论文标题
机器学习中的沙普利价值
The Shapley Value in Machine Learning
论文作者
论文摘要
在过去的几年中，合作游戏理论的解决方案概念的沙普利价值在机器学习中发现了许多应用。在本文中，我们首先讨论了莎普利价值的合作游戏理论和公理特性的基本概念。然后，我们概述了机器学习中沙普利价值的最重要应用：功能选择，解释性，多代理增强学习，整体修剪和数据估值。我们研究了沙普利价值的最关键局限性，并指出了未来研究的方向。
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.
