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 provide a taxonomy and define seven types of cooperative machine learning games that can be solved using the Shapley value. We examine the most crucial limitations of the Shapley value and point out directions for future research.
Wednesday, May 25, 2022, 11:30 am – 12:30 pm