mlsanityData to 7 Oct 2026

Rethinking Distance Metrics for Counterfactual Explainability

arXiv 2410.14522 ↗First posted 18 Oct 2024cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Counterfactual explanations have been a popular method of post-hoc explainability for a variety of settings in Machine Learning. Such methods focus on explaining classifiers by generating new data points that are similar to a given reference, while receiving a more desirable prediction. In this work, we investigate a framing for counterfactual generation methods that considers counterfactuals not as independent draws from a region around the reference, but as jointly sampled with the reference from the underlying data distribution. Through this framing, we derive a distance metric, tailored for counterfactual similarity that can be applied to a broad range of settings. Through both quantitative and qualitative analyses of counterfactual generation methods, we show that this framing allows us to express more nuanced dependencies among the covariates.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 35 of its 49 references that are in the map. First posted on arXiv 18 Oct 2024.

Builds on

35 of 49 references.

References · 35

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  4. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  5. 2015Variational Inference with Normalizing Flowscited by 2,161
  6. 2018Sanity Checks for Saliency Mapscited by 1,149
  7. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  8. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  9. 2020Concept Bottleneck Modelscited by 1,022
  10. 2019Explaining Machine Learning Classifiers through Diverse Counterfactual Explanationscited by 612
  11. 2019The many Shapley values for model explanationcited by 341
  12. 2018Actionable Recourse in Linear Classificationcited by 327
23 more
  1. 2020Algorithmic Recourse: from Counterfactual Explanations to Interventionscited by 250
  2. 2019FACE: Feasible and Actionable Counterfactual Explanationscited by 232
  3. 2019Learning Model-Agnostic Counterfactual Explanations for Tabular Datacited by 146
  4. 2019Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifierscited by 143
  5. 2020Algorithmic recourse under imperfect causal knowledge: a probabilistic approachcited by 139
  6. 2019Sanity Checks for Saliency Metricscited by 119
  7. 2019The Hidden Assumptions Behind Counterfactual Explanations and Principal Reasonscited by 115
  8. 2021Do Concept Bottleneck Models Learn as Intended?cited by 114
  9. 2022Algorithms to estimate Shapley value feature attributionscited by 114
  10. 2021Counterfactual Explanations Can Be Manipulatedcited by 113
  11. 2019CXPlain: Causal Explanations for Model Interpretation under Uncertaintycited by 98
  12. 2019The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanationscited by 97
  13. 2021CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithmscited by 85
  14. 2020Shapley Flow: A Graph-based Approach to Interpreting Model Predictionscited by 51
  15. 2017Inverse Classification for Comparison-based Interpretability in Machine Learningcited by 49
  16. 2018Generating Counterfactual Explanations with Natural Languagecited by 37
  17. 2021Consistent Counterfactuals for Deep Modelscited by 37
  18. 2023Towards Understanding In-Context Learning with Contrastive Demonstrations and Saliency Mapscited by 35
  19. 2023Counterfactual Learning on Graphs: A Surveycited by 22
  20. 2024On the Concept Trustworthiness in Concept Bottleneck Modelscited by 22
  21. 2020Counterfactual Explanation Based on Gradual Construction for Deep Networkscited by 12
  22. 2023Towards a Deeper Understanding of Concept Bottleneck Models Through End-to-End Explanationcited by 7
  23. 2021Explainable Neural Network-based Modulation Classification via Concept Bottleneck Modelscited by 5

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025GlyTwin: Digital Twin for Glucose Control in Type 1 Diabetes Through Optimal Behavioral Modifications Using Patient-Centric Counterfactualscited by 5