Integrated Gradient Correlation: a Dataset-wise Attribution Method

arXiv:2404.13910v1 Announce Type: new
Abstract: Attribution methods are primarily designed to study the distribution of input component contributions to individual model predictions. However, some research applications require a summary of attribution patterns across the entire dataset to facilitate the interpretability of the scrutinized models. In this paper, we present a new method called Integrated Gradient Correlation (IGC) that relates dataset-wise attributions to a model prediction score and enables region-specific analysis by a direct summation over associated components. We demonstrate our …

abstract applications arxiv attribution correlation cs.ai cs.lg dataset distribution gradient however interpretability paper patterns predictions research study summary type wise