The Shapley Value in Machine Learning
It synthesizes existing knowledge for researchers and practitioners in ML, but is incremental as it reviews and organizes prior work without introducing new methods or results.
This paper provides an overview of the Shapley value from cooperative game theory and its applications in machine learning, including feature selection, explainability, and data valuation, while discussing limitations and future research directions.
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.