Learning to count isomorphisms with graph neural networks

• Main Authors: YU, Xingtong, LIU, Zemin, FANG, Yuan, ZHANG, Xinming
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: Classical methods; Computational costs; Graph neural networks; Graph-based; Input graphs; Message-passing; Query graph; Search spaces; Subgraph isomorphism; Subgraphs; Information Security
• Online Access: https://ink.library.smu.edu.sg/sis_research/8178; https://ink.library.smu.edu.sg/context/sis_research/article/9181/viewcontent/AAAI23_CountGNN.pdf
• Institution: Singapore Management University

Subgraph isomorphism counting is an important problem on graphs, as many graph-based tasks exploit recurring subgraph patterns. Classical methods usually boil down to a backtracking framework that needs to navigate a huge search space with prohibitive computational costs. Some recent studies resort...