arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2309.03041cs.AI
收藏

对Shapley值用于可解释性的反驳

A Refutation of Shapley Values for Explainability

University of Toulouse(图卢兹大学);IRIT(信息科学与技术研究院);CNRS(法国国家科学研究中心)

Xuanxiang Huang, Joao Marques-Silva

AI总结:

本文通过理论证明,对于任意数量的特征,均存在表现出揭示不足问题的布尔函数,从而反驳了Shapley值作为可解释性中特征归因方法理论基础的有效性。

摘要:

近期的研究表明,存在一些布尔函数,对于这些函数,Shapley值在基于规则的解释中提供了关于特征相对重要性的误导性信息。这种误导性信息被广泛归类为若干可能的问题。这些问题中的每一个都与特征对预测是否相关有关,并且对于Shapley值在基于规则的可解释性中的不足都具有重要意义。早期的工作设计了一种暴力方法来识别定义在少量特征上的布尔函数,以及相关的实例,这些实例展示了这种揭示不足的问题,从而作为Shapley值在基于规则可解释性中不足的证据。然而,一个悬而未决的问题是,对于具有任意大量特征的布尔函数,这种揭示不足的问题发生的频率有多高。很明显,暴力方法不太可能为解决这一问题提供见解。本文通过证明对于任意数量的特征,都存在表现出一个或多个揭示不足问题的布尔函数来回答上述问题,从而为反对将Shapley值作为可解释性中特征归因方法的理论基础提供了决定性的论据。

英文摘要:

Recent work demonstrated the existence of Boolean functions for which Shapley values provide misleading information about the relative importance of features in rule-based explanations. Such misleading information was broadly categorized into a number of possible issues. Each of those issues relates with features being relevant or irrelevant for a prediction, and all are significant regarding the inadequacy of Shapley values for rule-based explainability. This earlier work devised a brute-force approach to identify Boolean functions, defined on small numbers of features, and also associated instances, which displayed such inadequacy-revealing issues, and so served as evidence to the inadequacy of Shapley values for rule-based explainability. However, an outstanding question is how frequently such inadequacy-revealing issues can occur for Boolean functions with arbitrary large numbers of features. It is plain that a brute-force approach would be unlikely to provide insights on how to tackle this question. This paper answers the above question by proving that, for any number of features, there exist Boolean functions that exhibit one or more inadequacy-revealing issues, thereby contributing decisive arguments against the use of Shapley values as the theoretical underpinning of feature-attribution methods in explainability.

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。

↑