NeurIPS 2020

PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks

Meta Review

In this paper, the authors propose a new method to explain GNN. The proposed algorithm PGM-Explainer is technically sounds and novel. Through experiments, the authors demonstrated that the proposed method outperforms GNNexplainer, which is a state-of-the-art GNN explainer. The explanation of GNN is an important research topic and there exist a few methods. Moreover, all reviewers are positive about the paper, and thus, this paper is good to be presented at NeurIPS.