Sanity Checks for Explanation Uncertainty

arXiv:2403.17212v1 Announce Type: new
Abstract: Explanations for machine learning models can be hard to interpret or be wrong. Combining an explanation method with an uncertainty estimation method produces explanation uncertainty. Evaluating explanation uncertainty is difficult. In this paper we propose sanity checks for uncertainty explanation methods, where a weight and data randomization tests are defined for explanations with uncertainty, allowing for quick tests to combinations of uncertainty and explanation methods. We experimentally show the validity and effectiveness of these tests …

abstract arxiv checks cs.ai cs.lg data machine machine learning machine learning models paper randomization tests type uncertainty