SHAP-XRT: The Shapley Value Meets Conditional Independence Testing

Published: 13 Dec 2023, Last Modified: 13 Dec 2023Accepted by TMLREveryoneRevisionsBibTeX
Authors that are also TMLR Expert Reviewers: ~Jeremias_Sulam1
Abstract: The complex nature of artificial neural networks raises concerns on their reliability, trustworthiness, and fairness in real-world scenarios. The Shapley value---a solution concept from game theory---is one of the most popular explanation methods for machine learning models. More traditionally, from a statistical perspective, feature importance is defined in terms of conditional independence. So far, these two approaches to interpretability and feature importance have been considered separate and distinct. In this work, we show that Shapley-based explanation methods and conditional independence testing are closely related. We introduce the \textbf{SHAP}ley E\textbf{X}planation \textbf{R}andomization \textbf{T}est (SHAP-XRT), a testing procedure inspired by the Conditional Randomization Test (CRT) for a specific notion of local (i.e., on a sample) conditional independence. With it, we prove that for binary classification problems, the marginal contributions in the Shapley value provide lower and upper bounds to the expected $p$-values of their respective tests. Furthermore, we show that the Shapley value itself provides an upper bound to the expected $p$-value of a global (i.e., overall) null hypothesis. As a result, we further our understanding of Shapley-based explanation methods from a novel perspective and characterize the conditions under which one can make statistically valid claims about feature importance via the Shapley value.
Certifications: Expert Certification
License: Creative Commons Attribution 4.0 International (CC BY 4.0)
Submission Length: Regular submission (no more than 12 pages of main content)
Previous TMLR Submission Url:
Changes Since Last Submission: Camera ready version
Assigned Action Editor: ~Mingming_Gong1
Submission Number: 1324