire [paper]
  77. [Arxiv 24.07] LLMExplainer: Large Language Model based Bayesian Inference for Graph Explanation Generation [paper]
  78. [Arxiv 24.06] Robust Ante-hoc Graph Explainer using Bilevel Optimization [paper]
  79. [Arxiv 24.05] Utilizing Description Logics for Global Explanations of Heterogeneous Graph Neural Networks [paper]
  80. [Arxiv 24.04] Improving the interpretability of GNN predictions through conformal-based graph sparsification [paper]
  81. [Arxiv 24.03] Iterative Graph Neural Network Enhancement via Frequent Subgraph Mining of Explanations [paper]
  82. [Arxiv 24.02] PAC Learnability under Explanation-Preserving Graph Perturbations [paper]
  83. [Arxiv 24.01] On Discprecncies between Perturbation Evaluations of Graph Neural Network Attributions [paper]
  84. [ECAI 24] PAGE: Parametric Generative Explainer for Graph Neural Network [paper]
  85. [MLST 24] Explainable Graph Neural Networks for Observation Impact Analysis in Atmospheric State Estimation [paper]
  86. [Preprint 24.11] Chiseling the Graph: An Edge-Sculpting Method for Explaining Graph Neural Networks [paper]
  87. [OpenReview 24] Robust Graph Attention for Graph Adversarial Attacks: An Information Bottleneck Inspired Approach [paper]
  88. [OpenReview 24] Graph Distributional Analytics: Enhancing GNN Explainability through Scalable Embedding and Distribution Analysis [paper]
  89. [Mach. Learn. Knowl. Extr. 24] Reliable and Faithful Generative Explainers for Graph Neural Networks [paper]
  90. [Machine Learning 24] L2XGNN: Learning to Explain Graph Neural Networks [paper]
  91. [Cell Reports Physical Science 24] Superior Polymeric Gas Separation Membrane Designed by Explainable Graph Machine Learning [paper]
  92. [ASP=DAC 24] LIPSTICK: Corruptibility-Aware and Explainable Graph Neural Network-based Oracle-Less Attack on Logic Locking [paper]
  93. [bioRxiv 24] Community-aware explanations in knowledge graphs with XP-GNN [paper]
  94. [ISCV 24] Adaptive Subgraph Feature Extraction for Explainable Multi-Modal Learning [paper]
  95. [IJCNN 24] Explanations for Graph Neural Networks using A Game-theoretic Value [paper]
  96. [AIxIA 24] Relating Explanations with the Inductive Biases of Deep Graph Networks [paper]
  97. [Neurocomputing] GeoExplainer: Interpreting Graph Convolutional Networks with geometric masking [paper]
  98. [Technologies] Explainable Graph Neural Networks: An Application to Open Statistics Knowledge Graphs for Estimating House Prices [paper]
  99. [Reliab. Eng. Syst. Saf.] Causal intervention graph neural network for fault diagnosis of complex industrial processes [paper]
  100. [Frontiers in big data] Global explanation supervision for Graph Neural Networks [paper]
  101. [Information and Software Technology] Graph-based explainable vulnerability prediction [paper]
  102. [Information Systems] Heterogeneous graph neural networks for fraud detection and explanation in supply chain finance [paper]
  103. [Information Procs. & Mana.] Towards explaining graph neural networks via preserving prediction ranking and structural dependency [paper]
  104. [Applied Energy] Explainable Spatio-Temporal Graph Neural Networks for multi-site photovoltaic energy production [paper]
  105. [PAKDD 24] Random Mask Perturbation Based Explainable Method of Graph Neural Networks [paper]
  106. [PAKDD 24] Toward Interpretable Graph Classification via Concept-Focused Structural Correspondence [paper]
  107. [Computational Materials Science] Graph isomorphism network for materials property prediction along with explainability analysis [paper]
  108. [NN 24] Explanatory subgraph attacks against Graph Neural Networks [paper]
  109. [NN 24] GRAM: An interpretable approach for graph anomaly detection using gradient attention maps [paper]
  110. [Neural Networks 24] CI-GNN: A Granger Causality-Inspired Graph Neural Network for Interpretable Brain Network-Based Psychiatric Diagnosis [paper]
  111. [NeuroImage 24] BPI-GNN: Interpretable brain network-based psychiatric diagnosis and subtyping [paper]
  112. [ICSE Poster 24] Graph Neural Network based Log Anomaly Detection and Explanation [paper]
  113. [ICPR 24] Interpretable Deep Graph-Level Clustering: A Prototype-Based Approach [paper]
  114. [AIMA 24] An Interpretable Population Graph Network to Identify Rapid Progression of Alzheimer’s Disease Using UK Biobank [paper]
  115. [IEEE Transactions] IEEE Transactions on Computational Social Systems [paper]
  116. [Journal of Physics] Explainer on GNN-based segmentation networks [paper]
  117. [Energy and AI] Electricity demand forecasting at distribution and household levels using explainable causal graph neural network [paper]
  118. [HI-AI@KDD 24] Interpretable Graph Model with Prototype-Based Graph Information Bottleneck [paper]
  119. [Neurosymbolic Artificial Intelligence] Towards Semantic Understanding of GNN Layers embedding with Functional-Semantic Activation Mapping [paper]
  120. [NeSy 24] Towards Understanding Graph Neural Networks: Functional-Semantic Activation Mapping [paper]
  121. [Thesis 24] Explainable and physics-guided graph deep learning for air pollution modelling [paper]
  122. [Thesis 24] Influence of molecular structures on graph neural network explainers’ performance [paper]
  123. [CEUR 24] Exposing Inductive Biases of Deep Graph Networks through Explainable AI [paper]
  124. [MobiQuitous 24] GNN-XAR: A Graph Neural Network for Explainable Activity Recognition in Smart Homes [paper]

Year 2023

  1. [NeurIPS 23] Interpretable Graph Networks Formulate Universal Algebra Conjectures [paper]
  2. [NeurIPS 23] SAME: Uncovering GNN Black Box with Structure-aware Shapley-based Multipiece Explanation [paper]
  3. [NeurIPS 23] Train Once and Explain Everywhere: Pre-training Interpretable Graph Neural Networks [paper]
  4. [NeurIPS 23] D4Explainer: In-distribution Explanations of Graph Neural Network via Discrete Denoising Diffusion [paper]
  5. [NeurIPS 23] TempME: Towards the Explainability of Temporal Graph Neural Networks via Motif Discovery [paper]
  6. [NeurIPS 23] V-InFoR: A Robust Graph Neural Networks Explainer for Structurally Corrupted Graphs [paper]
  7. [NeurIPS 23] Towards Self-Interpretable Graph-Level Anomaly Detection [paper]
  8. [NeurIPS 23] Evaluating Post-hoc Explanations for Graph Neural Networks via Robustness Analysis [paper]
  9. [NeurIPS 23] Interpretable Prototype-based Graph Information Bottleneck [paper]
  10. [ICML 23] Rethinking Explaining Graph Neural Networks via Non-parametric Subgraph Matching [paper]
  11. [ICML 23] Relevant Walk Search for Explaining Graph Neural Networks [paper]
  12. [ICML 23] Towards Understanding the Generalization of Graph Neural Networks [paper]
  13. [ICLR 23] GNNInterpreter: A Probabilistic Generative Model-Level Explanation for Graph Neural Networks [paper]
  14. [ICLR 23] Global Explainability of GNNs via Logic Combination of Learned Concepts [paper]
  15. [ICLR 23] Explaining Temporal Graph Models through an Explorer-Navigator Framework [paper]
  16. [ICLR 23] DAG Matters! GFlowNets Enhanced Explainer for Graph Neural Networks [paper]
  17. [ICLR 23] Interpretable Geometric Deep Learning via Learnable Randomness Injection [paper]
  18. [ICLR 23] A Differential Geometric View and Explainability of GNN on Evolving Graphs [paper]
  19. [KDD 23] MixupExplainer: Generalizing Explanations for Graph Neural Networks with Data Augmentation [paper]
  20. [KDD 23] Counterfactual Learning on Heterogeneous Graphs with Greedy Perturbation [paper]
  21. [KDD 23] Empower Post-hoc Graph Explanations with Information Bottleneck: A Pre-training and Fine-tuning Perspective [paper]
  22. [KDD 23] Less is More: SlimG for Accurate, Robust, and Interpretable Graph Mining. [paper]
  23. [KDD 23] Shift-Robust Molecular Relational Learning with Causal Substructure [paper]
  24. [AAAI 23] Global Concept-Based Interpretability for Graph Neural Networks via Neuron Analysis [paper]
  25. [AAAI 23] On the Limit of Explaining Black-box Temporal Graph Neural Networks [paper]
  26. [AAAI 23] Towards Fine-Grained Explainability for Heterogeneous Graph Neural Network [paper]
  27. [AAAI 23] Interpretable Chirality-Aware Graph Neural Network for Quantitative Structure Activity Relationship Modeling in Drug Discovery [paper]
  28. [VLDB 23] HENCE-X: Toward Heterogeneity-agnostic Multi-level Explainability for Deep Graph Networks [paper]
  29. [VLDB 23] On Data-Aware Global Explainability of Graph Neural Networks [paper]
  30. [AISTATS 23] Distill n' Explain: explaining graph neural networks using simple surrogates [paper]
  31. [AISTATS 23] Probing Graph Representations [paper]
  32. [ICDE 23] INGREX: An Interactive Explanation Framework for Graph Neural Networks [paper]
  33. [ICDE 23] Jointly Attacking Graph Neural Network and its Explanations [paper]
  34. [WWW 23] PaGE-Link: Path-based Graph Neural Network Explanation for Heterogeneous Link Prediction [paper]
  35. [ICDM 23] Limitations of Perturbation-based Explanation Methods for Temporal Graph Neural Networks
  36. [ICDM 23] Interpretable Subgraph Feature Extraction for Hyperlink Prediction [paper]
  37. [WSDM 23] Interpretable Research Interest Shift Detection with Temporal Heterogeneous Graphs [paper]
  38. [WSDM 23] Cooperative Explanations of Graph Neural Networks [paper]
  39. [WSDM 23] Towards Faithful and Consistent Explanations for Graph Neural Networks [paper]
  40. [WSDM 23] Global Counterfactual Explainer for Graph Neural Networks [paper]
  41. [CIKM 23] Explainable Spatio-Temporal Graph Neural Networks [paper]
  42. [CIKM 23] DuoGAT: Dual Time-oriented Graph Attention Networks for Accurate, Efficient and Explainable Anomaly Detection on Time-series. [paper]
  43. [CIKM 23] Heterogeneous Temporal Graph Neural Network Explainer [paper]
  44. [CIKM 23] ACGAN-GNNExplainer: Auxiliary Conditional Generative Explainer for Graph Neural Networks [paper]
  45. [CIKM 23] KG4Ex: An Explainable Knowledge Graph-Based Approach for Exercise Recommendation [paper]
  46. [ECML-PKDD 23] ENGAGE: Explanation Guided Data Augmentation for Graph Representation Learning [paper]
  47. [TPAMI 23] FlowX: Towards Explainable Graph Neural Networks via Message Flows [paper]
  48. [TAI] Prototype-based interpretable graph neural networks. [paper]
  49. [TKDE 23] Counterfactual Graph Learning for Anomaly Detection on Attributed Networks [paper]
  50. [Scientific Data 23 ] Evaluating explainability for graph neural networks [paper]
  51. [Nature Communications 23] Chemistry-intuitive explanation of graph neural networks for molecular property prediction with substructure masking [paper]
  52. [ACM Computing Surveys 23] A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation [paper]
  53. [TIST 23] Faithful and Consistent Graph Neural Network Explanations with Rationale Alignment [paper]
  54. [GLFrontiers 23] Everybody Needs a Little HELP: Explaining Graphs via Hierarchical Concepts [paper]
  55. [OpenReview 23] Iterative Graph Neural Network Enhancement Using Explanations [paper]
  56. [NeurIPS 2023 Workshop XAIA] GInX-Eval: Towards In-Distribution Evaluation of Graph Neural Networks Explanations [paper]
  57. [NeurIPS 2023 Workshop XAIA] On the Consistency of GNN Explainability Methods [paper]
  58. [AICS 23] A subgraph interpretation generative model for knowledge graph link prediction based on uni-relation transformation [paper]
  59. [GUT 23] Screening of normal endoscopic large bowel biopsies with interpretable graph learning: a retrospective study [paper]
  60. [PR 23] Towards self-explainable graph convolutional neural network with frequency adaptive inception [paper]
  61. [MLG 23] Understanding how explainers work in graph neural networks [paper]
  62. [MLG 23] Graph Model Explainer Tool [paper]
  63. [Information Science 23] Robust explanations for graph neural network with neuron explanation component [paper]
  64. [Recsys 23] Explainable Graph Neural Network Recommenders; Challenges and Opportunities [paper]
  65. [XAI 23] Counterfactual Explanations for Graph Classification Through the Lenses of Density [paper]
  66. [XAI 23] Evaluating Link Prediction Explanations for Graph Neural Networks [[paper]](https://arxiv.org/abs/2308.01682
  67. [XAI 23] XInsight: Revealing Model Insights for GNNs with Flow-based Explanations [paper]
  68. [XAI 23] Quantifying the Intrinsic Usefulness of Attributional Explanations for Graph Neural Networks with Artificial Simulatability Studies [paper]
  69. [XAI 23] MEGAN: Multi Explanation Graph Attention Network [paper]
  70. [XKDD 23] Game Theoretic Explanations for Graph Neural Networks [paper]
  71. [XKDD 23] From Black Box to Glass Box: Evaluating Faithfulness of Process Predictions with GCNNs [paper]
  72. [IJCNN 23] MEGA: Explaining Graph Neural Networks with Network Motifs [paper]
  73. [LOG Poster 23] On the Robustness of Post-hoc GNN Explainers to Label Noise [paper]
  74. [LOG Poster 23] How Faithful are Self-Explainable GNNs? [paper]
  75. [LOG Poster 23] Explaining Link Predictions in Knowledge Graph Embedding Models with Influential Examples [paper]
  76. [ICAID 23] Explanations for Graph Neural Networks via Layer Analysis. [paper]
  77. [ECAI 23] XGBD: Explanation-Guided Graph Backdoor Detection [paper]
  78. [IEEE Transactions on Consumer Electronics 23] Human Pose Prediction Using Interpretable Graph Convolutional Network for Smart Home [paper]
  79. [KBS 23] KE-X: Towards subgraph explanations of knowledge graph embedding based on knowledge information gain [paper]
  80. [ICML workshop 23] Generating Global Factual and Counterfactual Explainer for Molecule under Domain Constraints [paper]
  81. [Thesis 23] Developing interpretable graph neural networks for high dimensional feature spaces [paper]
  82. [Thesis 23] Evaluation of Explainability Methods on Single-Cell Classification Tasks Using Graph Neural Networks [paper]
  83. [ISSTA23] Interpreters for GNN-Based Vulnerability Detection: Are We There Yet? [paper]
  84. [ICECAI23] Improved GraphSVX for GNN Explanations Based on Cross Entropy [paper]
  85. [ICRA Workshop 23] Towards Semantic Interpretation and Validation of Graph Attention-based Explanations [paper]
  86. [Thesis 23] Interpretability of Graphical Models [paper]
  87. [Bioengineering 23] Personalized Explanations for Early Diagnosis of Alzheimer's Disease Using Explainable Graph Neural Networks with Population Graphs [paper]
  88. [BDSC 23] MDC: An Interpretable GNNs Method Based on Node Motif Degree and Graph Diffusion Convolution [[paper]] (https://link.springer.com/chapter/10.1007/978-981-99-3925-1_24)
  89. [Information Science 23] Explainability techniques applied to road traffic forecasting using Graph Neural Network models [paper]
  90. [Arxiv 23.05] EiX-GNN : Concept-level eigencentrality explainer for graph neural networks [paper]
  91. [ICLR Tiny 23] Message-passing selection: Towards interpretable GNNs for graph classification [paper]
  92. [ICLR Tiny 23] Revisiting CounteRGAN for Counterfactual Explainability of Graphs [paper]
  93. [MICCAI Workshop 23] IA-GCN: Interpretable Attention based Graph Convolutional Network for Disease prediction [paper]
  94. [GRADES & NDA'23] A Demonstration of Interpretability Methods for Graph Neural Networks [paper]
  95. [Arxiv 23] Self-Explainable Graph Neural Networks for Link Prediction [paper]
  96. [Arxiv 23.02] MotifExplainer: a Motif-based Graph Neural Network Explainer [paper]
  97. [ChemRxiv 23] Interpreting Graph Neural Networks with Myerson Values for Cheminformatics Approaches [paper]
  98. [Neural Networks 23] Generating Post-hoc Explanations for Skip-gram-based Node Embeddings by Identifying Important Nodes with Bridgeness [paper]
  99. [ICASSP 23] Towards a More Stable and General Subgraph Information Bottleneck [paper]
  100. [ESANN 23] Combining Stochastic Explainers and Subgraph Neural Networks can Increase Expressivity and Interpretability [paper]
  101. [IEEE Access] Generating Real-Time Explanations for GNNs via Multiple Specialty Learners and Online Knowledge Distillation [paper]
  102. [IEEE Access] Providing Post-Hoc Explanation for Node Representation Learning Models Through Inductive Conformal Predictions [paper]
  103. [Journal of Software 23] A Slice-level vulnerability detection and interpretation method based on graph neural network [paper]
  104. [Automation in Construction 23] Learning from explainable data-driven tunneling graphs: A spatio-temporal graph convolutional network for clogging detection [paper]
  105. [Briefings in Bioinformatics] Predicting molecular properties based on the interpretable graph neural network with multistep focus mechanism [paper]
  106. [Briefings in Bioinformatics] Identification of vital chemical information via visualization of graph neural networks [paper]
  107. [Bioinformatics 23] Explainable Multilayer Graph Neural Network for Cancer Gene Prediction [paper]
  108. [ICLR Workshop 23] GCI: A Graph Concept Interpretation Framework [paper]
  109. [Arxiv 23] Structural Explanations for Graph Neural Networks using HSIC [paper]
  110. [Internet of Things 23] XG-BoT: An Explainable Deep Graph Neural Network for Botnet Detection and Forensics [paper]
  111. [JOS23] A Generic Explaining & Locating Method for Malware Detection based on Graph Neural Networks [paper]
  112. [IJCNN 23] GRAPHSHAP: Explaining Identity-Aware Graph Classifiers Through the Language of Motifs [paper]
  113. [NLDL 23] Explainability in subgraphs-enhanced Graph Neural Networks [paper]
  114. [ICAAAIML 23] SEEN: Sharpening Explanations for Graph Neural Networks using Explanations from Neighborhoods [paper]

Year 2022

  1. [NeurIPS 22] GStarX:Explaining Graph-level Predictions with Communication Structure-Aware Cooperative Games [paper]
  2. [NeurIPS 22] Debiasing Graph Neural Networks via Learning Disentangled Causal Substructure [paper]
  3. [NeurIPS 22] Task-Agnostic Graph Neural Explanations [paper]
  4. [NeurIPS 22] CLEAR: Generative Counterfactual Explanations on Graphs [paper]
  5. [ICML 22] Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism [paper]
  6. [ICLR 22] DEGREE: Decomposition Based Explanation for Graph Neural Networks [paper]
  7. [ICLR 22] Explainable GNN-Based Models over Knowledge Graphs [paper]
  8. [ICLR 22] Discovering Invariant Rationales for Graph Neural Networks [paper]
  9. [KDD 22] On Structural Explanation of Bias in Graph Neural Networks [paper]
  10. [KDD 22] Causal Attention for Interpretable and Generalizable Graph Classification [paper]
  11. [CVPR 22] OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networks [paper]
  12. [CVPR 22] Improving Subgraph Recognition with Variational Graph Information Bottleneck [paper]
  13. [AISTATS 22] Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methods [paper]
  14. [AISTATS 22] CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks [paper]
  15. [TPAMI 22] Differentially Private Graph Neural Networks for Whole-Graph Classification [paper]
  16. [TPAMI 22] Reinforced Causal Explainer for Graph Neural Networks [paper]
  17. [VLDB 22] xFraud: Explainable Fraud Transaction Detection on Heterogeneous Graphs [paper]
  18. [LOG 22] GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networks [paper]
  19. [LOG 22] Towards Training GNNs using Explanation Directed Message Passing [paper]
  20. [The Webconf 22] Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoning [paper]
  21. [AAAI 22] Prototype-Based Explanations for Graph Neural Networks [paper]
  22. [AAAI 22] KerGNNs: Interpretable Graph Neural Networks with Graph Kernels [paper]
  23. [AAAI 22] ProtGNN: Towards Self-Explaining Graph Neural Networks [paper]
  24. [IEEE Big Data 22] Trade less Accuracy for Fairness and Trade-off Explanation for GNN [paper]
  25. [CIKM 22] GRETEL: Graph Counterfactual Explanation Evaluation Framework [paper]
  26. [CIKM 22] A Model-Centric Explainer for Graph Neural Network based Node Classification [paper]
  27. [IJCAI 22] What Does My GNN Really Capture? On Exploring Internal GNN Representations [paper]
  28. [ECML PKDD 22] Improving the quality of rule-based GNN explanations [paper]
  29. [MICCAI 22] Interpretable Graph Neural Networks for Connectome-Based Brain Disorder Analysis [paper]
  30. [MICCAI 22] Sparse Interpretation of Graph Convolutional Networks for Multi-modal Diagnosis of Alzheimer’s Disease [paper]
  31. [EuroS&P 22] Illuminati: Towards Explaining Graph Neural Networks for Cybersecurity Analysis [paper]
  32. [INFOCOM 22] Interpretability Evaluation of Botnet Detection Model based on Graph Neural Network [paper]
  33. [GLOBECOM 22] Shapley Explainer - An Interpretation Method for GNNs Used in SDN [paper]
  34. [GLOBECOM 22] An Explainer for Temporal Graph Neural Networks [paper]
  35. [TKDE 22] Zorro: Valid, Sparse, and Stable Explanations in Graph Neural Networks [paper]
  36. [TNNLS 22] Interpretable Graph Reservoir Computing With the Temporal Pattern Attention [paper]
  37. [TNNLS22] A Meta-Learning Approach for Training Explainable Graph Neural Networks [paper]
  38. [TNNLS 22] Explaining Deep Graph Networks via Input Perturbation [paper]
  39. [DMKD 22] On GNN explanability with activation patterns [paper]
  40. [KBS 22] EGNN: Constructing explainable graph neural networks via knowledge distillation [paper]
  41. [XKDD 22] GREASE: Generate Factual and Counterfactual Explanations for GNN-based Recommendations [paper]
  42. [AI 22] Are Graph Neural Network Explainers Robust to Graph Noises? [paper]
  43. [BRACIS 22] ConveXplainer for Graph Neural Networks [paper]
  44. [GLB 22] An Explainable AI Library for Benchmarking Graph Explainers [paper]
  45. [DASFAA 22] On Global Explainability of Graph Neural Networks [paper]
  46. [ISBI 22] Interpretable Graph Convolutional Network Of Multi-Modality Brain Imaging For Alzheimer’s Disease Diagnosis [paper]
  47. [Bioinformatics] GNN-SubNet: disease subnetwork detection with explainable Graph Neural Networks [paper]
  48. [Medical Imaging 22] Phenotype guided interpretable graph convolutional network analysis of fMRI data reveals changing brain connectivity during adolescence [paper]
  49. [NeuroComputing 22] Perturb more, trap more: Understanding behaviors of graph neural networks [paper]
  50. [DSN 22] CFGExplainer: Explaining Graph Neural Network-Based Malware Classification from Control Flow Graphs [paper]
  51. [IEEE Access 22] Providing Node-level Local Explanation for node2vec through Reinforcement Learning [paper]
  52. [Patterns 22] Quantitative Evaluation of Explainable Graph Neural Networks for Molecular Property Prediction [paper]
  53. [IEEE Access 22] Providing Post-Hoc Explanation for Node Representation Learning Models Through Inductive Conformal Predictions [paper]
  54. [IEEE 22] Explaining Graph Neural Networks With Topology-Aware Node Selection: Application in Air Quality Inference [paper]
  55. [IEEE Robotics and Automation Letters 22] Efficient and Interpretable Robot Manipulation with Graph Neural Networks [paper]
  56. [Arxiv 22] Deconfounding to Explanation Evaluation in Graph Neural Networks [paper]
  57. [ICCPR 22] GANExplainer: GAN-based Graph Neural Networks Explainer [paper]
  58. [Arxiv 22] Exploring Explainability Methods for Graph Neural Networks [paper]
  59. [OpenReview 22] TGP: Explainable Temporal Graph Neural Networks for Personalized Recommendation [paper]
  60. [Arxiv 22] PGX: A Multi-level GNN Explanation Framework Based on Separate Knowledge Distillation Processes [paper]
  61. [Arxiv 22] Defending Against Backdoor Attack on Graph Neural Network by Explainability [paper]
  62. [Arxiv 22] Faithful Explanations for Deep Graph Models [paper]
  63. [Arxiv 22] Towards Explanation for Unsupervised Graph-Level Representation Learning [paper]
  64. [Arxiv 22] Explainability in Graph Neural Networks: An Experimental Survey [paper]
  65. [IEEE TSIPN 22] Explainability and Graph Learning from Social Interactions [paper]

Year 2021

  1. [NeurIPS 21] SALKG: Learning From Knowledge Graph Explanations for Commonsense Reasoning [paper]
  2. [NeurIPS 21] Reinforcement Learning Enhanced Explainer for Graph Neural Networks [paper]
  3. [NeurIPS 21] Towards Multi-Grained Explainability for Graph Neural Networks [paper]
  4. [NeurIPS 21] Robust Counterfactual Explanations on Graph Neural Networks [paper]
  5. [ICML 21] On Explainability of Graph Neural Networks via Subgraph Explorations [paper]
  6. [ICML 21] Generative Causal Explanations for Graph Neural Networks [paper]
  7. [ICML 21] Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsity [paper]
  8. [ICML 21] Automated Graph Representation Learning with Hyperparameter Importance Explanation [paper]
  9. [ICLR 21] Explainable Subgraph Reasoning for Forecasting on Temporal Knowledge Graphs [paper]
  10. [ICLR 21] Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking [paper]
  11. [ICLR 21] Graph Information Bottleneck for Subgraph Recognition [paper]
  12. [KDD 21] When Comparing to Ground Truth is Wrong: On Evaluating GNN Explanation Methods [paper]
  13. [KDD 21] Counterfactual Graphs for Explainable Classification of Brain Networks [paper]
  14. [CVPR 21] Quantifying Explainers of Graph Neural Networks in Computational Pathology.[paper]
  15. [NAACL 21] Counterfactual Supporting Facts Extraction for Explainable Medical Record Based Diagnosis with Graph Network. [paper]
  16. [AAAI 21] Motif-Driven Contrastive Learning of Graph Representations [paper]
  17. [TPAMI 21] Higher-Order Explanations of Graph Neural Networks via Relevant Walks [paper]
  18. [WWW 21] Interpreting and Unifying Graph Neural Networks with An Optimization Framework [paper]
  19. [Genome medicine 21] Explaining decisions of Graph Convolutional Neural Networks: patient-specific molecular subnetworks responsible for metastasis prediction in breast cancer [paper]
  20. [IJCKG 21] Knowledge Graph Embedding in E-commerce Applications: Attentive Reasoning, Explanations, and Transferable Rules [paper]
  21. [RuleML+RR 21] Combining Sub-Symbolic and Symbolic Methods for Explainability [paper]
  22. [PAKDD 21] SCARLET: Explainable Attention based Graph Neural Network for Fake News spreader prediction [paper]
  23. [J. Chem. Inf. Model] Coloring Molecules with Explainable Artificial Intelligence for Preclinical Relevance Assessment [paper]
  24. [bioRxiv 21] APRILE: Exploring the Molecular Mechanisms of Drug Side Effects with Explainable Graph Neural Networks [paper]
  25. [ISM 21] Edge-Level Explanations for Graph Neural Networks by Extending Explainability Methods for Convolutional Neural Networks [paper]
  26. [Arxiv 21] Towards the Explanation of Graph Neural Networks in Digital Pathology with Information Flows [paper]
  27. [Arxiv 21] Preserve, Promote, or Attack? GNN Explanation via Topology Perturbation [paper]
  28. [Arxiv 21] Learnt Sparsification for Interpretable Graph Neural Networks [paper]
  29. [ICML workshop 21] GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networks [paper]
  30. [ICML workshop 21] Reliable Graph Neural Network Explanations Through Adversarial Training [paper]
  31. [ICML workshop 21] Reimagining GNN Explanations with ideas from Tabular Data [paper]
  32. [ICML workshop 21] Towards Automated Evaluation of Explanations in Graph Neural Networks [paper]
  33. [ICDM 21] GNES: Learning to Explain Graph Neural Networks [paper]
  34. [ICDM 21] GCN-SE: Attention as Explainability for Node Classification in Dynamic Graphs [paper]
  35. [ICDM 21] Multi-objective Explanations of GNN Predictions [paper]
  36. [CIKM 21] Towards Self-Explainable Graph Neural Network [paper]
  37. [ECML PKDD 21] GraphSVX: Shapley Value Explanations for Graph Neural Networks [paper]
  38. [WiseML 21] Explainability-based Backdoor Attacks Against Graph Neural Networks [paper]
  39. [IJCNN 21] MEG: Generating Molecular Counterfactual Explanations for Deep Graph Networks [paper]
  40. [ICCSA 21] Understanding Drug Abuse Social Network Using Weighted Graph Neural Networks Explainer [paper]
  41. [NeSy 21] A New Concept for Explaining Graph Neural Networks [paper]
  42. [Information Fusion 21] Towards multi-modal causability with Graph Neural Networks enabling information fusion for explainable AI [paper]
  43. [Patterns 21] hcga: Highly Comparative Graph Analysis for network phenotyping [paper]
  44. [Neural Networks 21] Understanding the Message Passing in Graph Neural Networks via Power Iteration [paper]

Year 2020 and Before

  1. [NeurIPS 20] Parameterized Explainer for Graph Neural Network.[paper]
  2. [NeurIPS 20] PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks [paper]
  3. [KDD 20] XGNN: Towards Model-Level Explanations of Graph Neural Networks [paper]
  4. [ACL 20] GCAN: Graph-aware Co-Attention Networks for Explainable Fake News Detection on Social Media. [paper]
  5. [Arxiv 20] Graph Neural Networks Including Sparse Interpretability [paper]
  6. [NeurIPS Workshop 20] Towards explainable message passing networks for predicting carbon dioxide adsorption in metal-organic frameworks [paper]
  7. [ICML workstop 20] Contrastive Graph Neural Network Explanation [paper]
  8. [ICML workstop 20] Towards Explainable Graph Representations in Digital Pathology [paper]
  9. [NeurIPS workshop 20] Explaining Deep Graph Networks with Molecular Counterfactuals [paper]
  10. [DataMod 20] Exploring Graph-Based Neural Networks for Automatic Brain Tumor Segmentation" [paper]
  11. [OpenReview 20] A Framework For Differentiable Discovery Of Graph Algorithms [paper]
  12. [OpenReview 20] Causal Screening to Interpret Graph Neural Networks [paper]
  13. [Arxiv 20] Understanding Graph Neural Networks from Graph Signal Denoising Perspectives [paper]
  14. [IJCNN 20] GCN-LRP explanation: exploring latent attention of graph convolutional networks] [paper]
  15. [CD-MAKE 20] Explain Graph Neural Networks to Understand Weighted Graph Features in Node Classification [paper]
  16. [ICDM 19] Scalable Explanation of Inferences on Large Graphs [paper]
  17. [NeurIPS 19] GNNExplainer: Generating Explanations for Graph Neural Networks [paper]