Year: 2022
Type: preprint
Abstract: 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.
Source: arXiv (Cornell University)
Institutions: Université de Poitiers, XLIM
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4282813372