IDEAS home Printed from https://ideas.repec.org/a/gam/jmathe/v11y2023i3p578-d1043616.html
   My bibliography  Save this article

Learning Heterogeneous Graph Embedding with Metapath-Based Aggregation for Link Prediction

Author

Listed:
  • Chengdong Zhang

    (School of Computer Science and Technology, Shandong University of Technology, Zibo 255091, China
    These authors contributed equally to this work.)

  • Keke Li

    (School of Computer Science and Technology, Shandong University of Technology, Zibo 255091, China
    These authors contributed equally to this work.)

  • Shaoqing Wang

    (School of Computer Science and Technology, Shandong University of Technology, Zibo 255091, China)

  • Bin Zhou

    (School of Computer Science and Technology, Shandong University of Technology, Zibo 255091, China)

  • Lei Wang

    (School of Computer Science and Technology, Shandong University of Technology, Zibo 255091, China)

  • Fuzhen Sun

    (School of Computer Science and Technology, Shandong University of Technology, Zibo 255091, China)

Abstract

Along with the growth of graph neural networks (GNNs), many researchers have adopted metapath-based GNNs to handle complex heterogeneous graph embedding. The conventional definition of a metapath only distinguishes whether there is a connection between nodes in the network schema, where the type of edge is ignored. This leads to inaccurate node representation and subsequently results in suboptimal prediction performance. In heterogeneous graphs, a node can be connected by multiple types of edges. In fact, each type of edge represents one kind of scene. The intuition is that if the embedding of nodes is trained under different scenes, the complete representation of nodes can be obtained by organically combining them. In this paper, we propose a novel definition of a metapath whereby the edge type, i.e., the relation between nodes, is integrated into it. A heterogeneous graph can be considered as the compound of multiple relation subgraphs from the view of a novel metapath. In different subgraphs, the embeddings of a node are separately trained by encoding and aggregating the neighbors of the intrapaths, which are the instance levels of a novel metapath. Then, the final embedding of the node is obtained by the use of the attention mechanism which aggregates nodes from the interpaths, which is the semantic level of the novel metapaths. Link prediction is a downstream task by which to evaluate the effectiveness of the learned embeddings. We conduct extensive experiments on three real-world heterogeneous graph datasets for link prediction. The empirical results show that the proposed model outperforms the state-of-the-art baselines; in particular, when comparing it to the best baseline, the F1 metric is increased by 10.35% over an Alibaba dataset.

Suggested Citation

  • Chengdong Zhang & Keke Li & Shaoqing Wang & Bin Zhou & Lei Wang & Fuzhen Sun, 2023. "Learning Heterogeneous Graph Embedding with Metapath-Based Aggregation for Link Prediction," Mathematics, MDPI, vol. 11(3), pages 1-18, January.
  • Handle: RePEc:gam:jmathe:v:11:y:2023:i:3:p:578-:d:1043616
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2227-7390/11/3/578/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/2227-7390/11/3/578/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Lü, Linyuan & Zhou, Tao, 2011. "Link prediction in complex networks: A survey," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 390(6), pages 1150-1170.
    2. 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)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Canwei Liu & Xingye Deng & Tingqin He & Lei Chen & Guangyang Deng & Yuanyu Hu, 2023. "Multi-View Learning-Based Fast Edge Embedding for Heterogeneous Graphs," Mathematics, MDPI, vol. 11(13), pages 1-23, July.

    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. Lee, Yan-Li & Zhou, Tao, 2021. "Collaborative filtering approach to link prediction," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 578(C).
    2. 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.
    3. 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).
    4. Wang, Feifei & Dong, Jiaxin & Lu, Wanzhao & Xu, Shuo, 2023. "Collaboration prediction based on multilayer all-author tripartite citation networks: A case study of gene editing," Journal of Informetrics, Elsevier, vol. 17(1).
    5. Mafakheri, Aso & Sulaimany, Sadegh & Mohammadi, Sara, 2023. "Predicting the establishment and removal of global trade relations for import and export of petrochemical products," Energy, Elsevier, vol. 269(C).
    6. 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).
    7. 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).
    8. Zhou, Tao, 2023. "Discriminating abilities of threshold-free evaluation metrics in link prediction," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 615(C).
    9. 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.
    10. Tofighy, Sajjad & Charkari, Nasrollah Moghadam & Ghaderi, Foad, 2022. "Link prediction in multiplex networks using intralayer probabilistic distance and interlayer co-evolving factors," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 606(C).
    11. 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.
    12. 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).
    13. Karimi, Fatemeh & Lotfi, Shahriar & Izadkhah, Habib, 2021. "Community-guided link prediction in multiplex networks," Journal of Informetrics, Elsevier, vol. 15(4).
    14. 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).
    15. Chen, Ling-Jiao & Zhang, Zi-Ke & Liu, Jin-Hu & Gao, Jian & Zhou, Tao, 2017. "A vertex similarity index for better personalized recommendation," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 466(C), pages 607-615.
    16. Dong-Rui Chen & Chuang Liu & Yi-Cheng Zhang & Zi-Ke Zhang, 2019. "Predicting Financial Extremes Based on Weighted Visual Graph of Major Stock Indices," Complexity, Hindawi, vol. 2019, pages 1-17, October.
    17. Blagus, Neli & Šubelj, Lovro & Bajec, Marko, 2012. "Self-similar scaling of density in complex real-world networks," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 391(8), pages 2794-2802.
    18. Wei, Daijun & Deng, Xinyang & Zhang, Xiaoge & Deng, Yong & Mahadevan, Sankaran, 2013. "Identifying influential nodes in weighted networks based on evidence theory," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 392(10), pages 2564-2575.
    19. Xu, Hua & Wang, Minggang & Jiang, Shumin & Yang, Weiguo, 2020. "Carbon price forecasting with complex network and extreme learning machine," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 545(C).
    20. Andreas Spitz & Anna Gimmler & Thorsten Stoeck & Katharina Anna Zweig & Emőke-Ágnes Horvát, 2016. "Assessing Low-Intensity Relationships in Complex Networks," PLOS ONE, Public Library of Science, vol. 11(4), pages 1-17, April.

    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:11:y:2023:i:3:p:578-:d:1043616. 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.