Evaluating Neighbor Explainability for Graph Neural Networks

arXiv:2311.08118v2 Announce Type: replace
Abstract: Explainability in Graph Neural Networks (GNNs) is a new field growing in the last few years. In this publication we address the problem of determining how important is each neighbor for the GNN when classifying a node and how to measure the performance for this specific task. To do this, various known explainability methods are reformulated to get the neighbor importance and four new metrics are presented. Our results show that there is almost no …

abstract arxiv cs.ai cs.lg explainability gnn gnns graph graph neural networks networks neural networks node performance publication type