The explainability of deep networks is becoming a central issue in the deep learning community. It is the same for learning on graphs, a data structure present in many real world problems. In this paper, we propose a method that is more optimal, lighter, consistent and better exploits the topology of the evaluated graph than the state-of-the-art methods.
@article{arxiv.2207.12748,
title = {ScoreCAM GNN: une explication optimale des r\'eseaux profonds sur graphes},
author = {Adrien Raison and Pascal Bourdon and David Helbert},
journal= {arXiv preprint arXiv:2207.12748},
year = {2022}
}
Comments
in French language. XXVIIIe Colloque GRETSI - Traitement du Signal et des Images, Sep 2022, Nancy, France