mlsanityData to 7 Oct 2026

Learning Representations for Counterfactual Inference

arXiv 1605.03661 ↗First posted 12 May 2016stat.ML cs.AI cs.LGcited by 327

Not on the map. Why?

Abstract (arXiv)

Observational studies are rising in importance due to the widespread accumulation of data in fields such as healthcare, education, employment and ecology. We consider the task of answering counterfactual questions such as, "Would this patient have lower blood sugar had she received a different medication?". We propose a new algorithmic framework for counterfactual inference which brings together ideas from domain adaptation and representation learning. In addition to a theoretical justification, we perform an empirical comparison with previous approaches to causal inference from observational data. Our deep learning algorithm significantly outperforms the previous state-of-the-art.

Key facts. Cited by 327 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 May 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 56; 2022: 62; 2023: 69; 2024: 70; 2025: 44; 2026: 26.

327 papers.

Sort:

By area:

  1. 2021Nonparametric Estimation of Heterogeneous Treatment Effects: From Theory to Learning Algorithmscited by 144
  2. 2022Causal Transformer for Estimating Counterfactual Outcomescited by 121
  3. 2021The Causal-Neural Connection: Expressiveness, Learnability, and Inferencecited by 97
  4. 2022Diffusion Causal Models for Counterfactual Estimationcited by 87
  5. 2021Size-Invariant Graph Representations for Graph Classification Extrapolationscited by 82
  6. 2021On Inductive Biases for Heterogeneous Treatment Effect Estimationcited by 74
  7. 2021Learning from Counterfactual Links for Link Predictioncited by 69
  8. 2021VCNet and Functional Targeted Regularization For Learning Causal Effects of Continuous Treatmentscited by 59
  9. 2022Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equationscited by 59
  10. 2021Causally motivated Shortcut Removal Using Auxiliary Labelscited by 55
  11. 2022Neural Causal Models for Counterfactual Identification and Estimationcited by 54
  12. 2022A Causal Lens for Controllable Text Generationcited by 45
38 more
  1. 2023A Survey on Causal Reinforcement Learningcited by 43
  2. 2023Counterfactual Identifiability of Bijective Causal Modelscited by 42
  3. 2021Conditional Distributional Treatment Effect with Kernel Conditional Mean Embeddings and U-Statistic Regressioncited by 40
  4. 2021Deep Proxy Causal Learning and its Application to Confounded Bandit Policy Evaluationcited by 39
  5. 2021Causal Effect Inference for Structured Treatmentscited by 38
  6. 2022Combining Observational and Randomized Data for Estimating Heterogeneous Treatment Effectscited by 32
  7. 2023Optimal Transport for Treatment Effect Estimationcited by 32
  8. 2022Data-Driven Offline Decision-Making via Invariant Representation Learningcited by 31
  9. 2025Foundation Models for Causal Inference via Prior-Data Fitted Networkscited by 30
  10. 2023In Search of Insights, Not Magic Bullets: Towards Demystification of the Model Selection Dilemma in Heterogeneous Treatment Effect Estimationcited by 29
  11. 2023Bayesian Neural Controlled Differential Equations for Treatment Effect Estimationcited by 26
  12. 2021Estimating Average Treatment Effects via Orthogonal Regularizationcited by 25
  13. 2021SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Datacited by 25
  14. 2022Exploring Transformer Backbones for Heterogeneous Treatment Effect Estimationcited by 25
  15. 2021Sequential Deconfounding for Causal Inference with Unobserved Confounderscited by 24
  16. 2024Causality for Large Language Modelscited by 24
  17. 2023Conformal Meta-learners for Predictive Inference of Individual Treatment Effectscited by 23
  18. 2021E-Commerce Promotions Personalization via Online Multiple-Choice Knapsack with Uplift Modelingcited by 21
  19. 2022Normalizing Flows for Interventional Density Estimationcited by 21
  20. 2022Direct Heterogeneous Causal Learning for Resource Allocation Problems in Marketingcited by 21
  21. 2023Bounds on Representation-Induced Confounding Bias for Treatment Effect Estimationcited by 20
  22. 2024Neural Causal Abstractionscited by 20
  23. 2024Doubly Robust Causal Effect Estimation under Networked Interference via Targeted Learningcited by 19
  24. 2021Auto IV: Counterfactual Prediction via Automatic Instrumental Variable Decompositioncited by 18
  25. 2021Estimating Categorical Counterfactuals via Deep Twin Networkscited by 18
  26. 2021A Theoretical Analysis on Independence-driven Importance Weighting for Covariate-shift Generalizationcited by 18
  27. 2022Robust and Agnostic Learning of Conditional Distributional Treatment Effectscited by 18
  28. 2022Learning Disentangled Representations for Counterfactual Regression via Mutual Information Minimizationcited by 18
  29. 2024Model-agnostic meta-learners for estimating heterogeneous treatment effects over timecited by 18
  30. 2023Zero-shot causal learningcited by 17
  31. 2023Estimating Treatment Effects from Irregular Time Series Observations with Hidden Confounderscited by 17
  32. 2023Towards Causal Foundation Model: on Duality between Causal Inference and Attentioncited by 17
  33. 2023Causal Inference with Conditional Front-Door Adjustment and Identifiable Variational Autoencodercited by 17
  34. 2023A Neural Framework for Generalized Causal Sensitivity Analysiscited by 17
  35. 2024DiffPO: A causal diffusion model for learning distributions of potential outcomescited by 17
  36. 2021Deconfounding Temporal Autoencoder: Estimating Treatment Effects over Time Using Noisy Proxiescited by 16
  37. 2022DESCN: Deep Entire Space Cross Networks for Individual Treatment Effect Estimationcited by 16
  38. 2023CF-GODE: Continuous-Time Causal Inference for Multi-Agent Dynamical Systemscited by 16

50 most cited of 327 All 327 (JSON)