arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.09042cs.LG
收藏

推理的形状:机器学习中基于规则的推理的拓扑描述

The Shape of Explanations: A Topological Account of Rule-Based Explanations in Machine Learning

University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校)

Brett Mullins

摘要:

基于规则的解释提供了解释机器学习分类器在特征空间中的给定点处的行为的简单原因。最近的几种方法(几何方法、LORE等)旨在为任意或黑盒分类器生成基于规则的解释。但是,是什么让这些方法在一般情况下起作用呢?我们引入了一个拓扑框架,基于规则的解释方法,并提供了一个表征的可解释性的定义的分类相对于一个解释方案。我们采用这个框架来考虑各种解释方案,并认为首选方案取决于用户对域的了解程度和特征空间上的概率测度。

英文摘要:

Rule-based explanations provide simple reasons explaining the behavior of machine learning classifiers at given points in the feature space. Several recent methods (Anchors, LORE, etc.) purport to generate rule-based explanations for arbitrary or black-box classifiers. But what makes these methods work in general? We introduce a topological framework for rule-based explanation methods and provide a characterization of explainability in terms of the definability of a classifier relative to an explanation scheme. We employ this framework to consider various explanation schemes and argue that the preferred scheme depends on how much the user knows about the domain and the probability measure over the feature space.

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。

↑