mlsanityData to 7 Oct 2026

Deep Backtracking Counterfactuals for Causally Compliant Explanations

arXiv 2310.07665 ↗First posted 11 Oct 2023cs.AI cs.LG stat.MLcited by 8

Not on the map. Why?

Abstract (arXiv)

Counterfactuals answer questions of what would have been observed under altered circumstances and can therefore offer valuable insights. Whereas the classical interventional interpretation of counterfactuals has been studied extensively, backtracking constitutes a less studied alternative where all causal laws are kept intact. In the present work, we introduce a practical method called deep backtracking counterfactuals (DeepBC) for computing backtracking counterfactuals in structural causal models that consist of deep generative components. We propose two distinct versions of our method--one utilizing Langevin Monte Carlo sampling and the other employing constrained optimization--to generate counterfactuals for high-dimensional data. As a special case, our formulation reduces to methods in the field of counterfactual explanations. Compared to these, our approach represents a causally compliant, versatile and modular alternative. We demonstrate these properties experimentally on a modified version of MNIST and CelebA.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 55 of its 89 references that are in the map. First posted on arXiv 11 Oct 2023.

Builds on

55 of 89 references.

References · 55

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2020Denoising Diffusion Implicit Modelscited by 9,655
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  5. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  6. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  7. 2015Variational Inference with Normalizing Flowscited by 2,161
  8. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  9. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
  10. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  11. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 636
  12. 2019Explaining Machine Learning Classifiers through Diverse Counterfactual Explanationscited by 612
38 more
  1. 2019Neural Spline Flowscited by 590
  2. 2019Counterfactual Visual Explanationscited by 312
  3. 2021The Intrinsic Dimension of Images and Its Impact on Learningcited by 307
  4. 2015MADE: Masked Autoencoder for Distribution Estimationcited by 306
  5. 2020Algorithmic Recourse: from Counterfactual Explanations to Interventionscited by 250
  6. 2020Deep Structural Causal Models for Tractable Counterfactual Inferencecited by 210
  7. 2020Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Reviewcited by 174
  8. 2019Learning Likelihoods with Conditional Normalizing Flowscited by 170
  9. 2021Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICAcited by 158
  10. 2017CausalGAN: Learning Causal Implicit Generative Models with Adversarial Trainingcited by 152
  11. 2019Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifierscited by 143
  12. 2020Algorithmic recourse under imperfect causal knowledge: a probabilistic approachcited by 139
  13. 2019From Variational to Deterministic Autoencoderscited by 131
  14. 2021CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networkscited by 118
  15. 2020CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learningcited by 109
  16. 2023Nonparametric Identifiability of Causal Representations from Unknown Interventionscited by 105
  17. 2020Causal Autoregressive Flowscited by 97
  18. 2023Learning Linear Causal Representations from Interventions under General Nonlinear Mixingcited by 92
  19. 2022Diffusion Causal Models for Counterfactual Estimationcited by 87
  20. 2018Semi-Amortized Variational Autoencoderscited by 83
  21. 2021Robust Counterfactual Explanations on Graph Neural Networkscited by 72
  22. 2023Identifiability of latent-variable and structural-equation models: from linear to nonlinearcited by 58
  23. 2018Morpho-MNIST: Quantitative Assessment and Diagnostics for Representation Learningcited by 56
  24. 2020Evaluating and Mitigating Bias in Image Classifiers: A Causal Perspective Using Counterfactualscited by 56
  25. 2021Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanationscited by 56
  26. 2023normflows: A PyTorch Package for Normalizing Flowscited by 56
  27. 2023Causal Component Analysiscited by 56
  28. 2022Causal Discovery in Heterogeneous Environments Under the Sparse Mechanism Shift Hypothesiscited by 54
  29. 2023Causal normalizing flows: from theory to practicecited by 49
  30. 2022CLEAR: Generative Counterfactual Explanations on Graphscited by 48
  31. 2020CausalVAE: Structured Causal Disentanglement in Variational Autoencodercited by 47
  32. 2022A Causal Lens for Controllable Text Generationcited by 45
  33. 2023Counterfactual Identifiability of Bijective Causal Modelscited by 42
  34. 2021STEEX: Steering Counterfactual Explanations with Semanticscited by 40
  35. 2023BISCUIT: Causal Representation Learning from Binary Interactionscited by 38
  36. 2022Causal Explanations and XAIcited by 30
  37. 2022Sparse Visual Counterfactual Explanations in Image Spacecited by 30
  38. 2022Embrace the Gap: VAEs Perform Independent Mechanism Analysiscited by 28

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 2; 2025: 5.

8 papers.

  1. 2024Benchmarking Counterfactual Image Generationcited by 22
  2. 2024Identifiable Causal Representation Learning: Unsupervised, Multi-View, and Multi-Environmentcited by 12
  3. 2025Diffusion Counterfactual Generation with Semantic Abductioncited by 8
  4. 2023Scalable Counterfactual Distribution Estimation in Multivariate Causal Modelscited by 6
  5. 2025Causally Steered Diffusion for Automated Video Counterfactual Generationcited by 5
  6. 2025Searching for Actual Causes: Approximate Algorithms with Adjustable Precisioncited by 1
  7. 2025A New Approach to Backtracking Counterfactual Explanations: A Unified Causal Framework for Efficient Model Interpretabilitycited by 0
  8. 2025Cyclic Counterfactuals under Shift-Scale Interventionscited by 0