Unifying Feature-Based Explanations with Functional ANOVA and Cooperative Game Theory
This work addresses the challenge for practitioners in interpreting black-box models by providing a theoretical unification of explanation methods, though it appears incremental as it builds on existing concepts.
The paper tackled the problem of understanding differences between feature-based explanation methods for black-box ML models by introducing a unified framework using functional ANOVA and cooperative game theory, and empirically demonstrated its usefulness on synthetic and real-world datasets.
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.