On the tractability of SHAP explanations under Markovian distributions

arXiv:2405.02936v1 Announce Type: new
Abstract: Thanks to its solid theoretical foundation, the SHAP framework is arguably one the most widely utilized frameworks for local explainability of ML models. Despite its popularity, its exact computation is known to be very challenging, proven to be NP-Hard in various configurations. Recent works have unveiled positive complexity results regarding the computation of the SHAP score for specific model families, encompassing decision trees, random forests, and some classes of boolean circuits. Yet, all these positive …

abstract arxiv computation cs.ai cs.lg explainability foundation framework frameworks ml models np-hard shap solid type