Adaptive Subgraph Neural Network with Reinforced Critical Structure Mining

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 45; no. 7; pp. 1 - 18
• Main Authors: Li, Jianxin, Sun, Qingyun, Peng, Hao, Yang, Beining, Wu, Jia, Yu, Phillp S.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.07.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Annotations; critical structure; Feature extraction; graph classification; graph neural network; Graph neural networks; Graph representation learning; Graph representations; Graph theory; Graphical representations; Information theory; Kernel; mutual information; Neural networks; reinforcement learning; Representation learning; Shape; Task analysis

While graph representation learning methods have shown success in various graph mining tasks, what knowledge is exploited for predictions is less discussed. This paper proposes a novel A daptive S ubgraph N eural N etwork named AdaSNN to find critical structures in graph data, i.e., subgraphs that a...