Skip to main content
SpringerLink
Log in

A representation learning model based on stochastic perturbation and homophily constraint

  • Regular paper
  • Published:
Knowledge and Information Systems Aims and scope Submit manuscript

Abstract

The network representation learning task of fusing node multi-dimensional classification information aims to effectively combine node multi-dimensional classification information and network structure information for representation learning, thereby improving the performance of network representation. However, the existing methods only consider multi-dimensional classification information as priori features, which assists the representation learning of the network structure information, lacks the coping mechanism in the case of missing data, and have low robustness in the case of incomplete information. To address these issues, in this paper, we propose a representation learning model based on stochastic perturbation and homophily constraint, called IMCIN. On the one hand, the data transformation is carried out through the random perturbation strategy to improve the adaptability of the model to incomplete information. On the other hand, in the process of learning fusion representation vectors, an attribute similarity retention method based on the principle of homogeneity is designed to further mine the effective semantic information in the incomplete information. Experiments show that our method can effectively deal with the problem of incomplete information and improve the performance of node classification and link prediction tasks.

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
Algorithm 1
Fig. 2
Fig. 3

Similar content being viewed by others

References

  1. Li Q, Cao Z, Ding W, Li Q (2020) A multi-objective adaptive evolutionary algorithm to extract communities in networks. Swarm Evol Comput 52:100629

    Article  Google Scholar 

  2. Li Z, Wang X, Li J, Zhang Q (2021) Deep attributed network representation learning of complex coupling and interaction. Knowl-Based Syst 212:106618

    Article  Google Scholar 

  3. Li Q, Cao Z, Zhong J, Li Q (2019) Graph representation learning with encoding edges. Neurocomputing 361:29–39

    Article  Google Scholar 

  4. McPherson M, Smith-Lovin L, Cook JM (2001) Birds of a feather: homophily in social networks. Ann Rev Sociol 27(1):415–444

    Article  Google Scholar 

  5. Kossinets G, Watts DJ (2009) Origins of homophily in an evolving social network. Am J Sociol 115(2):405–450

    Article  Google Scholar 

  6. Traud AL, Mucha PJ, Porter MA (2012) Social structure of facebook networks. Physica A 391(16):4165–4180

    Article  Google Scholar 

  7. Zhou J, Cui G, Hu S, Zhang Z, Yang C, Liu Z, Wang L, Li C, Sun M (2020) Graph neural networks: a review of methods and applications. AI Open 1:57–81

    Article  Google Scholar 

  8. Zhou J, Liu L, Wei W, Fan J (2022) Network representation learning: From preprocessing, feature extraction to node embedding. ACM Comput Surv (CSUR) 55(2):1–35

    Article  Google Scholar 

  9. Yang H, Chen L, Pan S, Wang H, Zhang P (2022) Discrete embedding for attributed graphs. Pattern Recogn 123:108368

    Article  Google Scholar 

  10. Pham P, Nguyen LT, Vo B, Yun U (2022) Bot2vec: a general approach of intra-community oriented representation learning for bot detection in different types of social networks. Inf Syst 103:101771

    Article  Google Scholar 

  11. Wang R, Liu Y, Chen J (2021) Network representation learning algorithm combined with node text information. J Phys Conf Ser 1769:012054. IOP Publishing

  12. Nguyen TT, Pham MT, Nguyen TT, Huynh TT, Nguyen QVH, Quan TT (2021) Structural representation learning for network alignment with self-supervised anchor links. Expert Syst Appl 165:113857

    Article  Google Scholar 

  13. Chen J, Zhong M, Li J, Wang D, Qian T, Tu H (2021) Effective deep attributed network representation learning with topology adapted smoothing. IEEE Trans Cybernet

  14. Zhao S, Du Z, Chen J, Zhang Y, Tang J, Yu P (2021) Hierarchical representation learning for attributed networks. IEEE Trans Knowl Data Eng

  15. Wu H, Ji J, Tian H, Chen Y, Ge W, Zhang H, Yu F, Zou J, Nakamura M, Liao J (2021) Chinese-named entity recognition from adverse drug event records: radical embedding-combined dynamic embedding-based bert in a bidirectional long short-term conditional random field (bi-lstm-crf) model. JMIR Med Inform 9(12):26407

    Article  Google Scholar 

  16. Wu Z, Zhan M, Zhang H, Luo Q, Tang K (2022) MTGCN: a multi-task approach for node classification and link prediction in graph data. Inf Process Manag 59(3):102902

    Article  Google Scholar 

  17. Chowdhary K (2020) Natural language processing. Fundam Artif Intell 603–649

  18. Chen J, Gong Z, Wang W, Liu W (2021) HNS: hierarchical negative sampling for network representation learning. Inf Sci 542:343–356

    Article  MathSciNet  MATH  Google Scholar 

  19. Cui P, Wang X, Pei J, Zhu W (2018) A survey on network embedding. IEEE Trans Knowl Data Eng 31(5):833–852

    Article  Google Scholar 

  20. Liu X, Zhuang C, Murata T, Kim K-S, Kertkeidkachorn N (2019) How much topological structure is preserved by graph embeddings? Comput Sci Inf Syst 16(2):597–614

    Article  Google Scholar 

  21. Aiello LM, Barrat A, Schifanella R, Cattuto C, Markines B, Menczer F (2012) Friendship prediction and homophily in social media. ACM Trans Web (TWEB) 6(2):1–33

    Article  Google Scholar 

  22. Zhang F, Sun B, Diao X, Zhao W, Shu T (2021) Prediction of adverse drug reactions based on knowledge graph embedding. BMC Med Inform Decis Mak 21(1):1–11

    Article  Google Scholar 

  23. Leskovec J, Sosič R (2016) Snap: A general-purpose network analysis and graph-mining library. ACM Trans Intell Syst Technol (TIST) 8(1):1–20

    Google Scholar 

  24. Tu C, Yang C, Liu Z, Sun M (2017) Network representation learning: an overview. Scientia sinica informationis 47(8):980–996

    Article  Google Scholar 

  25. Goyal P, Ferrara E (2018) Graph embedding techniques, applications, and performance: a survey. Knowl-Based Syst 151:78–94

    Article  Google Scholar 

  26. Cai H, Zheng VW, Chang KC-C (2018) A comprehensive survey of graph embedding: problems, techniques, and applications. IEEE Trans Knowl Data Eng 30(9):1616–1637

    Article  Google Scholar 

  27. Feng A, You C, Wang S, Tassiulas L (2022) KerGNNs: interpretable graph neural networks with graph kernels. In: Proceedings of the AAAI conference on artificial intelligence, vol 36, pp 6614–6622

  28. Pang Y, Liu C (2022) Efficient-Dyn: dynamic graph representation learning via event-based temporal sparse attention network. arXiv preprint arXiv:2201.01384

  29. Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. J Mach Learn Res 9:249–256

    Google Scholar 

  30. Liao L, He X, Zhang H, Chua T-S (2018) Attributed social network embedding. IEEE Trans Knowl Data Eng 30(12):2257–2270

    Article  Google Scholar 

  31. Tang D, Wei F, Qin B, Yang N, Liu T, Zhou M (2015) Sentiment embeddings with applications to sentiment analysis. IEEE Trans Knowl Data Eng 28(2):496–509

    Article  Google Scholar 

  32. Yu H, Dong W, Shi J (2022) RANEDDI: relation-aware network embedding for drug-drug interaction prediction. Inf Sci 582:167–180

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported by Natural Sciences Foundation of Zhejiang Province under Grant No. LY22F020003, National Natural Science Foundation of China under Grant No. 62002226 and China Postdoctoral Science Foundation under Grant No. 2022M711715.

Author information

Authors and Affiliations

  1. Institute of Artificial Intelligence, Shaoxing University, Shaoxing, 213000, Zhejiang, China

    Qi Li

  2. Guangxi Institute of Digital Technology Co., Ltd., Nanning, 530022, Guangxi, China

    Ming Jiang

Authors
  1. Qi Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ming Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

QL wrote the main manuscript text. All authors reviewed the manuscript.

Corresponding author

Correspondence to Ming Jiang.

Ethics declarations

Conflict of interest

The authors declare no competing interests.

Additional information

Publisher's Note

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

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

Li, Q., Jiang, M. A representation learning model based on stochastic perturbation and homophily constraint. Knowl Inf Syst 65, 5353–5373 (2023). https://doi.org/10.1007/s10115-023-01941-3

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10115-023-01941-3

Keywords

Search

Navigation