mlsanityData to 7 Oct 2026

Counterfactual Shapley Additive Explanations

arXiv 2110.14270 ↗First posted 27 Oct 2021cs.LG cs.AIcited by 22

Not on the map. Why?

Abstract (arXiv)

Feature attributions are a common paradigm for model explanations due to their simplicity in assigning a single numeric score for each input feature to a model. In the actionable recourse setting, wherein the goal of the explanations is to improve outcomes for model consumers, it is often unclear how feature attributions should be correctly used. With this work, we aim to strengthen and clarify the link between actionable recourse and feature attributions. Concretely, we propose a variant of SHAP, Counterfactual SHAP (CF-SHAP), that incorporates counterfactual information to produce a background dataset for use within the marginal (a.k.a. interventional) Shapley value framework. We motivate the need within the actionable recourse setting for careful consideration of background datasets when using Shapley values for feature attributions with numerous synthetic examples. Moreover, we demonstrate the efficacy of CF-SHAP by proposing and justifying a quantitative score for feature attributions, counterfactual-ability, showing that as measured by this metric, CF-SHAP is superior to existing methods when evaluated on public datasets using tree ensembles.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 44 of its 82 references that are in the map. First posted on arXiv 27 Oct 2021.

Builds on

44 of 82 references.

References · 44

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  2. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  4. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,543
  5. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
  6. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  7. 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
  8. 2019Explaining Machine Learning Classifiers through Diverse Counterfactual Explanationscited by 612
  9. 2021Tabular Data: Deep Learning is Not All You Needcited by 530
  10. 2019The many Shapley values for model explanationcited by 341
  11. 2018Actionable Recourse in Linear Classificationcited by 327
  12. 2020Algorithmic Recourse: from Counterfactual Explanations to Interventionscited by 250
32 more
  1. 2019FACE: Feasible and Actionable Counterfactual Explanationscited by 232
  2. 2019Explaining individual predictions when features are dependent: More accurate approximations to Shapley valuescited by 205
  3. 2019Model-Agnostic Counterfactual Explanations for Consequential Decisionscited by 204
  4. 2020Problems with Shapley-value-based explanations as feature importance measurescited by 198
  5. 2018Local Rule-Based Explanations of Black Box Decision Systemscited by 165
  6. 2019Feature relevance quantification in explainable AI: A causal problemcited by 164
  7. 2020Multi-Objective Counterfactual Explanationscited by 157
  8. 2019Learning Model-Agnostic Counterfactual Explanations for Tabular Datacited by 146
  9. 2020Algorithmic recourse under imperfect causal knowledge: a probabilistic approachcited by 139
  10. 2020True to the Model or True to the Data?cited by 123
  11. 2019The Hidden Assumptions Behind Counterfactual Explanations and Principal Reasonscited by 115
  12. 2019Efficient Search for Diverse Coherent Explanationscited by 111
  13. 2019The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanationscited by 97
  14. 2020Shapley explainability on the data manifoldcited by 88
  15. 2021CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithmscited by 85
  16. 2018Model Agnostic Supervised Local Explanationscited by 83
  17. 2021If Only We Had Better Counterfactual Explanations: Five Key Deficits to Rectify in the Evaluation of Counterfactual XAI Techniquescited by 82
  18. 2020On the Fairness of Causal Algorithmic Recoursecited by 69
  19. 2020Towards Unifying Feature Attribution and Counterfactual Explanations: Different Means to the Same Endcited by 66
  20. 2021Argumentative XAI: A Surveycited by 66
  21. 2020Shapley Flow: A Graph-based Approach to Interpreting Model Predictionscited by 51
  22. 2019Measurable Counterfactual Local Explanations for Any Classifiercited by 48
  23. 2019Counterfactual Explanation Algorithms for Behavioral and Textual Datacited by 26
  24. 2020BRPO: Batch Residual Policy Optimizationcited by 25
  25. 2019Generating Counterfactual and Contrastive Explanations using SHAPcited by 23
  26. 2021Counterfactual Explanations for Arbitrary Regression Modelscited by 22
  27. 2021A Few Good Counterfactuals: Generating Interpretable, Plausible and Diverse Counterfactual Explanationscited by 19
  28. 2021Rational Shapley Valuescited by 18
  29. 2020PermuteAttack: Counterfactual Explanation of Machine Learning Credit Scorecardscited by 16
  30. 2021Text Counterfactuals via Latent Optimization and Shapley-Guided Searchcited by 16
  31. 2019Generalized Integrated Gradients: A practical method for explaining diverse ensemblescited by 7
  32. 2020Influence-Driven Explanations for Bayesian Network Classifierscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 10; 2024: 4; 2025: 1; 2026: 2.

22 papers.

Sort:

  1. 2022From Shapley Values to Generalized Additive Models and backcited by 59
  2. 2022Robust Counterfactual Explanations for Tree-Based Ensemblescited by 49
  3. 2023Robust Counterfactual Explanations for Neural Networks With Probabilistic Guaranteescited by 45
  4. 2023The Inadequacy of Shapley Values for Explainabilitycited by 30
  5. 2022On the Trade-Off between Actionable Explanations and the Right to be Forgottencited by 20
  6. 2022Deletion and Insertion Tests in Regression Modelscited by 14
  7. 2023Efficient XAI Techniques: A Taxonomic Surveycited by 14
  8. 2022BASED-XAI: Breaking Ablation Studies Down for Explainable Artificial Intelligencecited by 12
  9. 2023Towards Algorithmic Fairness by means of Instance-level Data Re-weighting based on Shapley Valuescited by 7
  10. 2023Bayesian Hierarchical Models for Counterfactual Estimationcited by 6
  11. 2023The Disagreement Problem in Faithfulness Metricscited by 6
  12. 2023A Refutation of Shapley Values for Explainabilitycited by 4
10 more
  1. 2023Causal Dependence Plotscited by 2
  2. 2024Generally-Occurring Model Change for Robust Counterfactual Explanationscited by 2
  3. 2023T-COL: Generating Counterfactual Explanations for General User Preferences on Variable Machine Learning Systemscited by 1
  4. 2024Manifold-based Shapley for SAR Recognization Network Explanationcited by 1
  5. 2024Explaining Reinforcement Learning: A Counterfactual Shapley Values Approachcited by 1
  6. 2023On the Connection between Game-Theoretic Feature Attributions and Counterfactual Explanationscited by 0
  7. 2024XpertAI: uncovering regression model strategies for sub-manifoldscited by 0
  8. 2025Rigorous Feature Importance Scores based on Shapley Value and Banzhaf Indexcited by 0
  9. 2026A Data-Driven Approach to Support Clinical Renal Replacement Therapycited by 0
  10. 2026Feature Attribution in Directed Acyclic Graphs Using Edge Interventioncited by 0