The Shapley Value in Machine Learning

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.
Original languageEnglish
Title of host publicationProceedings of the 31st International Joint Conference on Artifical Intelligence, IJCAI-ECAI 2022
EditorsLuc De Raedt
PublisherInternational Joint Conferences on Artificial Intelligence Organization
Pages5572-5579
Number of pages8
ISBN (Print)978-1-956792-00-3
DOIs
Publication statusPublished - 23 Jul 2022
EventThe 31st International Joint Conference on Artificial Intelligence and the 25th European Conference on Artificial Intelligence - Vienna, Austria
Duration: 23 Jul 202229 Jul 2022
https://ijcai-22.org/

Conference

ConferenceThe 31st International Joint Conference on Artificial Intelligence and the 25th European Conference on Artificial Intelligence
Abbreviated titleIJCAI-ECAI 2022
Country/TerritoryAustria
CityVienna
Period23/07/2229/07/22
Internet address

Fingerprint

Dive into the research topics of 'The Shapley Value in Machine Learning'. Together they form a unique fingerprint.

Cite this