AI RESEARCH
Beyond Additive Decompositions: Interpretability Through Separability
arXiv CS.LG
•
ArXi:2605.31200v1 Announce Type: new Interpretable machine learning requires models that are accurate and structurally faithful to the data. Existing explainability methods rely heavily on additive representations (e.g., Generalized Additive Models (GAMs), SHapley Additive exPlanations (SHAP), functional ANOVA), which can suffer from signal cancellation and off- extrapolation in the presence of strong interactions.