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

TL;DR

EiX-GNN is a novel explanation method for graph neural networks that incorporates explainee background, improving interpretability, fairness, and compactness in explanations for critical applications.

Contribution

The paper introduces EiX-GNN, which encodes explainee background and adapts explanations accordingly, advancing interpretability in GNNs.

Findings

Achieves strong fairness and compactness results.

Outperforms state-of-the-art explanation methods.

Effectively incorporates explainee background into explanations.

Abstract

Nowadays, deep prediction models, especially graph neural networks, have a majorplace in critical applications. In such context, those models need to be highlyinterpretable or being explainable by humans, and at the societal scope, this understandingmay also be feasible for humans that do not have a strong prior knowledgein models and contexts that need to be explained. In the literature, explainingis a human knowledge transfer process regarding a phenomenon between an explainerand an explainee. We propose EiX-GNN (Eigencentrality eXplainer forGraph Neural Networks) a new powerful method for explaining graph neural networksthat encodes computationally this social explainer-to-explainee dependenceunderlying in the explanation process. To handle this dependency, we introducethe notion of explainee concept assimibility which allows explainer to adapt itsexplanation to explainee background or expectation. We lead a qualitative studyto illustrate our explainee concept assimibility notion on real-world data as wellas a qualitative study that compares, according to objective metrics established inthe literature, fairness and compactness of our method with respect to performingstate-of-the-art methods. It turns out that our method achieves strong results inboth aspects.