awesome-causality-algorithms

An index of algorithms in

• machine learning for causal inference: solves causal inference problems
• causal machine learning: solves ML problems

Reproducibility is important! We will remove those methods without open-source code unless it is a survey/review paper.

Please cite our survey paper if this index is helpful.

@article{guo2020survey,
  title={A survey of learning causality with data: Problems and methods},
  author={Guo, Ruocheng and Cheng, Lu and Li, Jundong and Hahn, P Richard and Liu, Huan},
  journal={ACM Computing Surveys (CSUR)},
  volume={53},
  number={4},
  pages={1--37},
  year={2020},
  publisher={ACM New York, NY, USA}
}

Table of Contents

• Toolboxes
• Causal Effect Estimation
• Causal Machine Learning
• Causal Discovery

Contributions are welcome, see CONTRIBUTING.md.

Toolboxes

Comprehensive

Name	Code	Comment
causal-learn	Python	Causal Discovery, Causal Representation Learning, Statistical Tests.
Trustworthy AI	Python	Causal Structure Learning, Causal Disentangled Representation Learning, gCastle (or pyCastle, pCastle).
YLearn	Python	Python package for causal discovery, causal effect identification/estimation, counterfactual inference, policy learning, etc.

Treatment Effect Estimation / Uplift Modeling

Name	Paper/Documentation	Venue	Code	Comment
DoWhy	Tutorial on Causal Inference and Counterfactual Reasoning	KDD 2018	Python	Python library for causal inference that supports explicit modeling and testing of causal assumptions.
EconML	Causal Inference and Machine Learning in Practice with EconML and CausalML	KDD 2021	Python	Python package that applies the power of machine learning techniques to estimate individualized causal responses from observational or experimental data.
CausalML	Causalml: Python package for causal machine learning	arXiv	Python	Uplift modeling and causal inference with machine learning algorithms
JustCause	Underlying thesis	NA	Python	For evaluation of heterogeneous treatment effect estimators on common reference as well as synthetic data.
WhyNot	Documentation	NA	Python	An experimental sandbox for causal inference and decision making in dynamics.
scikit-uplift	Documentation and User guide for uplift modeling	NA	Python	Uplift modeling in scikit-learn style in python.
DoubleML	Double/debiased machine learning for treatment and structural parameters	Econometrics Journal 2018	Python	Double machine learning framework for causal parameters; also available in R.
CausalPy	NA	NA	Python	Bayesian and quasi-experimental causal inference (synthetic control, DiD, RDD, IV) built on PyMC.

Causal Discovery

Name	Paper	Venue	Code	Comment
Bench Press	Benchpress: a scalable and versatile workflow for benchmarking structure learning algorithms for graphical models — Rios et al.	arXiv 2021	Code	Reproducible and scalable execution and benchmarks of 41 structure learning algorithms supporting multiple language
causal-learn	Causal-learn: Causal Discovery in Python — Zheng et al.	JMLR 2024	Python	Causal Discovery, Causal Representation Learning, Statistical Tests.
TETRAD R/Java	TETRAD: A Toolbox for Causal Discovery — Ramsey et al.	CI 2018	R/Java	Causal Discovery Toolbox from CMU
Causaldag	NA	NA	Code	Python package for the creation, manipulation, and learning of Causal DAGs
CausalNex	NA	NA	Python	A toolkit for causal reasoning with Bayesian Networks.
CausalDiscoveryToolbox	Causal Discovery Toolbox: Uncover causal relationships in Python — Kalainathan and Goudet	arXiv 2019	Python
pgmpy	NA	NA	Python	Probabilistic graphical models, structure learning and causal inference.
Tigramite	NA	NA	Python	Causal discovery and inference for time series (PCMCI and variants).
DoDiscover	NA	NA	Python	PyWhy library for causal discovery, including with latent confounders.
Causica	NA	NA	Python	Deep end-to-end causal inference (DECI) and related models from Microsoft.
LiNGAM	NA	NA	Python	Implementations of the LiNGAM family of non-Gaussian causal discovery methods.
Causal Chambers	Causal chambers as a real-world physical testbed for AI methodology — Gamella et al.	Nature Machine Intelligence 2025	Python	Real-world datasets with interventions and validated ground-truth graphs from two physical devices; the Python package loads the data and graphs and includes simulators.
causal-automata	NA	NA	Python	A relatively fast, GPU-native causal discovery and DAG structure learning package in JAX/NumPy via synchronous cellular automata and a 1D topological elevation field.

Root Cause Analysis

Name	Paper	Venue	Code	Comments
Chaos Genius	NA	NA	Python	ML powered analytics engine for outlier/anomaly detection and root cause analysis.

Causal Effect Estimation

Survey Papers

Name	Paper	Venue
Yao et al.	A survey on causal inference — Yao et al.	TKDD

With i.i.d Data

Individual Treatment Effect (ITE) / Conditional Average Treatment Effect (CATE)

Deep Learning based methods

Name	Paper	Venue	Code
TARNet, Counterfactual Regression	Estimating individual treatment effect: generalization bounds and algorithms — Shalit et al.	ICML 2017	Python
BNN, BLR	Learning representations for counterfactual inference — Johansson et al.	ICML 2016	Python
Causal Effect VAE	Causal effect inference with deep latent-variable models — Louizos et al.	NeurIPS 2017	Python
Dragonnet	Adapting neural networks for the estimation of treatment effects — Shi et al.	NeurIPS 2019	Python
SITE	Representation Learning for Treatment Effect Estimation from Observational Data — Yao et al.	NeurIPS 2018	Python
GANITE	GANITE: Estimation of Individualized Treatment Effects using Generative Adversarial Nets — Yoon et al.	ICLR 2018	Python
Perfect Match	Perfect match: A simple method for learning representations for counterfactual inference with neural networks — Schwab et al.	arXiv 2018	Python
Intact-VAE	Intact-VAE: Estimating treatment effects under unobserved confounding — Wu and Fukumizu	ICLR 2022	NA
CausalEGM	CausalEGM: a general causal inference framework by encoding generative modeling — Liu et al.	arXiv 2022	Python

Classic Methods

Name	Paper	Venue	Code

Tree based Methods

Name	Paper	Venue	Code
Causal Forest	Estimation and inference of heterogeneous treatment effects using random forests — Wager and Athey	JASA 2017	R, Python
Causal MARS, Causal Boosting, Pollinated Transformed Outcome Forests	Some methods for heterogeneous treatment effect estimation in high-dimensions — Powers et al.	arXiv 2017	R, R
Bayesian Additive Regression Trees (BART)	Bayesian nonparametric modeling for causal inference — Hill	JCGS 2011	Python

Meta Learner

Name	Paper	Venue	Code
X-learner	Metalearners for estimating heterogeneous treatment effects using machine learning — Künzel et al.	PNAS 2019	R, R
R-learner	Quasi-oracle estimation of heterogeneous treatment effects — Nie and Wager	Biometrika 2021	R

Average Treatment Effect (including ATT and ATC)

Name	Paper	Venue	Code
Propensity Score Matching	The central role of the propensity score in observational studies for causal effects — Rosenbaum and Rubin	Biometrika 1983	Python
Inverse Probability Reweighting	The central role of the propensity score in observational studies for causal effects — Rosenbaum and Rubin	Biometrika 1983	R
Doubly Robust Estimation	Doubly robust estimation in missing data and causal inference models — Bang and Robins	Biometrics 2005	R
Doubly Robust Estimation for High Dimensional Data	Doubly robust matching estimators for high dimensional confounding adjustment — Antonelli et al.	Biometrics 2016	R
TMLE	tmle: An R package for targeted maximum likelihood estimation — Gruber and van der Laan	JSS 2011	R
Entropy Balancing	Entropy balancing for causal effects: A multivariate reweighting method to produce balanced samples in observational studies — Hainmueller	Political Analysis 2012	R
CBPS(Covariate Balancing Propensity Score)	Covariate balancing propensity score — Imai and Ratkovic	JRSS-B 2014	R
Approximate Residual Balancing	Approximate residual balancing: debiased inference of average treatment effects in high dimensions — Athey et al.	JRSS-B 2018	R
Causal Bootstrapping	Causal bootstrapping — Little and Badawy	arXiv 2019	Matlab

Instrumental Variable (IV)

Name	Paper	Venue	Code
DeepIV	Deep iv: A flexible approach for counterfactual prediction — Hartford et al.	ICML 2017	Python
PDSLasso	PDSLASSO: Stata module for post-selection and post-regularization OLS or IV estimation and inference — Ahrens et al.	SSC 2018	STATA

Dose-Response Curve (Continuous Treatment)

Name	Paper	Venue	Code
Causal Dose-Response Curves / Causal Curves	causal-curve: A Python Causal Inference Package to Estimate Causal Dose-Response Curves — Kobrosly	JOSS 2020	Python
Dose response networks (DRNets)	Learning Counterfactual Representations for Estimating Individual Dose-Response Curves — Schwab et al.	arXiv 2019	Python

Vectorized Treatments

Name	Paper	Venue	Code
Causal Effect Inference for Structured Treatments	Causal Effect Inference for Structured Treatments — Kaddour et al.	NeurIPS 2021	Python

Multiple Causes

Name	Paper	Venue	Code
Deconfounder	The blessings of multiple causes — Wang and Blei	arXiv 2018	Python

Multiple Outcomes

Name	Paper	Venue	Code
Multiple Responses in Uplift Models	Estimating and Visualizing Business Tradeoffs in Uplift Models — Weiss	Blog	Python

Difference-in-Differences / Regression Discontinuity

Name	Paper	Venue	Code
Staggered Difference-in-Differences	Difference-in-differences with multiple time periods — Callaway and Sant'Anna	J. Econometrics 2021	R
Regression Discontinuity (rdrobust)	Robust nonparametric confidence intervals for regression-discontinuity designs — Calonico et al.	Econometrica 2014	R/Python/Stata

Mediation Analysis

Name	Paper	Venue	Code
mediation	A general approach to causal mediation analysis — Imai et al.	Psychological Methods 2010	R

Sensitivity Analysis

Name	Paper	Venue	Code
sensemakr	Making sense of sensitivity: extending omitted variable bias — Cinelli and Hazlett	JRSS-B 2020	R

Non-i.i.d Data

Panel Data / Time Series

Name	Paper	Venue	Code
Synthetic Control Method	Using synthetic controls: Feasibility, data requirements, and methodological aspects — Abadie	JEL 2021	R
Synthetic Difference in Differences	Synthetic difference in differences — Arkhangelsky et al.	NBER 2019	R Python
Causal Impact	Inferring causal impact using Bayesian structural time-series models — Brodersen et al.	AoAS 2015	R Python
Time Series Deconfounder	Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden Confounders — Bica et al.	ICML 2020	Code
Recurrent Marginal Structural Networks	Forecasting Treatment Responses Over Time Using Recurrent Marginal Structural Networks — Lim	NeurIPS 2018	Python
Longitudinal Targeted Maximum Likelihood Estimation	Targeted maximum likelihood estimation for dynamic and static longitudinal marginal structural working models — Petersen et al.	J. Causal Inference 2014	R
Causal Transformer	Causal Transformer for Estimating Counterfactual Outcomes — Melnychuk et al.	arXiv 2022	Python

Network Data (with or without Interference)

Name	Paper	Venue	Code
Network Deconfounder	Learning Individual Causal Effects from Networked Observational Data — Guo et al.	WSDM 2020	Python
Causal Inference with Network Embeddings	Using embeddings to correct for unobserved confounding — Veitch et al.	arXiv 2019	Python
Linked Causal Variational Autoencoder (LCVA)	Linked Causal Variational Autoencoder for Inferring Paired Spillover Effects — Rakesh et al.	CIKM 2018	Python
Method-of-moments Estimators	Causal Inference under Network Interference with Noise — Li et al.	arXiv 2021	Code

Causal Machine Learning

Surveys

Name	Paper	Venue	Code
Causal ML Survey	Causal Machine Learning: A Survey and Open Problems — Kaddour et al.	arXiv 2022	NA

OoD Generalization

Name	Paper	Venue	Code
DomainBed	In Search of Lost Domain Generalization — Gulrajani and Lopez-Paz	ICLR 2020	Code
WILDS	Wilds: A benchmark of in-the-wild distribution shifts — Koh et al.	ICML 2021	Code
IBM OoD	Repository for theory and methods for Out-of-Distribution (OoD) generalization by IBM Research	NA	Code
OoD Bench	Ood-bench: Benchmarking and understanding out-of-distribution generalization datasets and algorithms — Ye et al.	arXiv 2021	Code
BEDS-Bench	BEDS-Bench: Behavior of EHR-models under Distributional Shift--A Benchmark — Avati et al.	arXiv 2021	Code
Survey THU	Towards out-of-distribution generalization: A survey — Shen et al.	arXiv 2021	NA

Graph OoD Generalization

Name	Paper	Venue	Code
CIGA	Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs — Chen et al.	NeurIPS 2022	Code
Survey THU	Out-of-distribution generalization on graphs: A survey — Li et al.	arXiv 2022	NA

Recommendation Systems

Inverse Propensity Scoring / Doubly Robust

Name	Paper	Venue	Code
Top-K Off-policy Correction	Top-k off-policy correction for a REINFORCE recommender system — Chen et al.	WSDM 2019	Python
Unbiased Offline Recommender Learning	Unbiased Recommender Learning from Missing-Not-At-Random Implicit Feedback — Saito et al.	WSDM 2020	Python
Unbiased Offline Recommender Evaluation	Unbiased offline recommender evaluation for missing-not-at-random implicit feedback — Yang et al.	RecSys 2018	Python
IPS Estimator	Recommendations as treatments: Debiasing learning and evaluation — Schnabel et al.	ICML 2016	Python

Hidden Confounding

Name	Paper	Venue	Code
Deconfounded Recsys	Causal Inference for Recommender Systems — Wang et al.	RecSys 2020	Python

Domain Adaptation

Name	Paper	Venue	Code
Causal Embedding for Recommendation	Causal embeddings for recommendation — Bonner and Vasile	RecSys 2018	Python
Domain Adversarial Matrix Factorization	Towards Resolving Propensity Contradiction in Offline Recommender Learning — Saito and Nomura	IJCAI 2022	Code

Disentanglement

Name	Paper	Venue	Code
Causal Embedding for User Interest and Conformity	Disentangling User Interest and Conformity for Recommendation with Causal Embedding — Zheng et al.	WWW 2021	Python

Learning to Rank

Name	Paper	Venue	Code
Policy-aware Estimator	Policy-aware unbiased learning to rank for top-k rankings — Oosterhuis and de Rijke	SIGIR 2020	Python
Heckman^{rank}	Correcting for Selection Bias in Learning-to-rank Systems — Ovaisi et al.	arXiv 2020	Code
Unbiased LambdaMart	Unbiased LambdaMART: An Unbiased Pairwise Learning-to-Rank Algorithm — Hu et al.	WWW 2019	Code
IPW_rank and the Dual Learning Algorithm	Unbiased Learning to Rank with Unbiased Propensity Estimation — Ai et al.	SIGIR 2018	Python
Propensity SVM-rank	Unbiased learning-to-rank with biased feedback — Joachims et al.	WSDM 2017	Python

Off-line Policy Evaluation/Optimization (for Contextual Bandit or RL)

Name	Paper	Venue	Code
Optimal Kernel Balancing	Policy Evaluation with Latent Confounders via Optimal Balance — Bennett and Kallus	arXiv 2019	Python
BanditNet	Deep learning with logged bandit feedback — Joachims et al.	ICLR 2018	Python
Counterfactual Risk Minimization (POEM)	Counterfactual risk minimization: Learning from logged bandit feedback — Swaminathan and Joachims	ICML 2015	Python
Self Normalized Estimator	The self-normalized estimator for counterfactual learning — Swaminathan and Joachims	NeurIPS 2015	Python
Open Bandit Pipeline	Open Bandit Dataset and Pipeline: Towards Realistic and Reproducible Off-Policy Evaluation — Saito et al.	NeurIPS 2021	Python

Natural Language Processing

Name	Paper	Venue	Code
A Review of Using Text to Remove Confounding from Causal Estimates	Text and Causal Inference: A Review of Using Text to Remove Confounding from Causal Estimates — Keith et al.	ACL 2020	NA
Causal Analysis with Lexicons	Deconfounded lexicon induction for interpretable social science — Pryzant et al.	NAACL 2018	Python
Causal Text Embeddings	Using Text Embeddings for Causal Inference — Veitch et al.	arXiv 2019	Python
Handling Missing/Noisy Treatment	Challenges of Using Text Classifiers for Causal Inference — Wood-Doughty et al.	EMNLP 2018	Python
Causal Inferences Using Texts	How to make causal inferences using texts — Egami et al.	arXiv 2018	NA

Counterfactual Explanations

Paper	Venue	Code
Explaining machine learning classifiers through diverse counterfactual explanations — Mothilal et al.	arXiv 2019	Python
Efficient search for diverse coherent explanations — Russell	FAccT 2019	Python
Counterfactual explanations without opening the black box: Automated decisions and the GDPR — Wachter et al.	Harvard JL&T 2017

Counterfactual Fairness

Paper	Venue	Code
Counterfactual fairness — Kusner et al.	NeurIPS 2017	Python
Pc-fairness: A unified framework for measuring causality-based fairness — Wu et al.	NeurIPS 2019	Code
Path-specific counterfactual fairness — Chiappa	AAAI 2019	Code
Counterfactual fairness in text classification through robustness — Garg et al.	AIES 2019	Code

Reinforcement Learning

Name	Paper	Venue	Code
Deconfounded RL	Deconfounding reinforcement learning in observational settings — Lu et al.	arXiv 2018	Python
Structural Nested Models / G-estimation	Structural nested models and G-estimation: the partially realized promise — Vansteelandt and Joffe	Statistical Science 2014	NA
Counterfactual-Guided Policy Search (CF-GPS)	Woulda, Coulda, Shoulda: Counterfactually-Guided Policy Search — Buesing et al.	arXiv 2018	NA

Multi-Armed Bandit/Causal Bandit

Name	Paper	Venue	Code
Causal Bandits	Causal bandits: Learning good interventions via causal inference — Lattimore et al.	NeurIPS 2016	NA
Offline+MAB	Combining Offline Causal Inference and Online Bandit Learning for Data Driven Decisions — Ye et al.	arXiv 2020	NA
B-kl-UCB, B-TS	Transfer learning in multi-armed bandit: a causal approach — Zhang and Bareinboim	AAMAS 2017	NA
Incremental Model	Contextual Multi-Armed Bandits for Causal Marketing — Sawant et al.	arXiv 2018	NA

Large Language Models

Name	Paper	Venue	Code
PyWhy-LLM	Causal reasoning and large language models: Opening a new frontier for causality — Kıcıman et al.	arXiv 2023	Python

Causal Discovery

for i.i.d. Data

Classic Methods

Name	Paper	Venue	Code
IC algorithm	A theory of inferred causation — Pearl and Verma	KR 1991	Python
PC algorithm	Causation, Prediction, and Search — Spirtes et al.	Book 2000	Python R Julia
FCI algorithm	Causation, Prediction, and Search — Spirtes et al.	Book 2000	R Julia

Continuous Optimization

Paper	Venue	Code
DAGs with NO TEARS: Continuous optimization for structure learning — Zheng et al.	NeurIPS 2018	Code
DAG-GNN: DAG Structure Learning with Graph Neural Networks — Yu et al.	ICML 2019	Code
Learning Sparse Nonparametric DAGs — Zheng et al.	AISTATS 2020	Code
Amortized Inference for Causal Structure Learning — Lorch et al.	NeurIPS 2022	Code
DAGMA: Learning DAGs via M-matrices and a Log-Determinant Acyclicity Characterization — Bello et al.	NeurIPS 2022	Code
Deep End-to-end Causal Inference (DECI) — Geffner et al.	arXiv 2022	Code

Learning IV

Name	Paper	Venue	Code
Learning IV	Learning instrumental variables with structural and non-gaussianity assumptions — Silva and Shimizu	JMLR 2017	Code

Distinguishing Cause from Effect (Bivariate)

Name	Paper	Venue	Code
BMLiNGAM	Bayesian estimation of causal direction in acyclic structural equation models with individual-specific confounder variables and non-Gaussian distributions — Shimizu and Bollen	JMLR 2014	Python
Sloppy	Identifiability of Cause and Effect using Regularized Regression — Marx and Vreeken	KDD 2019	R
RECI	Cause-effect inference by comparing regression errors — Blöbaum et al.	AISTATS 2018	in CausalDiscoveryToolbox
bQCD	Distinguishing cause from effect using quantiles: Bivariate quantile causal discovery — Tagasovska et al.	ICML 2020	Code
CGNN	Learning functional causal models with generative neural networks — Goudet et al.	Springer 2018	Code

Conditional Independence Tests (for Constraint-based Algorithms)

Name	Paper	Venue	Code
RCIT	Approximate kernel-based conditional independence tests for fast non-parametric causal discovery — Strobl et al.	J. Causal Inference 2019	R

Causal Discovery with Probabilistic Logic Programming

Name	Paper	Venue	Code
Causal PSL	Scalable Probabilistic Causal Structure Discovery — Sridhar et al.	IJCAI 2018	Java

Scalable Ensemble Causal Discovery

Name	Paper	Venue	Code
Scalable and Hybrid Ensemble-Based Causality Discovery	Scalable and Hybrid Ensemble-Based Causality Discovery — Guo et al.	SMDS 2020	Python

with Temporal Data

Name	Paper	Venue	Code
TCDF: Temporal Causal Discovery Framework	Causal discovery with attention-based convolutional neural networks — Nauta et al.	MAKE 2019	Pytorch
PCMCI	Detecting and quantifying causal associations in large nonlinear time series datasets — Runge et al.	Science Advances 2019	Python