GRALIS: A Unified Canonical Framework for Linear Attribution Methods via Riesz Representation

概要

arXiv:2605.05480v1 Announce Type: cross Abstract: The main XAI attribution methods for deep neural networks -- GradCAM, SHAP, LIME, Integrated Gradients -- operate on separate theoretical foundations and are not formally comparable. We present GRALIS (Gradient-Riesz Averaged Locally-Integrated Shap…