The Shapley Value in Machine Learning
By Benedek Rozemberczki, Lauren Watson, Péter Bayer, Hao-Tsung Yang, Oliver Kiss, Sebastian Nilsson, Rik Sarkar. International Joint Conference on Artificial Intelligence, 2022
361 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence
View Paper: https://www.semanticscholar.org/paper/09c72d9d46f6750e487afdb5f7cae7693ffccc10
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Su-In Lee
- Scott M. Lundberg
- Ian Covert
- Hugh Chen
- Przemyslaw Biecek
- Adrian Weller
- David Watson
- Ankur Taly
Citations in the corpus
- Algorithms to estimate Shapley value feature attributions (2022, methodology): “Although these methods are largely outside the scope of this paper, a variety of applications of the Shapley value in machine learning are discussed in Rozemberczki et al. [83].”