Threading the Needle of On and Off-Manifold Value Functions for Shapley Explanations

TL;DR

This paper introduces the Joint Baseline value function for Shapley explanations, which respects data and model properties, is robust to adversarial perturbations, and addresses limitations of existing on- and off-manifold approaches.

Contribution

It formalizes axioms for desirable value functions, proves the uniqueness of the Joint Baseline value function, and demonstrates its effectiveness in experiments.

Findings

Joint Baseline value function satisfies key axioms.

JBshap is robust to adversarial manipulations.

Experimental validation shows improved explanation quality.

Abstract

A popular explainable AI (XAI) approach to quantify feature importance of a given model is via Shapley values. These Shapley values arose in cooperative games, and hence a critical ingredient to compute these in an XAI context is a so-called value function, that computes the "value" of a subset of features, and which connects machine learning models to cooperative games. There are many possible choices for such value functions, which broadly fall into two categories: on-manifold and off-manifold value functions, which take an observational and an interventional viewpoint respectively. Both these classes however have their respective flaws, where on-manifold value functions violate key axiomatic properties and are computationally expensive, while off-manifold value functions pay less heed to the data manifold and evaluate the model on regions for which it wasn't trained. Thus, there is no consensus on which class of value functions to use. In this paper, we show that in addition to these existing issues, both classes of value functions are prone to adversarial manipulations on low density regions. We formalize the desiderata of value functions that respect both the model and the data manifold in a set of axioms and are robust to perturbation on off-manifold regions, and show that there exists a unique value function that satisfies these axioms, which we term the Joint Baseline value function, and the resulting Shapley value the Joint Baseline Shapley (JBshap), and validate the effectiveness of JBshap in experiments.