arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2412.17152cs.LGstat.ML
收藏

基于功能ANOVA和合作博弈论统一特征解释方法

Unifying Feature-Based Explanations with Functional ANOVA and Cooperative Game Theory

Bielefeld University(比勒费尔德大学);LMU Munich(慕尼黑大学);Leibniz Institute for Agricultural Engineering and Bioeconomy(莱布尼茨农业工程与生物经济研究所)

Fabian Fumagalli, Maximilian Muschalik, Eyke Hüllermeier, Barbara Hammer, Julia Herbinger

AI总结:

针对特征解释方法差异不明的问题,本研究结合功能ANOVA和合作博弈论提出统一框架,通过三种fANOVA分解及博弈论度量揭示解释技术异同,在合成与真实数据集验证了有效性。

摘要:

基于扰动或梯度的特征解释是理解黑箱机器学习模型决策的常用工具,但这些方法之间的差异大多仍不明确,限制了其对从业者的适用性。本研究引入一个统一框架,结合统计学中的功能ANOVA(fANOVA)和合作博弈论中的价值与交互概念,用于局部和全局特征解释。我们提出三种fANOVA分解以确定特征分布的影响,并使用Shapley值和交互等博弈论度量来明确高阶交互的影响。该框架结合这两个维度,揭示了多种特征及特征组解释技术之间的异同,并在合成和真实世界数据集上实证展示了其有效性。

英文摘要:

Feature-based explanations, using perturbations or gradients, are a prevalent tool to understand decisions of black box machine learning models. Yet, differences between these methods still remain mostly unknown, which limits their applicability for practitioners. In this work, we introduce a unified framework for local and global feature-based explanations using two well-established concepts: functional ANOVA (fANOVA) from statistics, and the notion of value and interaction from cooperative game theory. We introduce three fANOVA decompositions that determine the influence of feature distributions, and use game-theoretic measures, such as the Shapley value and interactions, to specify the influence of higher-order interactions. Our framework combines these two dimensions to uncover similarities and differences between a wide range of explanation techniques for features and groups of features. We then empirically showcase the usefulness of our framework on synthetic and real-world datasets.

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。

↑