IDEAS home Printed from https://ideas.repec.org/a/gam/jmathe/v10y2022i17p3047-d896524.html
   My bibliography  Save this article

Subgraph Adaptive Structure-Aware Graph Contrastive Learning

Author

Listed:
  • Zhikui Chen

    (School of Software, Dalian University of Technology, Dalian 116620, China)

  • Yin Peng

    (School of Software, Dalian University of Technology, Dalian 116620, China)

  • Shuo Yu

    (School of Computer Science and Technology, Dalian University of Technology, Dalian 116024, China)

  • Chen Cao

    (Information Networking Institute, Carnegie Mellon University, Pittsburgh, PA 15213, USA)

  • Feng Xia

    (Institute of Innovation, Science and Sustainability, Federation University Australia, Ballarat, VIC 3353, Australia)

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.

Suggested Citation

  • Zhikui Chen & Yin Peng & Shuo Yu & Chen Cao & Feng Xia, 2022. "Subgraph Adaptive Structure-Aware Graph Contrastive Learning," Mathematics, MDPI, vol. 10(17), pages 1-18, August.
    • Handle: RePEc:gam:jmathe:v:10:y:2022:i:17:p:3047-:d:896524
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2227-7390/10/17/3047/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/2227-7390/10/17/3047/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Nasiri, Elahe & Berahmand, Kamal & Li, Yuefeng, 2021. "A new link prediction in multiplex networks using topologically biased random walks," Chaos, Solitons & Fractals, Elsevier, vol. 151(C).
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Mingshuo Nie & Dongming Chen & Dongqi Wang, 2022. "Graph Embedding Method Based on Biased Walking for Link Prediction," Mathematics, MDPI, vol. 10(20), pages 1-13, October.
    2. Jiaping Cao & Tianyang Lei & Jichao Li & Jiang Jiang, 2023. "A Novel Link Prediction Method for Social Multiplex Networks Based on Deep Learning," Mathematics, MDPI, vol. 11(7), pages 1-19, April.
    3. Nikzad-Khasmakhi, N. & Balafar, M.A. & Reza Feizi-Derakhshi, M. & Motamed, Cina, 2021. "BERTERS: Multimodal representation learning for expert recommendation system with transformers and graph embeddings," Chaos, Solitons & Fractals, Elsevier, vol. 151(C).
    4. Wenjun Li & Ting Li & Kamal Berahmand, 2023. "An effective link prediction method in multiplex social networks using local random walk towards dependable pathways," Journal of Combinatorial Optimization, Springer, vol. 45(1), pages 1-27, January.
    5. Wang, Minggang & Zhu, Mengrui & Tian, Lixin, 2022. "A novel framework for carbon price forecasting with uncertainties," Energy Economics, Elsevier, vol. 112(C).
    6. Liu, Qian & Wang, Jian & Zhao, Zhidan & Zhao, Na, 2022. "Relatively important nodes mining algorithm based on community detection and biased random walk with restart," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 607(C).
    7. Shengfeng Gan & Mohammed Alshahrani & Shichao Liu, 2022. "Positive-Unlabeled Learning for Network Link Prediction," Mathematics, MDPI, vol. 10(18), pages 1-13, September.
    8. Rai, Abhay Kumar & Tripathi, Shashi Prakash & Yadav, Rahul Kumar, 2023. "A novel similarity-based parameterized method for link prediction," Chaos, Solitons & Fractals, Elsevier, vol. 175(P2).
    9. Guanchen Xiao & Jinzhi Liao & Zhen Tan & Xiaonan Zhang & Xiang Zhao, 2022. "A Two-Stage Framework for Directed Hypergraph Link Prediction," Mathematics, MDPI, vol. 10(14), pages 1-18, July.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jmathe:v:10:y:2022:i:17:p:3047-:d:896524. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.