GNNExplainer: Generating Explanations for Graph Neural Networks

• Published in: Advances in neural information processing systems Vol. 32; p. 9240
• Main Authors: Ying, Rex, Bourgeois, Dylan, You, Jiaxuan, Zitnik, Marinka, Leskovec, Jure
• Format: Journal Article
• Language: English
• Published: United States 01.12.2019

Graph Neural Networks (GNNs) are a powerful tool for machine learning on graphs. GNNs combine node feature information with the graph structure by recursively passing neural messages along edges of the input graph. However, incorporating both graph structure and feature information leads to complex...