mlsanityData to 7 Oct 2026

Rational Shapley Values

arXiv 2106.10191 ↗First posted 18 Jun 2021cs.LG cs.AIcited by 18

Not on the map. Why?

Abstract (arXiv)

Explaining the predictions of opaque machine learning algorithms is an important and challenging task, especially as complex models are increasingly used to assist in high-stakes decisions such as those arising in healthcare and finance. Most popular tools for post-hoc explainable artificial intelligence (XAI) are either insensitive to context (e.g., feature attributions) or difficult to summarize (e.g., counterfactuals). In this paper, I introduce textitrational Shapley values, a novel XAI method that synthesizes and extends these seemingly incompatible approaches in a rigorous, flexible manner. I leverage tools from decision theory and causal modeling to formalize and implement a pragmatic approach that resolves a number of known challenges in XAI. By pairing the distribution of random variables with the appropriate reference class for a given explanation task, I illustrate through theory and experiments how user goals and knowledge can inform and constrain the solution set in an iterative fashion. The method compares favorably to state of the art XAI tools in a range of quantitative and qualitative comparisons.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 24 of its 51 references that are in the map. First posted on arXiv 18 Jun 2021.

Builds on

24 of 51 references.

References · 24

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  2. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
  3. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  4. 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
  5. 2019Explaining Machine Learning Classifiers through Diverse Counterfactual Explanationscited by 612
  6. 2018All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneouslycited by 364
  7. 2019The many Shapley values for model explanationcited by 341
  8. 2018Actionable Recourse in Linear Classificationcited by 327
  9. 2019Interpretable machine learning: definitions, methods, and applicationscited by 303
  10. 2020Algorithmic Recourse: from Counterfactual Explanations to Interventionscited by 250
  11. 2019FACE: Feasible and Actionable Counterfactual Explanationscited by 232
  12. 2019The What-If Tool: Interactive Probing of Machine Learning Modelscited by 207
12 more
  1. 2019Explaining individual predictions when features are dependent: More accurate approximations to Shapley valuescited by 205
  2. 2020Problems with Shapley-value-based explanations as feature importance measurescited by 198
  3. 2019Feature relevance quantification in explainable AI: A causal problemcited by 164
  4. 2019Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifierscited by 143
  5. 2020Reliable Post hoc Explanations: Modeling Uncertainty in Explainabilitycited by 125
  6. 2020A survey of algorithmic recourse: definitions, formulations, solutions, and prospectscited by 118
  7. 2019Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainabilitycited by 114
  8. 2019Efficient Search for Diverse Coherent Explanationscited by 111
  9. 2020Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Modelscited by 107
  10. 2018The age of secrecy and unfairness in recidivism predictioncited by 53
  11. 2021Local Explanations via Necessity and Sufficiency: Unifying Theory and Practicecited by 45
  12. 2014Statistical Causality from a Decision-Theoretic Perspectivecited by 7

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 0; 2023: 8; 2024: 2; 2025: 7.

18 papers.

Sort:

  1. 2023The Inadequacy of Shapley Values for Explainabilitycited by 30
  2. 2023Explainability is NOT a Gamecited by 23
  3. 2021Counterfactual Shapley Additive Explanationscited by 22
  4. 2023The role of causality in explainable artificial intelligencecited by 17
  5. 2023Disproving XAI Myths with Formal Methods -- Initial Resultscited by 12
  6. 2023Bayesian Hierarchical Models for Counterfactual Estimationcited by 6
  7. 2024Explainability of Machine Learning Models under Missing Datacited by 5
  8. 2023A Refutation of Shapley Values for Explainabilitycited by 4
  9. 2025SHAP-based Explanations are Sensitive to Feature Representationcited by 4
  10. 2025Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAPcited by 3
  11. 2023Causal Dependence Plotscited by 2
  12. 2025Attribution Explanations for Deep Neural Networks: A Theoretical Perspectivecited by 2
6 more
  1. 2024Error Analysis of Shapley Value-Based Model Explanations: An Informative Perspectivecited by 1
  2. 2025Detect & Score: Privacy-Preserving Misbehaviour Detection and Contribution Evaluation in Federated Learningcited by 1
  3. 2023Explainable Machine Learning for Categorical and Mixed Data with Lossless Visualizationcited by 0
  4. 2025Suboptimal Shapley Value Explanationscited by 0
  5. 2025TaylorPODA: A Taylor Expansion-Based Method to Improve Post-Hoc Attributions for Opaque Modelscited by 0
  6. 2025Rigorous Feature Importance Scores based on Shapley Value and Banzhaf Indexcited by 0