用统计与博弈论统一解释模型特征影响，看清不同方法差异。
Unifying Feature-Based Explanations with Functional ANOVA and Cooperative Game Theory
- 结合函数方差分析与合作博弈论，统一局部全局解释方法。
- 提出三种分解方式，量化特征分布与高阶交互的影响。
- 在真实与合成数据上验证框架有效性，适合模型可解释性研究者。
基于特征的解释方法（如扰动或梯度法）是理解黑箱机器学习模型决策的常用工具。然而，这些方法间的差异仍不明确，限制了其在实践中的应用。本文引入一个统一框架，利用统计学中的函数方差分析（fANOVA）与合作博弈论中的价值与交互概念，实现局部和全局特征解释的统一。提出三种fANOVA分解，用于确定特征分布的影响，并采用博弈论指标（如Shapley值、交互作用）刻画高阶交互作用的影响。该框架结合两个维度，揭示多种特征及特征组解释技术之间的异同。我们在合成数据与真实世界数据集上实证展示了该框架的实用性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。