The Shapley Value in Machine Learning
Machine Learning
2022-05-27 v2 Artificial Intelligence
Computer Science and Game Theory
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.
Keywords
Cite
@article{arxiv.2202.05594,
title = {The Shapley Value in Machine Learning},
author = {Benedek Rozemberczki and Lauren Watson and Péter Bayer and Hao-Tsung Yang and Olivér Kiss and Sebastian Nilsson and Rik Sarkar},
journal= {arXiv preprint arXiv:2202.05594},
year = {2022}
}
Comments
https://github.com/AstraZeneca/awesome-shapley-value