Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networks

arXiv:2310.01820v2 Announce Type: replace
Abstract: Graph Neural Networks (GNNs) are neural models that leverage the dependency structure in graphical data via message passing among the graph nodes. GNNs have emerged as pivotal architectures in analyzing graph-structured data, and their expansive application in sensitive domains requires a comprehensive understanding of their decision-making processes -- necessitating a framework for GNN explainability. An explanation function for GNNs takes a pre-trained GNN along with a graph as input, to produce a `sufficient statistic' subgraph …

arxiv cs.lg explainability fidelity graph graph neural networks networks neural networks robust type