arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.10936cs.LGcs.AIstat.ML
收藏

特征选择的Shapley值:好的、坏的和公理

Shapley values for feature selection: The good, the bad, and the axioms

School of Mathematics and Physics, The University of Queensland(昆士兰大学数学与物理学院);SimulaMet, Simula Research Laboratory(SimulaMet、Simula研究院);Department of Mathematics and Statistics, La Trobe University(拉筹伯大学数学与统计学院)

Daniel Fryer, Inga Strümke, Hien Nguyen

摘要:

Shapley值在可解释人工智能(XAI)文献中很受欢迎,这在很大程度上要归功于坚实的理论基础,包括可转移效用游戏中归因的四个“有利和公平”公理。Shapley值可以证明是满足这些公理的唯一解概念。在本文中,我们介绍了Shapley值,并提请注意其最近使用的特征选择工具。我们对Shapley值的这种使用提出了质疑,使用简单、抽象的“玩具”反例来说明公理可能会违背特征选择的目标。从这一点上,我们开发了一些见解,然后在具体的模拟设置中进行研究,各种Shapley值公式,包括SHapley加法解释(SHAP)和Shapley加法全局重要性(SAGE)。

英文摘要:

The Shapley value has become popular in the Explainable AI (XAI) literature, thanks, to a large extent, to a solid theoretical foundation, including four "favourable and fair" axioms for attribution in transferable utility games. The Shapley value is provably the only solution concept satisfying these axioms. In this paper, we introduce the Shapley value and draw attention to its recent uses as a feature selection tool. We call into question this use of the Shapley value, using simple, abstract "toy" counterexamples to illustrate that the axioms may work against the goals of feature selection. From this, we develop a number of insights that are then investigated in concrete simulation settings, with a variety of Shapley value formulations, including SHapley Additive exPlanations (SHAP) and Shapley Additive Global importancE (SAGE).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑