mlsanityData to 7 Oct 2026

Neural Causal Models for Counterfactual Identification and Estimation

arXiv 2210.00035 ↗First posted 30 Sep 2022cs.LGcited by 54

Not on the map. Why?

Abstract (arXiv)

Evaluating hypothetical statements about how the world would be had a different course of action been taken is arguably one key capability expected from modern AI systems. Counterfactual reasoning underpins discussions in fairness, the determination of blame and responsibility, credit assignment, and regret. In this paper, we study the evaluation of counterfactual statements through neural models. Specifically, we tackle two causal problems required to make such evaluations, i.e., counterfactual identification and estimation from an arbitrary combination of observational and experimental data. First, we show that neural causal models (NCMs) are expressive enough and encode the structural constraints necessary for performing counterfactual reasoning. Second, we develop an algorithm for simultaneously identifying and estimating counterfactual distributions. We show that this algorithm is sound and complete for deciding counterfactual identification in general settings. Third, considering the practical implications of these results, we introduce a new strategy for modeling NCMs using generative adversarial networks. Simulations corroborate with the proposed methodology.

Key facts. Cited by 54 papers in the map (data through 7 Oct 2026). Builds on 25 of its 78 references that are in the map. First posted on arXiv 30 Sep 2022.

Builds on

25 of 78 references.

References · 25

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2022Generative Adversarial Networkscited by 5,603
  3. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  4. 2017Improved Training of Wasserstein GANscited by 2,223
  5. 2017Causal Effect Inference with Deep Latent-Variable Modelscited by 408
  6. 2016Learning Representations for Counterfactual Inferencecited by 327
  7. 2015MADE: Masked Autoencoder for Distribution Estimationcited by 306
  8. 2019Adapting Neural Networks for the Estimation of Treatment Effectscited by 285
  9. 2013Direct and Indirect Effectscited by 276
  10. 2020Deep Structural Causal Models for Tractable Counterfactual Inferencecited by 210
  11. 2017CausalGAN: Learning Causal Implicit Generative Models with Adversarial Trainingcited by 152
  12. 2019Double Reinforcement Learning for Efficient Off-Policy Evaluation in Markov Decision Processescited by 118
13 more
  1. 2021The Causal-Neural Connection: Expressiveness, Learnability, and Inferencecited by 97
  2. 2021Partial Counterfactual Identification from Observational and Experimental Datacited by 64
  3. 2020A Framework For Contrastive Self-Supervised Learning And Designing A New Approachcited by 51
  4. 2018DeepMatch: Balancing Deep Covariate Representations for Causal Inference Using Adversarial Trainingcited by 42
  5. 2021Relating Graph Neural Networks to Structural Causal Modelscited by 39
  6. 2021Nested Counterfactual Identification from Arbitrary Surrogate Experimentscited by 38
  7. 2018A Survey of Learning Causality with Data: Problems and Methodscited by 37
  8. 2019Adversarial Balancing-based Representation Learning for Causal Effect Inference with Observational Datacited by 29
  9. 2017Nonparametric causal effects based on incremental propensity score interventionscited by 28
  10. 2020Probabilistic Reasoning across the Causal Hierarchycited by 19
  11. 2021VACA: Design of Variational Graph Autoencoders for Interventional and Counterfactual Queriescited by 18
  12. 2018Causal Identification under Markov Equivalencecited by 15
  13. 2021SBI: A Simulation-Based Test of Identifiability for Bayesian Causal Inferencecited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 11; 2024: 15; 2025: 16; 2026: 11.

54 papers.

Sort:

By area:

  1. 2023High Fidelity Image Counterfactuals with Probabilistic Causal Modelscited by 53
  2. 2023Causal normalizing flows: from theory to practicecited by 49
  3. 2025CausalPFN: Amortized Causal Effect Estimation via In-Context Learningcited by 43
  4. 2023Counterfactual Identifiability of Bijective Causal Modelscited by 42
  5. 2023Causal Interpretation of Self-Attention in Pre-Trained Transformerscited by 30
  6. 2023Sharp Bounds for Generalized Causal Sensitivity Analysiscited by 24
  7. 2024Neural Causal Abstractionscited by 20
  8. 2024Counterfactual Image Editingcited by 20
  9. 2023Towards Causal Foundation Model: on Duality between Causal Inference and Attentioncited by 17
  10. 2023A Neural Framework for Generalized Causal Sensitivity Analysiscited by 17
  11. 2023Partial Counterfactual Identification of Continuous Outcomes with a Curvature Sensitivity Modelcited by 14
  12. 2024Hybrid2 Neural ODE Causal Modeling and an Application to Glycemic Responsecited by 13
38 more
  1. 2024Mitigating attribute amplification in counterfactual image generationcited by 12
  2. 2022Deep Causal Learning: Representation, Discovery and Inferencecited by 11
  3. 2025CF-Seg: Counterfactuals meet Segmentationcited by 10
  4. 2024Modular Learning of Deep Causal Generative Models for High-dimensional Causal Inferencecited by 9
  5. 2024Learning Structural Causal Models through Deep Generative Models: Methods, Guarantees, and Challengescited by 8
  6. 2024The Fragility of Fairness: Causal Sensitivity Analysis for Fair Machine Learningcited by 8
  7. 2025DeCaFlow: A deconfounding causal generative modelcited by 8
  8. 2025Diffusion Counterfactual Generation with Semantic Abductioncited by 8
  9. 2024Counterfactual Concept Bottleneck Modelscited by 7
  10. 2024Latent Causal Modeling for 3D Brain MRI Counterfactualscited by 7
  11. 2024Deep Autoregressive Models as Causal Inference Enginescited by 6
  12. 2024Causality from Bottom to Top: A Surveycited by 5
  13. 2025Counterfactual Identifiability via Dynamic Optimal Transportcited by 5
  14. 2023Consistent End-to-End Estimation for Counterfactual Fairnesscited by 4
  15. 2024Conditional Generative Models are Sufficient to Sample from Any Causal Effect Estimandcited by 4
  16. 2025CausalMan: A physics-based simulator for large-scale causalitycited by 4
  17. 2025Interpretable Neural Causal Models with TRAM-DAGscited by 4
  18. 2024Consistency of Neural Causal Partial Identificationcited by 3
  19. 2024Estimating Causal Effects from Learned Causal Networkscited by 3
  20. 2025DoFlow: Flow-based Generative Models for Interventional and Counterfactual Forecasting on Time Seriescited by 3
  21. 2025Segmentor-Guided Counterfactual Fine-Tuning for Locally Coherent and Targeted Image Synthesiscited by 2
  22. 2025Towards Causal Market Simulatorscited by 2
  23. 2026Information-Theoretic Causal Bounds under Unmeasured Confoundingcited by 2
  24. 2026IV-ICL: Bounding Causal Effects with Instrumental Variables via In-Context Learningcited by 2
  25. 2023Advancing Counterfactual Inference through Nonlinear Quantile Regressioncited by 1
  26. 2025Learning Probabilities of Causation with Mask-Augmented Datacited by 1
  27. 2025Assessing the robustness of heterogeneous treatment effects in survival analysis under informative censoringcited by 1
  28. 2026Computational Identifiabilitycited by 1
  29. 2023A General Neural Causal Model for Interactive Recommendationcited by 0
  30. 2024Causally Consistent Normalizing Flowcited by 0
  31. 2025Unsupervised Structural-Counterfactual Generation under Domain Shiftcited by 0
  32. 2025Learning Counterfactually Fair Models via Improved Generation with Neural Causal Modelscited by 0
  33. 2025Causal Sensitivity Identification using Generative Learningcited by 0
  34. 2025Towards Error-Centric Intelligence II: Energy-Structured Causal Modelscited by 0
  35. 2026Uncertainty-aware Causal Decision Making via Effect Bound Decompositioncited by 0
  36. 2026Kolmogorov-Arnold causal generative modelscited by 0
  37. 2026Positional Segmentor-Guided Counterfactual Fine-Tuning for Spatially Localized Image Synthesiscited by 0
  38. 2026Counterfactual identifiability beyond global monotonicity: non-monotone triangular structural causal modelscited by 0

50 most cited of 54 All 54 (JSON)