Skip to main content
Springer Nature Link
Log in

CANE: community-aware network embedding via adversarial training

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

Abstract

Network embedding aims to learn a low-dimensional representation vector for each node while preserving the inherent structural properties of the network, which could benefit various downstream mining tasks such as link prediction and node classification. Most existing works can be considered as generative models that approximate the underlying node connectivity distribution in the network, or as discriminate models that predict edge existence under a specific discriminative task. Although several recent works try to unify the two types of models with adversarial learning to improve the performance, they only consider the local pairwise connectivity between nodes. Higher-order structural information such as communities, which essentially reflects the global topology structure of the network, is largely ignored. To this end, we propose a novel framework called CANE to simultaneously learn the node representations and identify the network communities. The two tasks are integrated and mutually reinforce each other under a novel adversarial learning framework. Specifically, with the detected communities, CANE jointly minimizes the pairwise connectivity loss and the community assignment error to improve node representation learning. In turn, the learned node representations provide high-quality features to facilitate community detection. Experimental results on multiple real datasets demonstrate that CANE achieves substantial performance gains over state-of-the-art baselines in various applications including link prediction, node classification, recommendation, network visualization, and community detection.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

Notes

  1. https://snap.stanford.edu/data/ca-AstroPh.html.

  2. https://snap.stanford.edu/data/ca-GrQc.html.

  3. http://socialcomputing.asu.edu/datasets/BlogCatalog.

  4. http://www.mattmahoney.net/dc/textdata.

  5. https://grouplens.org/datasets/movielens/100k/.

  6. https://transtats.bts.gov/.

  7. http://socialcomputing.asu.edu/datasets/Twitter.

References

  1. Adamic LA, Lukose RM, Puniyani AR, Huberman BA (2001) Search in power-law networks. Phys Rev E 64:046135

    Article  Google Scholar 

  2. Airoldi EM, Blei DM, Fienberg SE, Xing EP (2008) Mixed membership stochastic blockmodels. J Mach Learn Res 9:1981–2014

    MATH  Google Scholar 

  3. Ban Y, Pu J, Chen Y, Wang Y (2018) Negan: network embedding based on generative adversarial networks. In: IJCNN, pp 1–8

  4. Ball B, Newman EJ (2011) An efficient and principled method for detecting communities in networks. Phys Rev E 84:036103

    Article  Google Scholar 

  5. Bhagat S, Cormode G, Muthukrishnan S (2011) Node classification in social networks. In: Social network data analytics, pp 115–148

  6. Blei DM, Lafferty JD et al (2007) A correlated topic model of science. Ann Appl Stat 1:17–35

    Article  MathSciNet  Google Scholar 

  7. Blei DM, Ng AY, Jordan MI (2003) Latent dirichlet allocation. J Mach Learn Res 3:993–1022

    MATH  Google Scholar 

  8. Bojchevski A, Shchur O, Zügner D, Günnemann S (2018) Netgan: generating graphs via random walks. arXiv:1803.00816

  9. Bosch A, Zisserman A, Muñoz X (2006) Scene classification via PLSA. In: ECCV, pp 517–530

  10. Cai X, Han J, Yang L (2018) Generative adversarial network based heterogeneous bibliographic network representation for personalized citation recommendation. In: AAAI, pp 5747–5754

  11. Cao S, Lu W, Xu Q (2015) Grarep: learning graph representations with global structural information. In: CIKM, pp 891–900

  12. Cao S, Lu W, Xu Q (2016) Deep neural networks for learning graph representations. In: AAAI, pp 1145–1152

  13. Cavallari S, Zheng VW, Cai H, Chang KCC, Cambria E (2017) Learning community embedding with community detection and node embedding on graphs. In: CIKM, pp 377–386

  14. Cha Y, Cho J (2012) Social-network analysis using topic models. In: Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval. ACM, pp 565–574

  15. Chen Z, Li X, Bruna J (2017) Supervised community detection with line graph neural networks

  16. Dai Q, Li Q, Tang J, Wang D (2018) Adversarial network embedding. In: AAAI, pp 1–9

  17. Dai Q, Li Q, Zhang L, Wang D (2019) Ranking network embedding via adversarial learning. In: PAKDD, pp 27–39

  18. Dai Q, Shen X, Zhang L, Li Q, Wang D (2019) Adversarial training methods for network embedding. In: WWW, pp 329–339

  19. De Cao N, Kipf T (2018) Molgan: an implicit generative model for small molecular graphs. arXiv:1805.11973

  20. De Meo P, Ferrara E, Fiumara G, Provetti A (2011) Generalized Louvain method for community detection in large networks. In: ISDA, pp 88–93

  21. Dhillon IS, Guan Y, Kulis B (2004) Kernel k-means: spectral clustering and normalized cuts. In: SIGKDD, pp 551–556

  22. Dong HW, Hsiao WY, Yang LC, Yang YH (2018) Musegan: multi-track sequential generative adversarial networks for symbolic music generation and accompaniment. In: AAAI, pp 34–41

  23. Du B, Peng H, Wang S, Bhuiyan MZA, Wang L, Gong Q, Liu L, Li J (2019) Deep irregular convolutional residual LSTM for urban traffic passenger flows prediction. IEEE Trans Intell Transp Syst 21(3):972–985

    Article  Google Scholar 

  24. Gao H, Pei J, Huang H (2019) Progan: network embedding via proximity generative adversarial network. In: SIGKDD, pp 1308–1316

  25. Griffiths T (2002) Gibbs sampling in the generative model of latent Dirichlet allocation

  26. Griffiths TL, Jordan MI, Tenenbaum JB, Blei DM (2004) Hierarchical topic models and the nested Chinese restaurant process. In: Advances in neural information processing systems, pp 17–24

  27. Griffiths TL, Steyvers M (2004) Finding scientific topics. Proc Nat Acad Sci 101:5228–5235

    Article  Google Scholar 

  28. Grover A, Leskovec J (2016) node2vec: scalable feature learning for networks. In: KDD, pp 855–864

  29. Henderson K, Eliassi-Rad T (2009) Applying latent Dirichlet allocation to group discovery in large graphs. In: SAC, pp 1456–1461

  30. Goodfellow I, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial networks. In: NeurIPS, pp 2672–2680

  31. Jia Y, Zhang Q, Zhang W, Wang X (2019) Communitygan: community detection with generative adversarial nets. In: WWW, pp 784–794

  32. Kanungo T, Mount DM, Netanyahu NS, Piatko CD, Silverman R, Wu AY (2002) An efficient k-means clustering algorithm: analysis and implementation. IEEE Trans Pattern Anal Mach Intell 24(7):881–892

    Article  Google Scholar 

  33. Latouche P, Birmele E, Ambroise C (2012) Variational bayesian inference and complexity control for stochastic block models. Stat Modell 12:93–115

    Article  MathSciNet  Google Scholar 

  34. Li C, Wang S, Yang D, Li Z, Yang Y, Zhang X, Zhou J (2017) PPNE: property preserving network embedding. In: DASFAA, pp 163–179

  35. Li J, Zhu J, Zhang B (2016) Discriminative deep random walk for network classification. In: ACL, pp 1004–1013

  36. Liben-Nowell D, Kleinberg J (2007) The link-prediction problem for social networks. J Am Soc Inform Sci Technol 58:1019–1031

    Article  Google Scholar 

  37. Long B, Xu X, Zhang Z, Philip SY (2007) Community learning by graph approximation. In: ICDM, pp 232–241

  38. Ma T, Chen J, Xiao C (2018) Constrained generation of semantically valid graphs via regularizing variational autoencoders. In: NeurIPS, pp 7113–7124

  39. Maaten L, Hinton G (2008) Visualizing data using T-SNE. J Mach Learn Res 9:2579–2605

    MATH  Google Scholar 

  40. Mimno D, Li W, McCallum A (2007) Mixtures of hierarchical topics with pachinko allocation. In: ICML, pp 633–640

  41. Newman D, Asuncion A, Smyth P, Welling M (2009) Distributed algorithms for topic models. J Mach Learn Res 10:1801–1828

    MathSciNet  MATH  Google Scholar 

  42. Newman ME (2004) Fast algorithm for detecting community structure in networks. Phys Rev E 69:066133

    Article  Google Scholar 

  43. Newman ME (2006) Modularity and community structure in networks. Proc Nat Acad Sci 103:8577–8582

    Article  Google Scholar 

  44. Ng AY, Jordan MI, Weiss Y (2002) On spectral clustering: analysis and an algorithm. In: Advances in neural information processing systems, pp 849–856

  45. Palangi H, Deng L, Shen Y, Gao J, He X, Chen J, Song X, Ward R (2016) Deep sentence embedding using long short-term memory networks: analysis and application to information retrieval. IEEE/ACM Trans Audio Speech Lang Process 24:694–707

    Article  Google Scholar 

  46. Perozzi B, Al-Rfou R, Skiena S (2014) Deepwalk: online learning of social representations. In: SIGKDD, pp 701–710

  47. Radicchi F, Castellano C, Cecconi F, Loreto V, Parisi D (2004) Defining and identifying communities in networks. Proc Nat Acad Sci 101:2658–2663

    Article  Google Scholar 

  48. Ribeiro LF, Saverese PH, Figueiredo DR (2017) struc2vec: learning node representations from structural identity. In: SIGKDD, pp 385–394

  49. Sun FY, Qu M, Hoffmann J, Huang CW, Tang J (2019) vGraph: a generative model for joint community detection and node representation learning. arXiv:1906.07159

  50. Sun Y, Wang S, Hsieh TY, Tang X, Honavar V (2019) Megan: a generative adversarial network for multi-view network embedding. IJCAI

  51. Sutton RS, McAllester D, Singh S, Mansour Y (2000) Policy gradient methods for reinforcement learning with function approximation. In: NeurIPS, pp 1057–1063

  52. Tang H, Shen L, Qi Y, Chen Y, Shu Y, Li J, Clausi DA (2013) A multiscale latent dirichlet allocation model for object-oriented clustering of VHR panchromatic satellite images. IEEE Trans Geosci Remote Sens 51:1680–1692

    Article  Google Scholar 

  53. Tang J, Qu M, Wang M, Zhang M, Yan J, Mei Q (2015) Line: large-scale information network embedding. In: WWW, pp 1067–1077

  54. Tang L, Liu H, Zhang J, Nazeri Z (2008) Community evolution in dynamic multi-mode networks. In: SIGKDD, pp 677–685

  55. Tillé Y, Qualité L, Wilhelm M (2018) Sampling designs on finite populations with spreading control parameters. Stat Sin 28(1):471–504

    MathSciNet  MATH  Google Scholar 

  56. Tu C, Zeng X, Wang H, Zhang Z, Liu Z, Sun M, Zhang B, Lin L (2018) A unified framework for community detection and network representation learning. IEEE Trans Knowl Data Eng 31(6):1051–1065

    Article  Google Scholar 

  57. Van Laarhoven T (2018) Generative models for local network community detection. Phys Rev E 97:042316

    Article  Google Scholar 

  58. Wang D, Cui P, Zhu W (2016) Structural deep network embedding. In: KDD, pp 1225–1234

  59. Wang H, Wang J, Wang J, Zhao M, Zhang W, Zhang F, Xie X, Guo M (2018) Graphgan: graph representation learning with generative adversarial nets. In: AAAI, pp 1–9

  60. Wang S, Hu X, Yu PS, Li Z (2014) Mmrate: inferring multi-aspect diffusion networks with multi-pattern cascades. In: SIGKDD, pp 1246–1255

  61. Wang S, Tang J, Aggarwal C, Liu H (2016) Linked document embedding for classification. In: CIKM, pp 115–124

  62. Wang S, Tang J, Morstatter F, Liu H (2016) Paired restricted Boltzmann machine for linked data. In: CIKM, pp 1753–1762

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

  64. Wolfe J, Haghighi A, Klein D (2008) Fully distributed EM for very large datasets. In: ICML, pp 1184–1191

  65. Xu L, Cao J, Wei X, Yu P (2019) Network embedding via coupled kernelized multi-dimensional array factorization. IEEE Trans Knowl Data Eng. https://doi.org/10.1109/TKDE.2019.2931833

  66. Xu L, Wang J, He L, Cao J, Wei X, Yu P, Yamanishi K (2019) MixSp: a framework for embedding heterogeneous information networks with arbitrary number of node and edge types. IEEE Trans Knowl Data Eng. https://doi.org/10.1109/TKDE.2019.2955945

  67. Xu L, Wei X, Cao J, Yu PS (2017) Embedding of embedding (EOE) joint embedding for coupled heterogeneous networks. In: Proceedings of the tenth ACM international conference on web search and data mining, pp 741–749

  68. Yu W, Zheng C, Cheng W, Aggarwal CC, Song D, Zong B, Chen H, Wang W (2018) Learning deep network representations with adversarially regularized autoencoders. In: SIGKDD, pp 2663–2671

  69. Yu X, Ren X, Sun Y, Gu Q (2014) Personalized entity recommendation: a heterogeneous information network approach. In: SIGKDD, pp 283–292

  70. Zhang H, Qiu B, Giles CL, Foley HC, Yen J (2007) An LDA-based community structure discovery approach for large-scale social networks. In: Intelligence and security informatics, pp 200–207

  71. Zhang Y, Chen M, Huang D, Wu D, Li Y (2017) idoctor: personalized and professionalized medical recommendations based on hybrid matrix factorization. Future Gen Comput Syst 66:30–35

    Article  Google Scholar 

  72. Zhang Y, Lyu T, Zhang Y (2018) Cosine: community-preserving social network embedding from information diffusion cascades. In: AAAI, pp 1–9

  73. Zheng W, Ge B, Wang C (2019) Building a TIN-LDA model for mining microblog users’ interest. IEEE Access 7:21795–21806

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported by Guangdong Key Area R & D Plan (Grant No. 2020B010164002), HK RGC Collaborative Research Fund (RGC No. C5026-18G), and the Fundamental Research Funds for the Central Universities (No. NZ2020014).

Author information

Authors and Affiliations

  1. The Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China

    Jia Wang, Jiannong Cao, Wei Li & Senzhang Wang

  2. School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, Jiangsu, People’s Republic of China

    Wei Li

  3. Jiangsu Key Laboratory of Media Design and Software Technology, Wuxi, Jiangsu, People’s Republic of China

    Wei Li

  4. Nanjing University of Aeronautics and Astronautics, Nanjing, China

    Senzhang Wang

  5. Collaboration Innovation Center of Novel Software Technology and Industrialization, Nanjing, China

    Senzhang Wang

Authors
  1. Jia Wang
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Jiannong Cao
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Wei Li
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Senzhang Wang
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Senzhang Wang.

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

Wang, J., Cao, J., Li, W. et al. CANE: community-aware network embedding via adversarial training. Knowl Inf Syst 63, 411–438 (2021). https://doi.org/10.1007/s10115-020-01521-9

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10115-020-01521-9

Keywords