mlsanityData to 7 Oct 2026

Counterfactual Identifiability of Bijective Causal Models

arXiv 2302.02228 ↗First posted 4 Feb 2023stat.ML cs.LGcited by 42

Not on the map. Why?

Abstract (arXiv)

We study counterfactual identifiability in causal models with bijective generation mechanisms (BGM), a class that generalizes several widely-used causal models in the literature. We establish their counterfactual identifiability for three common causal structures with unobserved confounding, and propose a practical learning method that casts learning a BGM as structured generative modeling. Learned BGMs enable efficient counterfactual estimation and can be obtained using a variety of deep conditional generative models. We evaluate our techniques in a visual task and demonstrate its application in a real-world video streaming simulation task.

Key facts. Cited by 42 papers in the map (data through 7 Oct 2026). Builds on 67 of its 127 references that are in the map. First posted on arXiv 4 Feb 2023.

Builds on

67 of 127 references.

References · 67

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  5. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  6. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  7. 2016Density estimation using Real NVPcited by 2,029
  8. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  9. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  10. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
  11. 2019Neural Spline Flowscited by 590
  12. 2019Variational Autoencoders and Nonlinear ICA: A Unifying Frameworkcited by 494
38 more
  1. 2020Underspecification Presents Challenges for Credibility in Modern Machine Learningcited by 488
  2. 2017Causal Effect Inference with Deep Latent-Variable Modelscited by 408
  3. 2018Pyro: Deep Universal Probabilistic Programmingcited by 379
  4. 2016Learning Representations for Counterfactual Inferencecited by 327
  5. 2018Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learningcited by 278
  6. 2019Residual Flows for Invertible Generative Modelingcited by 256
  7. 2013Causal Discovery with Continuous Additive Noise Modelscited by 252
  8. 2017AttGAN: Facial Attribute Editing by Only Changing What You Wantcited by 241
  9. 2020Deep Structural Causal Models for Tractable Counterfactual Inferencecited by 210
  10. 2019Learning Likelihoods with Conditional Normalizing Flowscited by 170
  11. 2017CausalGAN: Learning Causal Implicit Generative Models with Adversarial Trainingcited by 152
  12. 2016Identifying Causal Effects With Proxy Variables of an Unmeasured Confoundercited by 138
  13. 2019From Variational to Deterministic Autoencoderscited by 131
  14. 2016Learning in Implicit Generative Modelscited by 124
  15. 2017Fader Networks: Manipulating Images by Sliding Attributescited by 118
  16. 2019Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Modelscited by 114
  17. 2018The Blessings of Multiple Causescited by 103
  18. 2020Causal Autoregressive Flowscited by 97
  19. 2021The Causal-Neural Connection: Expressiveness, Learnability, and Inferencecited by 97
  20. 2022Deep End-to-end Causal Inferencecited by 93
  21. 2013Probabilities of Causation: Bounds and Identificationcited by 89
  22. 2022Diffusion Causal Models for Counterfactual Estimationcited by 87
  23. 2013Counterfactual Probabilities: Computational Methods, Bounds and Applicationscited by 67
  24. 2019Causal structure based root cause analysis of outlierscited by 65
  25. 2021Partial Counterfactual Identification from Observational and Experimental Datacited by 64
  26. 2020Counterfactual Credit Assignment in Model-Free Reinforcement Learningcited by 60
  27. 2020Sample-Efficient Reinforcement Learning via Counterfactual-Based Data Augmentationcited by 57
  28. 2022On the Identifiability and Estimation of Causal Location-Scale Noise Modelscited by 56
  29. 2018Conditional Density Estimation with Bayesian Normalising Flowscited by 54
  30. 2022Neural Causal Models for Counterfactual Identification and Estimationcited by 54
  31. 2020Invertible Generative Modeling using Linear Rational Splinescited by 39
  32. 2021Relating Graph Neural Networks to Structural Causal Modelscited by 39
  33. 2021Nested Counterfactual Identification from Arbitrary Surrogate Experimentscited by 38
  34. 2022Identifying Patient-Specific Root Causes with the Heteroscedastic Noise Modelcited by 38
  35. 2019Structured Output Learning with Conditional Generative Flowscited by 37
  36. 2017ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matchingcited by 32
  37. 2022Counterfactual harmcited by 29
  38. 2017Nonparametric causal effects based on incremental propensity score interventionscited by 28

50 most cited of 67 All 67 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 10; 2024: 6; 2025: 18; 2026: 8.

42 papers.

Sort:

By area:

  1. 2023Causal normalizing flows: from theory to practicecited by 49
  2. 2023From Identifiable Causal Representations to Controllable Counterfactual Generation: A Survey on Causal Generative Modelingcited by 21
  3. 2024Counterfactual Image Editingcited by 20
  4. 2023Learning Causally Disentangled Representations via the Principle of Independent Causal Mechanismscited by 14
  5. 2023Partial Counterfactual Identification of Continuous Outcomes with a Curvature Sensitivity Modelcited by 14
  6. 2023Finding Counterfactually Optimal Action Sequences in Continuous State Spacescited by 12
  7. 2023Deep Backtracking Counterfactuals for Causally Compliant Explanationscited by 8
  8. 2024Learning Structural Causal Models through Deep Generative Models: Methods, Guarantees, and Challengescited by 8
  9. 2024Counterfactual Fairness by Combining Factual and Counterfactual Predictionscited by 8
  10. 2025DeCaFlow: A deconfounding causal generative modelcited by 8
  11. 2024Deep Learning With DAGscited by 7
  12. 2025Distinguishing Cause from Effect with Causal Velocity Modelscited by 6
30 more
  1. 2025Counterfactual Identifiability via Dynamic Optimal Transportcited by 5
  2. 2023Towards Characterizing Domain Counterfactuals For Invertible Latent Causal Modelscited by 4
  3. 2023Consistent End-to-End Estimation for Counterfactual Fairnesscited by 4
  4. 2025Interpretable Neural Causal Models with TRAM-DAGscited by 4
  5. 2025Multi-Domain Causal Discovery in Bijective Causal Modelscited by 4
  6. 2025Counterfactual reasoning: an analysis of in-context emergencecited by 4
  7. 2025Causal-Adapter: Taming Text-to-Image Diffusion for Faithful Counterfactual Generationcited by 4
  8. 2024Causal Bayesian Optimization via Exogenous Distribution Learningcited by 3
  9. 2025DoFlow: Flow-based Generative Models for Interventional and Counterfactual Forecasting on Time Seriescited by 3
  10. 2026FoundCause: Causal Discovery with Latent Confounders from Observational Datacited by 3
  11. 2024Lookahead Counterfactual Fairnesscited by 2
  12. 2025Counterfactually Fair Conformal Predictioncited by 2
  13. 2023Advancing Counterfactual Inference through Nonlinear Quantile Regressioncited by 1
  14. 2023Agent-Specific Effects: A Causal Effect Propagation Analysis in Multi-Agent MDPscited by 1
  15. 2025Flow-based Generative Modeling of Potential Outcomes and Counterfactualscited by 1
  16. 2025Flow IV: Counterfactual Inference In Nonseparable Outcome Models Using Instrumental Variablescited by 1
  17. 2026CEPAE: Conditional Entropy-Penalized Autoencoders for Time Series Counterfactualscited by 1
  18. 2025Learning Counterfactual Outcomes Under Rank Preservationcited by 0
  19. 2025Unsupervised Structural-Counterfactual Generation under Domain Shiftcited by 0
  20. 2025Learning Counterfactually Fair Models via Improved Generation with Neural Causal Modelscited by 0
  21. 2025A New Approach to Backtracking Counterfactual Explanations: A Unified Causal Framework for Efficient Model Interpretabilitycited by 0
  22. 2025Partially Functional Dynamic Backdoor Diffusion-based Causal Modelcited by 0
  23. 2025What is a good matching of probability measures? A counterfactual lens on transport mapscited by 0
  24. 2025Wasserstein Distributionally Robust Optimization Through the Lens of Structural Causal Models and Individual Fairnesscited by 0
  25. 2026Kolmogorov-Arnold causal generative modelscited by 0
  26. 2026Counterfactual identifiability beyond global monotonicity: non-monotone triangular structural causal modelscited by 0
  27. 2026Causal Learning with the Invariance Principlecited by 0
  28. 2026Causal Variational Deep Embedding: A Family of Interventional Generators for Confounded Imagescited by 0
  29. 2026Causal Gaussian Processes for Robust Treatment Effect Evaluation with Unobserved Confoundingcited by 0
  30. 2026Beyond the Shadows of Plato's Cave: Evaluating False Memory in Autonomous Agents via Counterfactual Reasoningcited by 0