Explaining Probabilistic Models with Distributional Values

arXiv:2402.09947v1 Announce Type: new
Abstract: A large branch of explainable machine learning is grounded in cooperative game theory. However, research indicates that game-theoretic explanations may mislead or be hard to interpret. We argue that often there is a critical mismatch between what one wishes to explain (e.g. the output of a classifier) and what current methods such as SHAP explain (e.g. the scalar probability of a class). This paper addresses such gap for probabilistic models by generalising cooperative games and …

abstract arxiv classifier cs.lg explainable machine learning game game theory machine machine learning research theory type values