mlsanityData to 7 Oct 2026

Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties

arXiv 2103.08951 ↗First posted 16 Mar 2021cs.LG stat.APcited by 41

Not on the map. Why?

Abstract (arXiv)

Counterfactual explanations (CEs) are a practical tool for demonstrating why machine learning classifiers make particular decisions. For CEs to be useful, it is important that they are easy for users to interpret. Existing methods for generating interpretable CEs rely on auxiliary generative models, which may not be suitable for complex datasets, and incur engineering overhead. We introduce a simple and fast method for generating interpretable CEs in a white-box setting without an auxiliary model, by using the predictive uncertainty of the classifier. Our experiments show that our proposed algorithm generates more interpretable CEs, according to IM1 scores, than existing methods. Additionally, our approach allows us to estimate the uncertainty of a CE, which may be important in safety-critical applications, such as those in the medical domain.

Key facts. Cited by 41 papers in the map (data through 7 Oct 2026). Builds on 23 of its 33 references that are in the map. First posted on arXiv 16 Mar 2021.

Builds on

23 of 33 references.

References · 23

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  5. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  6. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  7. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  8. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
  9. 2018Robustness May Be at Odds with Accuracycited by 873
  10. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  11. 2016The Mythos of Model Interpretabilitycited by 716
  12. 2017Adversarial Patchcited by 514
11 more
  1. 2019Your Classifier is Secretly an Energy Based Model and You Should Treat it Like Onecited by 402
  2. 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
  3. 2018Actionable Recourse in Linear Classificationcited by 327
  4. 2018Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negativescited by 261
  5. 2019Interpretable Counterfactual Explanations Guided by Prototypescited by 223
  6. 2018Understanding Measures of Uncertainty for Adversarial Example Detectioncited by 177
  7. 2019Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systemscited by 128
  8. 2019The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanationscited by 97
  9. 2020Uncertainty Estimation Using a Single Deep Deterministic Neural Networkcited by 37
  10. 2018What is Interpretable? Using Machine Learning to Design Interpretable Decision-Support Systemscited by 11
  11. 2018Sufficient Conditions for Idealised Models to Have No Adversarial Examples: a Theoretical and Empirical Study with Bayesian Neural Networkscited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 11; 2023: 7; 2024: 5; 2025: 7; 2026: 4.

41 papers.

Sort:

By area:

  1. 2022Diffusion Visual Counterfactual Explanationscited by 96
  2. 2022Diffusion Causal Models for Counterfactual Estimationcited by 87
  3. 2021CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithmscited by 85
  4. 2022Diffusion Models for Counterfactual Explanationscited by 79
  5. 2023High Fidelity Image Counterfactuals with Probabilistic Causal Modelscited by 53
  6. 2023Adversarial Counterfactual Visual Explanationscited by 47
  7. 2022Sparse Visual Counterfactual Explanations in Image Spacecited by 30
  8. 2022Diffeomorphic Counterfactuals with Generative Modelscited by 29
  9. 2022Scientific Inference With Interpretable Machine Learning: Analyzing Models to Learn About Real-World Phenomenacited by 21
  10. 2021CounterNet: End-to-End Training of Prediction Aware Counterfactual Explanationscited by 17
  11. 2021Uncertainty Estimation and Out-of-Distribution Detection for Counterfactual Explanations: Pitfalls and Solutionscited by 16
  12. 2024Global Counterfactual Directionscited by 15
29 more
  1. 2024Rethinking Visual Counterfactual Explanations Through Region Constraintcited by 14
  2. 2022Counterfactual Explanations for Misclassified Images: How Human and Machine Explanations Differcited by 12
  3. 2023Endogenous Macrodynamics in Algorithmic Recoursecited by 9
  4. 2021Attribution of Predictive Uncertainties in Classification Modelscited by 8
  5. 2025Diffusion Counterfactual Generation with Semantic Abductioncited by 8
  6. 2021On Quantitative Evaluations of Counterfactualscited by 7
  7. 2021DeDUCE: Generating Counterfactual Explanations Efficientlycited by 6
  8. 2022What is Flagged in Uncertainty Quantification? Latent Density Models for Uncertainty Categorizationcited by 5
  9. 2023Designing User-Centric Behavioral Interventions to Prevent Dysglycemia with Novel Counterfactual Explanationscited by 5
  10. 2023Faithful Model Explanations through Energy-Constrained Conformal Counterfactualscited by 5
  11. 2025GlyTwin: Digital Twin for Glucose Control in Type 1 Diabetes Through Optimal Behavioral Modifications Using Patient-Centric Counterfactualscited by 5
  12. 2025From Search To Sampling: Generative Models For Robust Algorithmic Recoursecited by 5
  13. 2023Explaining Black-Box Models through Counterfactualscited by 4
  14. 2024Causal Generative Explainers using Counterfactual Inference: A Case Study on the Morpho-MNIST Datasetcited by 4
  15. 2024Generating Feasible and Plausible Counterfactual Explanations for Outcome Prediction of Business Processescited by 4
  16. 2025Uncertainty Quantification as a Principled Foundation for Explainable Artificial Intelligence: A Case Study of Counterfactual Explanationscited by 2
  17. 2026Concerning Uncertainty -- A Systematic Survey of Uncertainty-Aware XAIcited by 2
  18. 2025Improving Counterfactual Truthfulness for Molecular Property Prediction through Uncertainty Quantificationcited by 1
  19. 2025Counterfactual Visual Explanation via Causally-Guided Adversarial Steeringcited by 1
  20. 2026Provably Robust Bayesian Counterfactual Explanations under Model Changescited by 1
  21. 2021Dense Uncertainty Estimation via an Ensemble-based Conditional Latent Variable Modelcited by 0
  22. 2022Beyond Model Interpretability: On the Faithfulness and Adversarial Robustness of Contrastive Textual Explanationscited by 0
  23. 2022Decomposing Counterfactual Explanations for Consequential Decision Makingcited by 0
  24. 2022Clarity: an improved gradient method for producing quality visual counterfactual explanationscited by 0
  25. 2023Two-step counterfactual generation for OOD examplescited by 0
  26. 2024Natural Counterfactuals With Necessary Backtrackingcited by 0
  27. 2025CONFEX: Uncertainty-Aware Counterfactual Explanations with Conformal Guaranteescited by 0
  28. 2026Counterfactual Training: Teaching Models Plausible and Actionable Explanationscited by 0
  29. 2026AVCG: A Generalized Variational Framework for Counterfactual Generation under Hypothesis Distributionscited by 0