XpertAI: uncovering model strategies for sub-manifolds

arXiv:2403.07486v1 Announce Type: new
Abstract: In recent years, Explainable AI (XAI) methods have facilitated profound validation and knowledge extraction from ML models. While extensively studied for classification, few XAI solutions have addressed the challenges specific to regression models. In regression, explanations need to be precisely formulated to address specific user queries (e.g.\ distinguishing between `Why is the output above 0?' and `Why is the output above 50?'). They should furthermore reflect the model's behavior on the relevant data sub-manifold. In …

abstract arxiv challenges classification cs.lg explainable ai extraction knowledge ml models queries regression solutions strategies type validation xai