IDEAS home Printed from https://ideas.repec.org/a/gam/jmathe/v10y2022i23p4586-d992832.html
   My bibliography  Save this article

Convolution Based Graph Representation Learning from the Perspective of High Order Node Similarities

Author

Listed:
  • Xing Li

    (School of Mathematical Sciences, Beihang University, Beijing 100191, China
    Key Laboratory of Mathematics Informatics Behavioral Semantics, Ministry of Education, Beijing 100191, China)

  • Qingsong Li

    (Key Laboratory of Mathematics Informatics Behavioral Semantics, Ministry of Education, Beijing 100191, China
    Institute of Artificial Intelligence, Beihang University, Beijing 100191, China
    Zhongguancun Laboratory, Beijing 100094, China)

  • Wei Wei

    (School of Mathematical Sciences, Beihang University, Beijing 100191, China
    Key Laboratory of Mathematics Informatics Behavioral Semantics, Ministry of Education, Beijing 100191, China
    Institute of Artificial Intelligence, Beihang University, Beijing 100191, China
    Zhongguancun Laboratory, Beijing 100094, China)

  • Zhiming Zheng

    (School of Mathematical Sciences, Beihang University, Beijing 100191, China
    Key Laboratory of Mathematics Informatics Behavioral Semantics, Ministry of Education, Beijing 100191, China
    Institute of Artificial Intelligence, Beihang University, Beijing 100191, China
    Zhongguancun Laboratory, Beijing 100094, China)

Abstract

Nowadays, graph representation learning methods, in particular graph neural network methods, have attracted great attention and performed well in many downstream tasks. However, most graph neural network methods have a single perspective since they start from the edges (or adjacency matrix) of graphs, ignoring the mesoscopic structure (high-order local structure). In this paper, we introduce HS-GCN (High-order Node Similarity Graph Convolutional Network), which can mine the potential structural features of graphs from different perspectives by combining multiple high-order node similarity methods. We analyze HS-GCN theoretically and show that it is a generalization of the convolution-based graph neural network methods from different normalization perspectives. A series of experiments have shown that by combining high-order node similarities, our method can capture and utilize the high-order structural information of the graph more effectively, resulting in better results.

Suggested Citation

  • Xing Li & Qingsong Li & Wei Wei & Zhiming Zheng, 2022. "Convolution Based Graph Representation Learning from the Perspective of High Order Node Similarities," Mathematics, MDPI, vol. 10(23), pages 1-13, December.
    • Handle: RePEc:gam:jmathe:v:10:y:2022:i:23:p:4586-:d:992832
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2227-7390/10/23/4586/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/2227-7390/10/23/4586/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Tao Zhou & Linyuan Lü & Yi-Cheng Zhang, 2009. "Predicting missing links via local information," The European Physical Journal B: Condensed Matter and Complex Systems, Springer;EDP Sciences, vol. 71(4), pages 623-630, October.
    2. Wu, Zhihao & Lin, Youfang & Wang, Jing & Gregory, Steve, 2016. "Link prediction with node clustering coefficient," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 452(C), pages 1-8.
    3. Leo Katz, 1953. "A new status index derived from sociometric analysis," Psychometrika, Springer;The Psychometric Society, vol. 18(1), pages 39-43, March.
    4. Kumar, Ajay & Singh, Shashank Sheshar & Singh, Kuldeep & Biswas, Bhaskar, 2020. "Link prediction techniques, applications, and performance: A survey," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 553(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. Mishra, Shivansh & Singh, Shashank Sheshar & Kumar, Ajay & Biswas, Bhaskar, 2022. "ELP: Link prediction in social networks based on ego network perspective," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 605(C).
    2. Lin, Dan & Wu, Jiajing & Xuan, Qi & Tse, Chi K., 2022. "Ethereum transaction tracking: Inferring evolution of transaction networks via link prediction," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 600(C).
    3. Shenshen Bai & Longjie Li & Jianjun Cheng & Shijin Xu & Xiaoyun Chen, 2018. "Predicting Missing Links Based on a New Triangle Structure," Complexity, Hindawi, vol. 2018, pages 1-11, December.
    4. Lee, Yan-Li & Zhou, Tao, 2021. "Collaborative filtering approach to link prediction," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 578(C).
    5. Peng Liu & Liang Gui & Huirong Wang & Muhammad Riaz, 2022. "A Two-Stage Deep-Learning Model for Link Prediction Based on Network Structure and Node Attributes," Sustainability, MDPI, vol. 14(23), pages 1-15, December.
    6. Yu, Jiating & Wu, Ling-Yun, 2022. "Multiple Order Local Information model for link prediction in complex networks," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 600(C).
    7. Ankita Singh & Nanhay Singh, 2022. "An approach for predicting missing links in social network using node attribute and path information," International Journal of System Assurance Engineering and Management, Springer;The Society for Reliability, Engineering Quality and Operations Management (SREQOM),India, and Division of Operation and Maintenance, Lulea University of Technology, Sweden, vol. 13(2), pages 944-956, April.
    8. Wang, Jun & Zhang, Qian-Ming & Zhou, Tao, 2019. "Tag-aware link prediction algorithm in complex networks," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 523(C), pages 105-111.
    9. Kumar, Ajay & Singh, Shashank Sheshar & Singh, Kuldeep & Biswas, Bhaskar, 2020. "Link prediction techniques, applications, and performance: A survey," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 553(C).
    10. Chunning Wang & Fengqin Tang & Xuejing Zhao, 2023. "LPGRI: A Global Relevance-Based Link Prediction Approach for Multiplex Networks," Mathematics, MDPI, vol. 11(14), pages 1-15, July.
    11. Wu, Jiehua & Shen, Jing & Zhou, Bei & Zhang, Xiayan & Huang, Bohuai, 2019. "General link prediction with influential node identification," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 523(C), pages 996-1007.
    12. Xu-Wen Wang & Lorenzo Madeddu & Kerstin Spirohn & Leonardo Martini & Adriano Fazzone & Luca Becchetti & Thomas P. Wytock & István A. Kovács & Olivér M. Balogh & Bettina Benczik & Mátyás Pétervári & Be, 2023. "Assessment of community efforts to advance network-based prediction of protein–protein interactions," Nature Communications, Nature, vol. 14(1), pages 1-14, December.
    13. Mueller, Falko, 2023. "Link and edge weight prediction in air transport networks — An RNN approach," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 613(C).
    14. Yao, Yabing & Zhang, Ruisheng & Yang, Fan & Tang, Jianxin & Yuan, Yongna & Hu, Rongjing, 2018. "Link prediction in complex networks based on the interactions among paths," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 510(C), pages 52-67.
    15. Karimi, Fatemeh & Lotfi, Shahriar & Izadkhah, Habib, 2021. "Community-guided link prediction in multiplex networks," Journal of Informetrics, Elsevier, vol. 15(4).
    16. Wang, Zuxi & Wu, Yao & Li, Qingguang & Jin, Fengdong & Xiong, Wei, 2016. "Link prediction based on hyperbolic mapping with community structure for complex networks," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 450(C), pages 609-623.
    17. Moradabadi, Behnaz & Meybodi, Mohammad Reza, 2016. "Link prediction based on temporal similarity metrics using continuous action set learning automata," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 460(C), pages 361-373.
    18. 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.
    19. Wu, Tao & Chen, Leiting & Zhong, Linfeng & Xian, Xingping, 2017. "Predicting the evolution of complex networks via similarity dynamics," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 465(C), pages 662-672.
    20. Zhang, Xue & Wang, Xiaojie & Zhao, Chengli & Yi, Dongyun & Xie, Zheng, 2014. "Degree-corrected stochastic block models and reliability in networks," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 393(C), pages 553-559.

    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:23:p:4586-:d:992832. 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.