From Shapley back to Pearson: Hypothesis Testing via the Shapley Value

Jacopo Teneggi, Beepul Bharti, Yaniv Romano, Jeremias Sulam

Research output: Working paperPreprint

Abstract

Machine learning models, in particular artificial neural networks, are increasingly used to inform decision making in high-stakes scenarios across a variety of fields -- from financial services, to public safety, and healthcare. While neural networks have achieved remarkable performance in many settings, their complex nature raises concerns on their reliability, trustworthiness, and fairness in real-world scenarios. As a result, several a-posteriori explanation methods have been proposed to highlight the features that influence a model's prediction. Notably, the Shapley value -- a game theoretic quantity that satisfies several desirable properties -- has gained popularity in the machine learning explainability literature. More traditionally, however, feature importance in statistical learning has been formalized by conditional independence, and a standard way to test for it is via Conditional Randomization Tests (CRTs). So far, these two perspectives on interpretability and feature importance have been considered distinct and separate. In this work, we show that Shapley-based explanation methods and conditional independence testing for feature importance are closely related. More precisely, we prove that for binary classification problems, evaluating a Shapley coefficient amounts to performing a specific set of conditional independence tests, as implemented by a procedure similar to the CRT but for a different null hypothesis. Furthermore, the obtained game-theoretic values upper bound the $p$-values of such tests. As a result, we grant large Shapley coefficients with a precise statistical sense of importance with controlled type I error.
Original languageAmerican English
StatePublished - 2022

Fingerprint

Dive into the research topics of 'From Shapley back to Pearson: Hypothesis Testing via the Shapley Value'. Together they form a unique fingerprint.

Cite this