Analyzing Explainer Robustness via Probabilistic Lipschitzness of Prediction Functions

arXiv:2206.12481v3 Announce Type: replace
Abstract: Machine learning methods have significantly improved in their predictive capabilities, but at the same time they are becoming more complex and less transparent. As a result, explainers are often relied on to provide interpretability to these black-box prediction models. As crucial diagnostics tools, it is important that these explainers themselves are robust. In this paper we focus on one particular aspect of robustness, namely that an explainer should give similar explanations for similar data inputs. …

abstract arxiv box capabilities cs.lg diagnostics explainer functions interpretability machine machine learning prediction prediction models predictive robustness tools transparent type via