Boundary-Aware Uncertainty for Feature Attribution Explainers

arXiv:2210.02419v5 Announce Type: replace
Abstract: Post-hoc explanation methods have become a critical tool for understanding black-box classifiers in high-stakes applications. However, high-performing classifiers are often highly nonlinear and can exhibit complex behavior around the decision boundary, leading to brittle or misleading local explanations. Therefore there is an impending need to quantify the uncertainty of such explanation methods in order to understand when explanations are trustworthy. In this work we propose the Gaussian Process Explanation UnCertainty (GPEC) framework, which generates a …

abstract applications arxiv attribution become behavior box classifiers cs.lg decision feature tool type uncertainty understanding