The Shapley Value in Machine Learning

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.

Cite

Text

Rozemberczki et al. "The Shapley Value in Machine Learning." International Joint Conference on Artificial Intelligence, 2022. doi:10.24963/IJCAI.2022/778

Markdown

[Rozemberczki et al. "The Shapley Value in Machine Learning." International Joint Conference on Artificial Intelligence, 2022.](https://mlanthology.org/ijcai/2022/rozemberczki2022ijcai-shapley/) doi:10.24963/IJCAI.2022/778

BibTeX

@inproceedings{rozemberczki2022ijcai-shapley,
  title     = {{The Shapley Value in Machine Learning}},
  author    = {Rozemberczki, Benedek and Watson, Lauren and Bayer, Péter and Yang, Hao-Tsung and Kiss, Oliver and Nilsson, Sebastian and Sarkar, Rik},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2022},
  pages     = {5572-5579},
  doi       = {10.24963/IJCAI.2022/778},
  url       = {https://mlanthology.org/ijcai/2022/rozemberczki2022ijcai-shapley/}
}