EiX-GNN : Concept-level eigencentrality explainer for graph neural networks

Adrien Raison (1, 2) , Pascal Bourdon (2, 1) , David Helbert (2, 1)

1 Université de Poitiers - Faculté de Sciences fondamentales et appliquées
2 XLIM-ASALI - Synthèse et analyse d'images

Explaining is a human knowledge transfer process regarding a phenomenon between an explainer and an explainee. Each word used to explain this phenomenon must be carefully selected by the explainer in accordance with the current explainee phenomenon-related knowledge level and the phenomenon itself in order to have a high understanding from the explainee of the phenomenon. Nowadays, deep models, especially graph neural networks, have a major place in daily life even in critical applications. In such context, those models need to have a human high interpretability also referred as being explainable, in order to improve usage trustability of them in sensitive cases. Explaining is also a human dependent task and methods that explain deep model behavior must include these social-related concerns for providing profitable and quality explanations. Current explaining methods often occlude such social aspect for providing their explanations and only focus on the signal aspect of the question. In this contribution we propose a reliable social-aware explaining method suited for graph neural network that includes this social feature as a modular concept generator and by both leveraging signal and graph domain aspect thanks to an eigencentrality concept ordering approach. Besides our method takes into account the human-dependent aspect underlying any explanation process, we also reach high score regarding state-of-the-art objective metrics assessing explanation methods for graph neural networks models.

Domaines: Intelligence artificielle [cs.AI]; Vision par ordinateur et reconnaissance de formes [cs.CV]

Adrien Raison, Pascal Bourdon, David Helbert. EiX-GNN : Concept-level eigencentrality explainer for graph neural networks. 2022. ⟨hal-03686299v2⟩