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.
翻译:过去几年来, " Shapley " 价值(合作游戏理论的一个解决方案概念)在机器学习中发现了许多应用。在本文中,我们首先讨论合作游戏理论的基本概念和 " Shapley " 价值的不言自明特性。然后我们概述了 " Shapley " 价值在机器学习中最重要的应用:特征选择、可解释性、多试剂强化学习、混合编目和数据评估。我们审视了 " Shapley " 价值的最关键的局限性,并指明了未来研究的方向。