- Title
- Subgraph adaptive structure-aware graph contrastive learning
- Creator
- Chen, Zhikui; Peng, Yin; Yu, Shuo; Cao, Chen; Xia, Feng
- Date
- 2022
- Type
- Text; Journal article
- Identifier
- http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/191335
- Identifier
- vital:17781
- Identifier
-
https://doi.org/10.3390/math10173047
- Identifier
- ISSN:2227-7390
- Abstract
- Graph contrastive learning (GCL) has been subject to more attention and been widely applied to numerous graph learning tasks such as node classification and link prediction. Although it has achieved great success and even performed better than supervised methods in some tasks, most of them depend on node-level comparison, while ignoring the rich semantic information contained in graph topology, especially for social networks. However, a higher-level comparison requires subgraph construction and encoding, which remain unsolved. To address this problem, we propose a subgraph adaptive structure-aware graph contrastive learning method (PASCAL) in this work, which is a subgraph-level GCL method. In PASCAL, we construct subgraphs by merging all motifs that contain the target node. Then we encode them on the basis of motif number distribution to capture the rich information hidden in subgraphs. By incorporating motif information, PASCAL can capture richer semantic information hidden in local structures compared with other GCL methods. Extensive experiments on six benchmark datasets show that PASCAL outperforms state-of-art graph contrastive learning and supervised methods in most cases.
- Publisher
- MDPI AG
- Relation
- Mathematics (Basel) Vol. 10, no. 17 (2022), p. 3047
- Rights
- All metadata describing materials held in, or linked to, the repository is freely available under a CC0 licence
- Rights
- https://creativecommons.org/licenses/by/4.0/
- Rights
- © 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license
- Subject
- Analysis; Classification; Clustering; Cognitive tasks; Datasets; Deep learning; Graph contrastive learning; Graph representations; Graph theory; Learning; Network motif; Nodes; Semantics; Smart structures; Social network; Social networks; subgraph learning; Teaching methods; Topology; Unsupervised node classification; 49 Mathematical Sciences
- Full Text
- Reviewed
- Funder
- This work is partially supported by the National Key Research and Development Program of China under Grant No. 2021ZD0112400, the National Natural Science Foundation of China under Grant No. 62102060 and No. 62076047, and the Fundamental Research Funds for the Central Universities under Grant No. DUT22RC(3)060.
- Hits: 1693
- Visitors: 1737
- Downloads: 51
| Thumbnail | File | Description | Size | Format | |||
|---|---|---|---|---|---|---|---|
| View Details Download | SOURCE1 | Published version | 686 KB | Adobe Acrobat PDF | View Details Download |