2023
DOI: 10.1609/aaai.v37i4.25610
|View full text |Cite
|
Sign up to set email alerts
|

Learning to Count Isomorphisms with Graph Neural Networks

Abstract: 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 cost. Some recent studies resort to graph neural networks (GNNs) to learn a low-dimensional representation for both the query and input graphs, in order to predict the number of subgraph isomorphisms on the input graph. However, typical GNNs employ … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2

Citation Types

0
2
0

Year Published

2024
2024
2024
2024

Publication Types

Select...
3
1

Relationship

1
3

Authors

Journals

citations
Cited by 4 publications
(2 citation statements)
references
References 40 publications
0
2
0
Order By: Relevance
“…Mining such widespread graph data has fueled a myriad of Web applications, ranging from Web mining [1,54] and social network analysis [63,65] to content recommendation [35,66]. Contemporary techniques for graph analysis predominantly rely on graph representation learning, particularly graph neural networks (GNNs) [12,13,23,43,60]. Most GNNs operate on a message-passing framework, where each node updates its representation by iteratively receiving and aggregating messages from its neighbors [2,3,25,26,[44][45][46], while more recent approaches have also explored transformer-based architectures [21,52,62].…”
Section: Introductionmentioning
confidence: 99%
“…Mining such widespread graph data has fueled a myriad of Web applications, ranging from Web mining [1,54] and social network analysis [63,65] to content recommendation [35,66]. Contemporary techniques for graph analysis predominantly rely on graph representation learning, particularly graph neural networks (GNNs) [12,13,23,43,60]. Most GNNs operate on a message-passing framework, where each node updates its representation by iteratively receiving and aggregating messages from its neighbors [2,3,25,26,[44][45][46], while more recent approaches have also explored transformer-based architectures [21,52,62].…”
Section: Introductionmentioning
confidence: 99%
“…So far, GNNs have significantly promoted the development of graph analysis towards real-world applications. e.g, node classifification (Abu-El-Haija et al 2019;Wu, He, and Xu 2019), link prediction (Kipf and Welling 2016b;You, Ying, and Leskovec 2019), subgraph isomorphism counting (Yu et al 2023), and graph classifification (Gao and Ji 2019;Zhang et al 2018).…”
Section: Introductionmentioning
confidence: 99%