Skip to main content
SpringerLink
Log in

End-to-end variational graph clustering with local structural preservation

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Graph clustering, a basic problem in machine learning and artificial intelligence, facilitates a variety of real-world applications. How to perform a task of graph clustering, with a relatively high-quality optimization decision and an effective yet efficient way to use graph information, to obtain a more excellent assignment for discrete points is not an ordinary challenge that troubles scholars. Often, many preeminent works on graph clustering neglect an essential element that the defined clustering loss may destroy the feature space. This is also a vital factor that leads to unrepresentative nonsense features that generate poor partitioning decisions. Here, we propose an end-to-end variational graph clustering (EVGC) algorithm focusing on preserving the original information of the graph. Specifically, the KL loss with an auxiliary distribution serves as a specific guide to manipulate the embedding space, and consequently disperse data points. A graph auto-encoder plays a propulsive role in maximumly retaining the local structure of the generative distribution of the graph. And each node is represented as a Gaussian distribution in dealing with separating the true embedding position and uncertainty from the graph. Experimental results reveal the importance of preserving local structure, and our EVGC system outperforms state-of-the-art approaches.

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
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Ganguli I, Sil J, Sengupta N (2021) Nonparametric method of topic identification using granularity concept and graph-based modeling. Neural Comput Appl. https://doi.org/10.1007/s00521-020-05662-4

    Article  Google Scholar 

  2. Ma H, Yang H, Zhou K, Zhang L, Zhang X (2020) A local-to-global scheme-based multi-objective evolutionary algorithm for overlapping community detection on large-scale complex networks. Neural Comput Appl. https://doi.org/10.1007/s00521-020-05311-w

    Article  Google Scholar 

  3. Zhou R, Zhang Q, Zhang P, Niu L, Lin X (2021) Anomaly detection in dynamic attributed networks. Neural Comput Appl 33(6):2125–2136. https://doi.org/10.1007/s00521-020-05091-3

    Article  Google Scholar 

  4. Nguyen T-H, Jung JJ (2020) Multiple ACO-based method for solving dynamic MSMD traffic routing problem in connected vehicles. Neural Comput Appl. https://doi.org/10.1007/s00521-020-05402-8

    Article  Google Scholar 

  5. Shah SH, Iqbal MJ, Ahmad I, Khan S, Rodrigues JJPC (2020) Optimized gene selection and classification of cancer from microarray gene expression data using deep learning. Neural Comput Appl. https://doi.org/10.1007/s00521-020-05367-8

    Article  Google Scholar 

  6. Newman MEJ (2006) Finding community structure in networks using the eigenvectors of matrices. Phys Rev E 74(3):036104. https://doi.org/10.1103/PhysRevE.74.036104

    Article  MathSciNet  Google Scholar 

  7. Han Y, Shen Y (2016) Partially supervised graph embedding for positive unlabelled feature selection. In: Proceedings of the international joint conference on artificial intelligence, pp 1548–1554.

  8. Wang X, Jin D, Cao X, Yang L, Zhang W (2016) Semantic community identification in large attribute networks. In: Proceedings of the national conference on artificial intelligence, pp 265–271.

  9. Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: Proceedings of the international conference on learning representations.

  10. Pan S, Hu R, Long G, Jiang J, Yao L, Zhang C (2018) Adversarially regularized graph autoencoder for graph embedding. In: Proceedings of the international joint conference on artificial intelligence, pp 2609–2615. doi:https://doi.org/10.24963/ijcai.2018/362

  11. Kipf TN, Welling M (2016) Variational graph auto-encoders. arXiv: Machine learning

  12. Zhang M, Cui Z, Neumann M, Chen Y (2018) An end-to-end deep learning architecture for graph classification. In: Proceedings of the national conference on artificial intelligence.

  13. Khodayar M, Mohammadi S, Khodayar ME, Wang J, Liu G (2020) Convolutional graph autoencoder: a generative deep neural network for probabilistic spatio-temporal solar irradiance forecasting. IEEE Trans Sustain Energy 11(2):571–583

    Article  Google Scholar 

  14. Xie K, Wei Z, Huang L, Qin Q, Zhang W (2021) Graph convolutional networks with attention for multi-label weather recognition. Neural Comput Appl. https://doi.org/10.1007/s00521-020-05650-8

    Article  Google Scholar 

  15. Tian F, Gao B, Cui Q, Chen E, Liu T (2014) Learning deep representations for graph clustering. In: Proceedings of the national conference on artificial intelligence, pp 1293–1299.

  16. Perozzi B, Alrfou R, Skiena S (2014) DeepWalk: online learning of social representations. In: Proceedings of the international conference on knowledge discovery and data mining, pp 701–710. doi:https://doi.org/10.1145/2623330.2623732

  17. Grover A, Leskovec J (2016) node2vec: scalable feature learning for networks. In: Proceedings of the international conference on knowledge discovery and data mining, pp 855–864. doi:https://doi.org/10.1145/2939672.2939754

  18. Cao S, Lu W, Xu Q (2016) Deep neural networks for learning graph representations. In: Proceedings of the national conference on artificial intelligence, pp 1145–1152.

  19. Ye F, Chen C, Zheng Z (2018) Deep autoencoder-like nonnegative matrix factorization for community detection. In: Proceedings of the conference on information and knowledge management, pp 1393–1402.

  20. Sharma KK, Seal A (2021) Spectral embedded generalized mean based k-nearest neighbors clustering with S-distance. Exp Syst Appl 169:114326. https://doi.org/10.1016/j.eswa.2020.114326

    Article  Google Scholar 

  21. Sharma KK, Seal A, Herrera-Viedma E, Krejcar O (2021) An enhanced spectral clustering algorithm with S-distance. Symmetry 13(6):2125–2136. https://doi.org/10.3390/SYM13040596

    Article  Google Scholar 

  22. Sharma KK, Seal A (2021) Multi-view spectral clustering for uncertain objects. Inform Sci 547:723–745. https://doi.org/10.1016/j.ins.2020.08.080

    Article  MathSciNet  MATH  Google Scholar 

  23. Seal A, Karlekar A, Krejcar O, Herrera-Viedma E (2021) Performance and convergence analysis of modified C-means using jeffreys-divergence for clustering. Int J Interact Multimedia Artif Intell. https://doi.org/10.9781/ijimai.2021.04.009

    Article  Google Scholar 

  24. Sharma KK, Seal A (2019) Modeling uncertain data using Monte Carlo integration method for clustering. Exp Syst Appl 137:100–116. https://doi.org/10.1016/j.eswa.2019.06.050

    Article  Google Scholar 

  25. Chang J, Blei DM (2009) Relational topic models for document networks. In: Proceedings of the international conference on artificial intelligence and statistics, pp 81–88.

  26. Xia R, Pan Y, Du L, Yin J (2014) Robust multi-view spectral clustering via low-rank and sparse decomposition. In: Proceedings of the national conference on artificial intelligence, pp 2149–2155.

  27. Yang C, Liu Z, Zhao D, Sun M, Chang EY (2015) Network representation learning with rich text information. In: Proceedings of the international conference on artificial intelligence, pp 2111–2117.

  28. Salha G, Hennequin R, Vazirgiannis M (2020) Simple and effective graph autoencoders with one-hop linear models. In: Proceedings of the european conference on machine learning, pp 319–334.

  29. Xie J, Girshick R, Farhadi A (2016) Unsupervised deep embedding for clustering analysis. In: Proceedings of the international conference on machine learning, pp 478–487.

  30. Der Maaten LV, Hinton GE (2008) Visualizing data using t-SNE. J Mach Learn Res 9:2579–2605

    MATH  Google Scholar 

  31. Nigam K, Ghani R (2000) Analyzing the effectiveness and applicability of co-training. In: Proceedings of the ninth international conference on information and knowledge management, pp 86–93. doi:https://doi.org/10.1145/354756.354805

  32. Rezende DJ, Mohamed S, Wierstra D (2014) Stochastic backpropagation and approximate inference in deep generative models. In: Proceedings of the international conference on machine learning, pp 1278–1286.

  33. Kingma DP, Welling M (2014) Auto-encoding variational bayes. In: Proceedings of the international conference on learning representations.

  34. Sharma KK, Seal A (2020) Clustering analysis using an adaptive fused distance. Eng Appl Artif Intell 96:103928. https://doi.org/10.1016/j.engappai.2020.103928

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported by the National Key R&D Program of China (Grant Nos. 2018YFC2001600, 2018YFC2001602); and the National Natural Science Foundation of China under Grant no. 61473150.

Author information

Authors and Affiliations

  1. College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, 211106, China

    Lin Guo & Qun Dai

Authors
  1. Lin Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Qun Dai
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Qun Dai.

Ethics declarations

Conflict of interest

The authors declared that they have no conflicts of interest to this work.

Additional information

Publisher's Note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Guo, L., Dai, Q. End-to-end variational graph clustering with local structural preservation. Neural Comput & Applic 34, 3767–3782 (2022). https://doi.org/10.1007/s00521-021-06639-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-021-06639-7

Keywords

Search

Navigation