EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Time

arXiv:2405.01762v1 Announce Type: new
Abstract: Understanding and explaining the predictions of Graph Neural Networks (GNNs), is crucial for enhancing their safety and trustworthiness. Subgraph-level explanations are gaining attention for their intuitive appeal. However, most existing subgraph-level explainers face efficiency challenges in explaining GNNs due to complex search processes. The key challenge is to find a balance between intuitiveness and efficiency while ensuring transparency. Additionally, these explainers usually induce subgraphs by nodes, which may introduce less-intuitive disconnected nodes in the subgraph-level …

abstract arxiv attention challenges cs.lg edge efficiency explainers face gnn gnns graph graph neural networks however key linear networks neural networks predictions processes safety search the key type understanding