The Shapley Value in Machine Learning
Benedek Rózemberczki, Lauren Watson, Péter Bayer, Hao-Tsung Yang, Olivér Kiss, Sebastian Nilsson, Rik Sarkar
2022Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence259 citationsDOIOpen Access PDF
Abstract
Over the last few years, the Shapley value, a solution concept from cooperative game theory, has found numerous applications in machine learning. In this paper, we first discuss fundamental concepts of cooperative game theory and axiomatic properties of the Shapley value. Then we give an overview of the most important applications of the Shapley value in machine learning: feature selection, explainability, multi-agent reinforcement learning, ensemble pruning, and data valuation. We examine the most crucial limitations of the Shapley value and point out directions for future research.
Topics & Concepts
Shapley valueAxiomCooperative game theoryComputer scienceValuation (finance)Artificial intelligenceGame theoryReinforcement learningPruningValue (mathematics)Machine learningMathematical economicsMathematicsEconomicsBiologyAgronomyGeometryFinanceExplainable Artificial Intelligence (XAI)Bayesian Modeling and Causal InferenceImbalanced Data Classification Techniques