AI RESEARCH
Always Keep Your Promises: A Model-Agnostic Attribution Algorithm for Neural Networks
arXiv CS.LG
•
ArXi:2512.07010v4 Announce Type: replace Layer-wise Relevance Propagation (LRP) provides principled attribution for neural networks through conservation properties and foundations in Deep Taylor Decomposition. However, existing implementations operate at the module level, requiring architecture-specific propagation rules and model modifications. These limit the generality of target model and sustainability of implementations as architectures evolve. We