Explainability in Graph Neural Networks: An Experimental Survey
This addresses the black-box problem in GNNs for researchers and practitioners, but it is incremental as it builds on existing survey work with new experiments.
The paper tackles the lack of transparency in graph neural networks (GNNs) by providing an experimental survey of explainability methods, proposing a new evaluation metric, and comparing methods on real-world datasets.
Graph neural networks (GNNs) have been extensively developed for graph representation learning in various application domains. However, similar to all other neural networks models, GNNs suffer from the black-box problem as people cannot understand the mechanism underlying them. To solve this problem, several GNN explainability methods have been proposed to explain the decisions made by GNNs. In this survey, we give an overview of the state-of-the-art GNN explainability methods and how they are evaluated. Furthermore, we propose a new evaluation metric and conduct thorough experiments to compare GNN explainability methods on real world datasets. We also suggest future directions for GNN explainability.