mlsanityData to 7 Oct 2026

Natural Counterfactuals With Necessary Backtracking

arXiv 2402.01607 ↗First posted 2 Feb 2024cs.AI cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Counterfactual reasoning is pivotal in human cognition and especially important for providing explanations and making decisions. While Judea Pearl's influential approach is theoretically elegant, its generation of a counterfactual scenario often requires too much deviation from the observed scenarios to be feasible, as we show using simple examples. To mitigate this difficulty, we propose a framework of natural counterfactuals and a method for generating counterfactuals that are more feasible with respect to the actual data distribution. Our methodology incorporates a certain amount of backtracking when needed, allowing changes in causally preceding variables to minimize deviations from realistic scenarios. Specifically, we introduce a novel optimization framework that permits but also controls the extent of backtracking with a naturalness criterion. Empirical experiments demonstrate the effectiveness of our method. The code is available at https://github.com/GuangyuanHao/naturalcounterfactuals.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 43 references that are in the map. First posted on arXiv 2 Feb 2024.

Builds on

22 of 43 references.

References · 22

  1. 2021Convex optimizationcited by 2,479
  2. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  3. 2019Explaining Machine Learning Classifiers through Diverse Counterfactual Explanationscited by 612
  4. 2018Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negativescited by 261
  5. 2020Algorithmic Recourse: from Counterfactual Explanations to Interventionscited by 250
  6. 2019FACE: Feasible and Actionable Counterfactual Explanationscited by 232
  7. 2020Deep Structural Causal Models for Tractable Counterfactual Inferencecited by 210
  8. 2017CausalGAN: Learning Causal Implicit Generative Models with Adversarial Trainingcited by 152
  9. 2019Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systemscited by 128
  10. 2019The Hidden Assumptions Behind Counterfactual Explanations and Principal Reasonscited by 115
  11. 2019Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Modelscited by 114
  12. 2019BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modelingcited by 109
10 more
  1. 2022Diffusion Causal Models for Counterfactual Estimationcited by 87
  2. 2020Sample-Efficient Reinforcement Learning via Counterfactual-Based Data Augmentationcited by 57
  3. 2018Morpho-MNIST: Quantitative Assessment and Diagnostics for Representation Learningcited by 56
  4. 2020Evaluating and Mitigating Bias in Image Classifiers: A Causal Perspective Using Counterfactualscited by 56
  5. 2023High Fidelity Image Counterfactuals with Probabilistic Causal Modelscited by 53
  6. 2021Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertaintiescited by 41
  7. 2023Measuring axiomatic soundness of counterfactual image modelscited by 34
  8. 2020Convex Density Constraints for Computing Plausible Counterfactual Explanationscited by 32
  9. 2023Self-Interpretable Time Series Prediction with Counterfactual Explanationscited by 24
  10. 2022Backtracking Counterfactualscited by 15

Built on by

Not cited yet.