Provably Robust and Plausible Counterfactual Explanations for Neural Networks via Robust Optimisation

arXiv:2309.12545v2 Announce Type: replace
Abstract: Counterfactual Explanations (CEs) have received increasing interest as a major methodology for explaining neural network classifiers. Usually, CEs for an input-output pair are defined as data points with minimum distance to the input that are classified with a different label than the output. To tackle the established problem that CEs are easily invalidated when model parameters are updated (e.g. retrained), studies have proposed ways to certify the robustness of CEs under model parameter changes bounded …

abstract arxiv ces classifiers counterfactual cs.ai cs.lg data input-output major methodology network networks neural network neural networks optimisation robust type via