EiX-GNN : Concept-level eigencentrality explainer for graph neural networks
This addresses the need for interpretable AI in critical applications, but it is incremental as it builds on existing explanation methods with a focus on user adaptation.
The authors tackled the problem of making graph neural networks interpretable by proposing EiX-GNN, a method that adapts explanations to the user's background, and it achieved strong results in fairness and compactness compared to state-of-the-art methods.
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.