Preprint
Aug 2026
RelShap: Relationally Consistent Shapley Explanations
Experiments show that RelShap produces explanations that are more faithful to the data-generating process, correctly identifying the dominant feature in controlled settings where existing methods, including Conditional SHAP and ManifoldShap, do not.
Seungeun Lee, João Fonseca, Julia Stoyanovich
· 0 citations