IDEAS home Printed from https://ideas.repec.org/a/gam/jmathe/v12y2024i13p1991-d1423933.html
   My bibliography  Save this article

Unsupervised Graph Structure Learning Based on Optimal Graph Topology Modeling and Adaptive Data Augmentation

Author

Listed:
  • Dongdong An

    (Shanghai Engineering Research Center of Intelligent Education and Bigdata, Shanghai Normal University, Shanghai 200234, China)

  • Zongxu Pan

    (Shanghai Engineering Research Center of Intelligent Education and Bigdata, Shanghai Normal University, Shanghai 200234, China)

  • Qin Zhao

    (Shanghai Engineering Research Center of Intelligent Education and Bigdata, Shanghai Normal University, Shanghai 200234, China)

  • Wenyan Liu

    (Ant Group, Hangzhou 310023, China
    College of Computer Science and Technology, Zhejiang University, Hangzhou 310058, China)

  • Jing Liu

    (Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai 200062, China)

Abstract

Graph neural networks (GNNs) are effective for structured data analysis but face reduced learning accuracy due to noisy connections and the necessity for explicit graph structures and labels. This requirement constrains their usability in diverse graph-based applications. In order to address these issues, considerable research has been directed toward graph structure learning that aims to denoise graph structures concurrently and refine GNN parameters. However, existing graph structure learning approaches encounter several challenges, including dependence on label information, underperformance of learning algorithms, insufficient data augmentation methods, and limitations in performing downstream tasks. We propose Uogtag, an unsupervised graph structure learning framework to address these challenges. Uogtag optimizes graph topology through the selection of suitable graph learners for the input data and incorporates contrastive learning with adaptive data augmentation, enhancing the learning and applicability of graph structures for downstream tasks. Comprehensive experiments on various real-world datasets demonstrate Uogtag’s efficacy in managing noisy graphs and label scarcity.

Suggested Citation

  • Dongdong An & Zongxu Pan & Qin Zhao & Wenyan Liu & Jing Liu, 2024. "Unsupervised Graph Structure Learning Based on Optimal Graph Topology Modeling and Adaptive Data Augmentation," Mathematics, MDPI, vol. 12(13), pages 1-22, June.
  • Handle: RePEc:gam:jmathe:v:12:y:2024:i:13:p:1991-:d:1423933
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2227-7390/12/13/1991/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/2227-7390/12/13/1991/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Zhang, Panpan & Wang, Tiandong & Yan, Jun, 2022. "PageRank centrality and algorithms for weighted, directed networks," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 586(C).
    2. Shilin Sun & Hua Tian & Runze Wang & Zehua Zhang, 2023. "Biomedical Interaction Prediction with Adaptive Line Graph Contrastive Learning," Mathematics, MDPI, vol. 11(3), pages 1-14, February.
    3. Wenchuan Zhang & Weihua Ou & Weian Li & Jianping Gou & Wenjun Xiao & Bin Liu, 2023. "Robust Graph Structure Learning with Virtual Nodes Construction," Mathematics, MDPI, vol. 11(6), pages 1-18, March.
    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. Fink, Christian G. & Fullin, Kelly & Gutierrez, Guillermo & Omodt, Nathan & Zinnecker, Sydney & Sprint, Gina & McCulloch, Sean, 2023. "A centrality measure for quantifying spread on weighted, directed networks," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 626(C).
    2. Bowater, David & Stefanakis, Emmanuel, 2023. "Extending the Adapted PageRank Algorithm centrality model for urban street networks using non-local random walks," Applied Mathematics and Computation, Elsevier, vol. 446(C).
    3. Beheshtian-Ardakani, Arash & Salehi, Mostafa & Sharma, Rajesh, 2023. "CMPN: Modeling and analysis of soccer teams using Complex Multiplex Passing Network," Chaos, Solitons & Fractals, Elsevier, vol. 174(C).
    4. Xiao, Shiying & Yan, Jun & Zhang, Panpan, 2022. "Incorporating auxiliary information in betweenness measure for input–output networks," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 607(C).
    5. Tao Wang & Shiying Xiao & Jun Yan, 2024. "Comparison of sectoral structures between China and Japan: A network perspective," Papers 2402.15620, arXiv.org.
    6. Cao, Huiying & Gao, Chao & Wang, Zhen, 2023. "Ranking academic institutions by means of institution–publication networks," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 629(C).
    7. Lan, He & Ma, Xiaoxue & Qiao, Weiliang & Deng, Wanyi, 2023. "Determining the critical risk factors for predicting the severity of ship collision accidents using a data-driven approach," Reliability Engineering and System Safety, Elsevier, vol. 230(C).

    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:12:y:2024:i:13:p:1991-:d:1423933. 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.