mlsanityData to 7 Oct 2026

Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations

arXiv 1905.07697 ↗First posted 19 May 2019cs.LG cs.CY stat.MLcited by 612

Not on the map. Why?

Abstract (arXiv)

Post-hoc explanations of machine learning models are crucial for people to understand and act on algorithmic predictions. An intriguing class of explanations is through counterfactuals, hypothetical examples that show people how to obtain a different prediction. We posit that effective counterfactual explanations should satisfy two properties: feasibility of the counterfactual actions given user context and constraints, and diversity among the counterfactuals presented. To this end, we propose a framework for generating and evaluating a diverse set of counterfactual explanations based on determinantal point processes. To evaluate the actionability of counterfactuals, we provide metrics that enable comparison of counterfactual-based methods to other local explanation methods. We further address necessary tradeoffs and point to causal implications in optimizing for counterfactuals. Our experiments on four real-world datasets show that our framework can generate a set of counterfactuals that are diverse and well approximate local decision boundaries, outperforming prior approaches to generating diverse counterfactuals. We provide an implementation of the framework at https://github.com/microsoft/DiCE.

Key facts. Cited by 612 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 81; 2022: 96; 2023: 118; 2024: 113; 2025: 104; 2026: 100.

612 papers.

Sort:

By area:

  1. 2021Deep Neural Networks and Tabular Data: A Surveycited by 489
  2. 2021Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyondcited by 177
  3. 2021Benchmarking and Survey of Explanation Methods for Black Box Modelscited by 136
  4. 2022Text and Patterns: For Effective Chain of Thought, It Takes Two to Tangocited by 128
  5. 2021Human-Centered Explainable AI (XAI): From Algorithms to User Experiencescited by 123
  6. 2021Explaining in Style: Training a GAN to explain a classifier in StyleSpacecited by 122
  7. 2023AI Transparency in the Age of LLMs: A Human-Centered Research Roadmapcited by 119
  8. 2021Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyondcited by 116
  9. 2021Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identificationcited by 114
  10. 2021Counterfactual Explanations Can Be Manipulatedcited by 113
  11. 2021Robustness Gym: Unifying the NLP Evaluation Landscapecited by 107
  12. 2021Interpretable Image Classification with Differentiable Prototypes Assignmentcited by 97
38 more
  1. 2022Diffusion Visual Counterfactual Explanationscited by 96
  2. 2021The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanationscited by 86
  3. 2021CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithmscited by 85
  4. 2021If Only We Had Better Counterfactual Explanations: Five Key Deficits to Rectify in the Evaluation of Counterfactual XAI Techniquescited by 82
  5. 2022Diffusion Models for Counterfactual Explanationscited by 79
  6. 2022TalkToModel: Explaining Machine Learning Models with Interactive Natural Language Conversationscited by 65
  7. 2021NICE: An Algorithm for Nearest Instance Counterfactual Explanationscited by 62
  8. 2021Counterfactuals and Causability in Explainable Artificial Intelligence: Theory, Algorithms, and Applicationscited by 59
  9. 2022GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networkscited by 57
  10. 2021Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanationscited by 56
  11. 2021Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactualscited by 55
  12. 2022Framework for Evaluating Faithfulness of Local Explanationscited by 55
  13. 2022Post-Hoc Explanations Fail to Achieve their Purpose in Adversarial Contextscited by 53
  14. 2023High Fidelity Image Counterfactuals with Probabilistic Causal Modelscited by 53
  15. 2023TIBET: Identifying and Evaluating Biases in Text-to-Image Generative Modelscited by 51
  16. 2022CLEAR: Generative Counterfactual Explanations on Graphscited by 48
  17. 2023Adversarial Counterfactual Visual Explanationscited by 47
  18. 2021Local Explanations via Necessity and Sufficiency: Unifying Theory and Practicecited by 45
  19. 2022Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic Recoursecited by 40
  20. 2022DoWhy-GCM: An extension of DoWhy for causal inference in graphical causal modelscited by 40
  21. 2021Counterfactual State Explanations for Reinforcement Learning Agents via Generative Deep Learningcited by 38
  22. 2021DISSECT: Disentangled Simultaneous Explanations via Concept Traversalscited by 37
  23. 2021Consistent Counterfactuals for Deep Modelscited by 37
  24. 2021Optimal Counterfactual Explanations in Tree Ensemblescited by 36
  25. 2021Counterfactual Explanations in Sequential Decision Making Under Uncertaintycited by 36
  26. 2023Explaining Predictive Uncertainty with Information Theoretic Shapley Valuescited by 36
  27. 2022Cycle-Consistent Counterfactuals by Latent Transformationscited by 33
  28. 2023ProtoSeg: Interpretable Semantic Segmentation with Prototypical Partscited by 33
  29. 2021GeCo: Quality Counterfactual Explanations in Real Timecited by 32
  30. 2022On the Robustness of Sparse Counterfactual Explanations to Adverse Perturbationscited by 32
  31. 2022On the Privacy Risks of Algorithmic Recoursecited by 32
  32. 2022DualCF: Efficient Model Extraction Attack from Counterfactual Explanationscited by 31
  33. 2021Interpretable Data-Based Explanations for Fairness Debuggingcited by 30
  34. 2022Making Heads or Tails: Towards Semantically Consistent Visual Counterfactualscited by 30
  35. 2022Sparse Visual Counterfactual Explanations in Image Spacecited by 30
  36. 2023A Survey on Vertical Federated Learning: From a Layered Perspectivecited by 30
  37. 2021Conditional Generative Models for Counterfactual Explanationscited by 28
  38. 2024Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable?cited by 28

50 most cited of 612 All 612 (JSON)