XAudit : A Learning-Theoretic Look at Auditing with Explanations

Abstract

Responsible use of machine learning requires models to be audited for undesirable properties. While a body of work has proposed using explanations for auditing, how to do so and why has remained relatively ill-understood. This work formalizes the role of explanations in auditing using inspirations from active learning and investigates if and how model explanations can help audits. As an instantiation of our framework, we look at `feature sensitivity' and propose explanation-based algorithms for auditing linear classifiers and decision trees for this property. Our results illustrate that Counterfactual explanations are extremely helpful for auditing feature sensitivity, even in the worst-case. While Anchor explanations and decision paths may not be as beneficial in the worst-case, in the average-case they do aid significantly as demonstrated by our experiments.