skip to main content
10.1145/3488560.3498531acmconferencesArticle/Chapter ViewAbstractPublication PageswsdmConference Proceedingsconference-collections
research-article

Multi-Scale Variational Graph AutoEncoder for Link Prediction

Published: 15 February 2022 Publication History

Abstract

Link prediction has become a significant research problem in deep learning, and the graph-based autoencoder model is one of the most important methods to solve it. The existing graph-based autoencoder models only learn a single set of distributions, which cannot accurately represent the mixed distribution in real graph data. Meanwhile, existing learning models have been greatly restricted when the graph data has insufficient attribute information and inaccurate topology information. In this paper, we propose a novel graph embedding framework, termed multi-scale variational graph autoencoder (MSVGAE), which learns multiple sets of low-dimensional vectors of different dimensions through the graph encoder to represent the mixed probability distribution of the original graph data, and performs multiple sampling in each dimension. Furthermore, a self-supervised learning strategy (i.e., graph feature reconstruction auxiliary learning) is introduced to fully use the graph attribute information to help the graph structure learning. Experiment studies on real-world graphs demonstrate that the proposed model achieves state-of-the-art performance compared with other baseline methods in link prediction tasks. Besides, the robustness analysis shows that the proposed MSVGAE method has obvious advantages in the processes of graph data with insufficient attribute information and inaccurate topology information.

Supplementary Material

MP4 File (WSDM22-fp288.mp4)
Presentation video of wsdmfp288

References

[1]
Shaosheng Cao, Wei Lu, and Qiongkai Xu. 2015. Grarep: Learning graph representations with global structural information. In Proceedings of the 24th ACM International on Conference on Information and Knowledge Management . 891--900.
[2]
Liang Chen, Paul Bentley, Kensaku Mori, Kazunari Misawa, Michitaka Fujiwara, and Daniel Rueckert. 2019. Self-supervised learning for medical image analysis using image context restoration. Medical Image Analysis, Vol. 58 (2019), 101539.
[3]
Aaron Clauset, Cristopher Moore, and Mark EJ Newman. 2008. Hierarchical structure and the prediction of missing links in networks. Nature, Vol. 453, 7191 (2008), 98--101.
[4]
Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. Advances in Neural Information Processing Systems, Vol. 27 (2014), 2672--2680.
[5]
Aditya Grover and Jure Leskovec. 2016. node2vec: Scalable feature learning for networks. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining . 855--864.
[6]
Di Jin, Cuiying Huo, Chundong Liang, and Liang Yang. 2021 b. Heterogeneous Graph Neural Network via Attribute Completion. In Proceedings of the Web Conference 2021. 391--400.
[7]
Di Jin, Zhizhi Yu, Pengfei Jiao, Shirui Pan, Dongxiao He, Jia Wu, Philip Yu, and Weixiong Zhang. 2021 c. A Survey of Community Detection Approaches: From Statistical Modeling to Deep Learning. IEEE Transactions on Knowledge and Data Engineering (2021). https://doi.org/10.1109/TKDE.2021.3104155
[8]
Wei Jin, Tyler Derr, Yiqi Wang, Yao Ma, Zitao Liu, and Jiliang Tang. 2021 a. Node similarity preserving graph convolutional networks. In Proceedings of the 14th ACM International Conference on Web Search and Data Mining . 148--156.
[9]
Diederik P Kingma and Max Welling. 2014. Auto-encoding variational bayes. In International Conference on Learning Representations .
[10]
Thomas N Kipf and Max Welling. 2016. Variational graph auto-encoders. In Bayesian Deep Learning Workshop on NIPS .
[11]
Thomas N Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In International Conference on Learning Representations .
[12]
David Liben-Nowell and Jon Kleinberg. 2007. The link-prediction problem for social networks. Journal of the American Society for Information Science and Technology, Vol. 58, 7 (2007), 1019--1031.
[13]
Zheng Ma, Junyu Xuan, Yu Guang Wang, Ming Li, and Pietro Liò. 2020. Path Integral Based Convolution and Pooling for Graph Neural Networks. In Advances in Neural Information Processing Systems. 16433--16445.
[14]
Mingdong Ou, Peng Cui, Jian Pei, Ziwei Zhang, and Wenwu Zhu. 2016. Asymmetric transitivity preserving graph embedding. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining . 1105--1114.
[15]
Shirui Pan, Ruiqi Hu, Guodong Long, Jing Jiang, Lina Yao, and Chengqi Zhang. 2018. Adversarially regularized graph autoencoder for graph embedding. ArXiv Preprint ArXiv:1802.04407 (2018).
[16]
Jiwoong Park, Minsik Lee, Hyung Jin Chang, Kyuewang Lee, and Jin Young Choi. 2019. Symmetric graph convolutional autoencoder for unsupervised graph representation learning. In Proceedings of the IEEE International Conference on Computer Vision. 6519--6528.
[17]
Bryan Perozzi, Rami Al-Rfou, and Steven Skiena. 2014. Deepwalk: Online learning of social representations. In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining . 701--710.
[18]
Jian Tang, Meng Qu, Mingzhe Wang, Ming Zhang, Jun Yan, and Qiaozhu Mei. 2015. Line: Large-scale information network embedding. In Proceedings of the 24th International Conference on World Wide Web. 1067--1077.
[19]
Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of Machine Learning Research, Vol. 9, 11 (2008).
[20]
Petar Velivc ković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. 2018a. Graph Attention Networks. In International Conference on Learning Representations .
[21]
Petar Velivc ković, William Fedus, William L Hamilton, Pietro Liò, Yoshua Bengio, and R Devon Hjelm. 2018b. Deep Graph Infomax. In International Conference on Learning Representations .
[22]
Chun Wang, Shirui Pan, Guodong Long, Xingquan Zhu, and Jing Jiang. 2017c. Mgae: Marginalized graph autoencoder for graph clustering. In Proceedings of the 2017 ACM on Conference on Information and Knowledge Management . 889--898.
[23]
Hongwei Wang, Jia Wang, Jialin Wang, Miao Zhao, Weinan Zhang, Fuzheng Zhang, Xing Xie, and Minyi Guo. 2018. Graphgan: Graph representation learning with generative adversarial nets. In Proceedings of the Thirty-second AAAI Conference on Artificial Intelligence .
[24]
Jie Wang, Jianqing Liang, Junbiao Cui, and Jiye Liang. 2021. Semi-supervised learning with mixed-order graph convolutional networks. Information Sciences, Vol. 573 (2021), 171--181.
[25]
Xiao Wang, Peng Cui, Jing Wang, Jian Pei, Wenwu Zhu, and Shiqiang Yang. 2017b. Community preserving network embedding. In Proceedings of the Thirty-first AAAI conference on artificial intelligence .
[26]
Yu Guang Wang, Ming Li, Zheng Ma, Guido Montufar, Xiaosheng Zhuang, and Yanan Fan. 2020. Haar graph pooling. In Proceedings of the International Conference on Machine Learning. 9952--9962.
[27]
Zhitao Wang, Chengyao Chen, and Wenjie Li. 2017a. Predictive network representation learning for link prediction. In Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval. 969--972.
[28]
Yaochen Xie, Zhao Xu, Jingtun Zhang, Zhengyang Wang, and Shuiwang Ji. 2021. Self-supervised learning of graph neural networks: A unified review. ArXiv Preprint ArXiv:2102.10757 (2021).
[29]
Shuai Zheng, Zhenfeng Zhu, Xingxing Zhang, Zhizhe Liu, Jian Cheng, and Yao Zhao. 2020. Distribution-induced Bidirectional Generative Adversarial Network for Graph Representation Learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 7224--7233.
[30]
Tao Zhou, Linyuan Lü, and Yi-Cheng Zhang. 2009. Predicting missing links via local information. The European Physical Journal B, Vol. 71, 4 (2009), 623--630.

Cited By

View all
  • (2025)Dual stream fusion link prediction for sparse graph based on variational graph autoencoder and pairwise learningInformation Processing & Management10.1016/j.ipm.2025.10407362:3(104073)Online publication date: May-2025
  • (2025)DMGAE: An interpretable representation learning method for directed scale-free networks based on autoencoder and maskingInformation Processing & Management10.1016/j.ipm.2024.10400762:3(104007)Online publication date: May-2025
  • (2024)Identification of microbe–disease signed associations via multi-scale variational graph autoencoder based on signed message propagationBMC Biology10.1186/s12915-024-01968-022:1Online publication date: 15-Aug-2024
  • Show More Cited By

Index Terms

  1. Multi-Scale Variational Graph AutoEncoder for Link Prediction

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Conferences
    WSDM '22: Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining
    February 2022
    1690 pages
    ISBN:9781450391320
    DOI:10.1145/3488560
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

    Sponsors

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 15 February 2022

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. graph autoencoder
    2. graph neural networks
    3. link prediction
    4. self-supervised learning

    Qualifiers

    • Research-article

    Funding Sources

    Conference

    WSDM '22

    Acceptance Rates

    Overall Acceptance Rate 498 of 2,863 submissions, 17%

    Upcoming Conference

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)146
    • Downloads (Last 6 weeks)10
    Reflects downloads up to 13 Feb 2025

    Other Metrics

    Citations

    Cited By

    View all
    • (2025)Dual stream fusion link prediction for sparse graph based on variational graph autoencoder and pairwise learningInformation Processing & Management10.1016/j.ipm.2025.10407362:3(104073)Online publication date: May-2025
    • (2025)DMGAE: An interpretable representation learning method for directed scale-free networks based on autoencoder and maskingInformation Processing & Management10.1016/j.ipm.2024.10400762:3(104007)Online publication date: May-2025
    • (2024)Identification of microbe–disease signed associations via multi-scale variational graph autoencoder based on signed message propagationBMC Biology10.1186/s12915-024-01968-022:1Online publication date: 15-Aug-2024
    • (2024)Social Influence Learning for Recommendation SystemsProceedings of the 33rd ACM International Conference on Information and Knowledge Management10.1145/3627673.3679598(312-322)Online publication date: 21-Oct-2024
    • (2024)Decoupled Variational Graph Autoencoder for Link PredictionProceedings of the ACM Web Conference 202410.1145/3589334.3645601(839-849)Online publication date: 13-May-2024
    • (2024)Reconstruction and Generation of Porous Metamaterial Units Via Variational Graph Autoencoder and Large Language ModelJournal of Computing and Information Science in Engineering10.1115/1.406609525:2Online publication date: 15-Nov-2024
    • (2024)Improving Variational Graph Autoencoders With Multi-Order Graph ConvolutionsIEEE Access10.1109/ACCESS.2024.338001212(46919-46929)Online publication date: 2024
    • (2024)Graph autoencoder with mirror temporal convolutional networks for traffic anomaly detectionScientific Reports10.1038/s41598-024-51374-314:1Online publication date: 13-Jan-2024
    • (2024)Attribute imputation autoencoders for attribute-missing graphsKnowledge-Based Systems10.1016/j.knosys.2024.111583291:COnline publication date: 2-Jul-2024
    • (2024)Review of heterogeneous graph embedding methods based on deep learning techniques and comparing their efficiency in node classificationSocial Network Analysis and Mining10.1007/s13278-023-01178-614:1Online publication date: 3-Jan-2024
    • Show More Cited By

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media