Skip to main content
SpringerLink
Log in

A subspace constraint based approach for fast hierarchical graph embedding

  • Published:
World Wide Web Aims and scope Submit manuscript

Abstract

Hierarchy network, as a type of complex graphs, is widely used in many application scenarios such as social network analysis in web, human resource analysis in e-government, and product recommendation in e-commerce. Hierarchy preserving network embedding is a representation learning method that project nodes into feature space by preserving the hierarchy property of networks. Recently, researches on network embedding are devoted to mining hierarchical structures and profit a lot form it. Among these works, SpaceNE stands out of preserving hierarchy with the help of subspace constraint on the hierarchical subspace system. However, like all other existing works, SpaceNE is based on transductive learning method and is hard to generalize to new nodes. Besides, they have high time complexity and hard to be scalable to large-scale networks. This paper proposes an inductive method, FastHGE to learn node representation more efficiently and generalize to new nodes more easily. As SpaceNE, a hierarchy network is embedded into a hierarchical subspace tree. For upper communities, we exploit transductive learning by preserving inner-subspace proximity of subspace from the same ancestor. For extending to new nodes, we adopt inductive learning to learn representations of leaf nodes. The overall representation of a node is retrieved by concatenating the embedding vectors of all its ancestor communities and the leaf node. By learning the basis vectors of subspace, the computing cost is alleviated from updating many parameters of projection matrices as in SpaceNE. The performance evaluation experiments show that FastHGE outperforms with much fast speed and the same accuracy. For example, in the node classification, FastHGE is nearly 30 times faster than SpaceNE. The source code of FastHGE is available online.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

Data Availability

Our code and data are open-source and are available on Anonymous Github (https://anonymous.4open.science/r/FGEcode-6B34/README.md).

Notes

  1. https://anonymous.4open.science/r/FGEcode-6B34/README.md

References

  1. Shen, S., Fu, Y., Jia, A.L., Su, H., Wang, Q., Wang, C., Dou, Y.: Learning network representation through reinforcement learning. In: ICASSP, pp. 3537–3541. IEEE, Piscataway (2020)

    Google Scholar 

  2. Gamage, A., Rappaport, B., Aeron, S., Hu, X.: Common randomized shortest paths (C-RSP): a simple yet effective framework for multi-view graph embedding. In: ICASSP, pp. 3542–3546. IEEE, Piscataway (2019)

  3. Bi, X., Nie, H., Zhang, G., Hu, L., Ma, Y., Zhao, X., Yuan, Y., Wang, G.: Boosting question answering over knowledge graph with reward integration and policy evaluation under weak supervision. Inf. Process. Manag. 60(2), 103242 (2023)

    Article  Google Scholar 

  4. Song, X., Li, J., Cai, T., Yang, S., Yang, T., Liu, C.: A survey on deep learning based knowledge tracing. Knowl. Based Syst. 258, 110036 (2022)

    Article  Google Scholar 

  5. Perozzi, B., Al-Rfou, R., Skiena, S.: Deepwalk: online learning of social representations. In: KDD, pp. 701–710. ACM, New York (2014)

  6. Tang, J., Qu, M., Wang, M., Zhang, M., Yan, J., Mei, Q.: LINE: large-scale information network embedding. In: WWW, pp. 1067–1077. ACM, New York (2015)

  7. Grover, A., Leskovec, J.: Node2vec: scalable feature learning for networks. In: KDD, pp. 855–864. ACM, New York (2016)

  8. Wang, X., Cui, P., Wang, J., Pei, J., Zhu, W., Yang, S.: Community preserving network embedding. In: AAAI, pp. 203–209. AAAI Press, Palo Alto (2017)

  9. Du, L., Lu, Z., Wang, Y., Song, G., Wang, Y., Chen, W.: Galaxy network embedding: a hierarchical community structure preserving approach. In: IJCAI, pp. 2079–2085. ijcai.org, New York (2018)

  10. Long, Q., Wang, Y., Du, L., Song, G., Jin, Y., Lin, W.: Hierarchical community structure preserving network embedding: a subspace approach. In: CIKM, pp. 409–418. ACM, New York (2019)

  11. Chen, X., Du, L., Chen, M., Wang, Y., Long, Q., Xie, K.: Fast hierarchy preserving graph embedding via subspace constraints. In: ICASSP, pp. 3580–3584. IEEE, Piscataway (2021)

  12. Hamilton, W.L., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: NIPS, New York pp. 1024–1034 (2017)

  13. Traud, A.L., Mucha, P.J., Porter, M.A.: Social structure of facebook networks. Phys. A Stat. Mech. Appl. 391(16), 4165–4180 (2012)

    Article  Google Scholar 

  14. Hu, F., Zhu, Y., Wu, S., Wang, L., Tan, T.: Hierarchical graph convolutional networks for semi-supervised node classification. In: IJCAI, pp. 4532–4539. ijcai.org, New York (2019)

  15. Rushing, J.A., Ramachandran, R., Nair, U., Graves, S.J., Welch, R., Lin, H.: Adam: a data mining toolkit for scientists and engineers. Comput. Geosci. 31(5), 607–618 (2005)

    Article  Google Scholar 

  16. Wang, H., Chen, E., Liu, Q., Xu, T., Du, D., Su, W., Zhang, X.: A united approach to learning sparse attributed network embedding. In: ICDM, pp. 557–566. IEEE Computer Society, Los Alamitos (2018)

  17. Yang, R., Shi, J., Xiao, X., Yang, Y., Bhowmick, S.S., Liu, J.: No pane, no gain: Scaling attributed network embedding in a single server. SIGMOD Rec. 51(1), 42–49 (2022)

    Article  Google Scholar 

  18. Liu, X., Yang, B., Song, W., Musial, K., Zuo, W., Chen, H., Yin, H.: A block-based generative model for attributed network embedding. World Wide Web 24(5), 1439–1464 (2021)

    Article  Google Scholar 

  19. Zheng, Z., Zhang, C., Gao, X., Chen, G.: HIEN: hierarchical intention embedding network for click-through rate prediction. In: SIGIR, pp. 322–331. ACM, New York (2022)

  20. Zhang, D., Yin, J., Zhu, X., Zhang, C.: Homophily, structure, and content augmented network representation learning. In: ICDM, pp. 609–618. IEEE Computer Society, Los Alamitos (2016)

  21. Liu, J., He, Z., Wei, L., Huang, Y.: Content to node: Self-translation network embedding. In: KDD, pp. 1794–1802. ACM, New York (2018)

  22. Yang, C., Liu, Z., Zhao, D., Sun, M., Chang, E.Y.: Network representation learning with rich text information. In: IJCAI, pp. 2111–2117. AAAI Press, Palo Alto (2015)

  23. Meng, Z., Liang, S., Bao, H., Zhang, X.: Co-embedding attributed networks. In: WSDM, pp. 393–401. ACM, New York (2019)

  24. Zhang, Z., Xiong, H., Xu, T., Qin, C., Zhang, L., Chen, E.: Complex attributed network embedding for medical complication prediction. Knowl. Inf. Syst. 64(9), 2435–2456 (2022)

    Article  Google Scholar 

  25. Zhang, Y., Gao, S., Pei, J., Huang, H.: Improving social network embedding via new second-order continuous graph neural networks. In: KDD, pp. 2515–2523. ACM, New York (2022)

  26. Zhang, R., Zimek, A., Schneider-Kamp, P.: A simple meta-path-free framework for heterogeneous network embedding. In: CIKM, pp. 2600–2609. ACM, New York (2022)

  27. Xiong, H., Yan, J.: Btwalk: Branching tree random walk for multi-order structured network embedding. IEEE Trans. Knowl. Data Eng. 34(8), 3611–3628 (2022)

    Article  Google Scholar 

  28. Zheng, S., Guan, D., Yuan, W.: Semantic-aware heterogeneous information network embedding with incompatible meta-paths. World Wide Web 25(1), 1–21 (2022)

    Article  Google Scholar 

  29. Du, L., Chen, X., Gao, F., Fu, Q., Xie, K., Han, S., Zhang, D.: Understanding and improvement of adversarial training for network embedding from an optimization perspective. In: WSDM, pp. 230–240. ACM, New York (2022)

Download references

Funding

This work was supported by the National Natural Science Foundation of China(61902055, 62137001).

Author information

Authors and Affiliations

  1. Software College, Northeastern University, No. 195 Chuangxin Road, 110169, Shenyang, China

    Minghe Yu

  2. School of Intelligence Science and Technology, Peking University, No. 5 Yiheyuan Road, 100871, Beijing, China

    Xu Chen & Lun Du

  3. School of Computer Science and Engineering, Northeastern University, No. 195 Chuangxin Road, 100169, Shenyang, China

    Xinhao Gu & Hengyu Liu

Authors
  1. Minghe Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xu Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xinhao Gu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Hengyu Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Lun Du
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Minghe Yu and Xu Chen wrote the main manuscript text. Xinhao Gu and Hengyu Liu programed the code of the model and validated the model. Lun Du supervised the work. All authors reviewed the manuscript.

Corresponding author

Correspondence to Minghe Yu.

Ethics declarations

Competing Interests

We wish to confirm that there are no known conflicts of interest associated with this publication and there has been no significant financial support for this work that could have influenced its outcome.

Ethics Approval

Not applicable.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Minghe Yu and Xu Chen contributed equally to this work.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yu, M., Chen, X., Gu, X. et al. A subspace constraint based approach for fast hierarchical graph embedding. World Wide Web 26, 3691–3705 (2023). https://doi.org/10.1007/s11280-023-01177-9

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11280-023-01177-9

Keywords

Search

Navigation