AI RESEARCH
Beyond Additivity: Sparse Isotonic Shapley Regression toward Nonlinear Explainability
arXiv CS.LG
•
ArXi:2512.03112v2 Announce Type: replace Shapley values, a gold standard for feature attribution in Explainable AI, face two key challenges. First, the canonical Shapley framework assumes that the worth function is additive, yet real-world payoff constructions--driven by non-Gaussian distributions, heavy tails, feature dependence, or domain-specific loss scales--often violate this assumption, leading to distorted attributions.