The Shapley Value in Machine Learning

Benedek Rozemberczki, Lauren Watson, Péter Bayer, Hao-Tsung Yang, Olivér Kiss, Sebastian Nilsson, Rik Sarkar

Producció científica: Contribució a revistaArticle de revisióRecercaAvaluat per experts

97 Cites (Scopus)

Resum

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.
Idioma originalAnglès
Pàgines (de-a)5572-5579
RevistaProceedings of the Thirty-First International Joint Conference on Artificial Intelligence
DOIs
Estat de la publicacióPublicada - de jul. 2022

Fingerprint

Navegar pels temes de recerca de 'The Shapley Value in Machine Learning'. Junts formen un fingerprint únic.

Com citar-ho