Abstract
Attributed community detection is a challenging task as it requires joint modelling of graph structure and node attributes. Recent progress on graph neural network (GNN) has proved that it is effective in combining structural and content information, and several GNN-based methods have achieved promising clustering performance on real-world attributed network. Most of the existing community detection methods adopt non-clustering-oriented representation learning methods, which is incapable of capturing interaction between embedding and clustering, thus resulting in suboptimal outcome. In this paper, we propose a novel Hierarchical Attention Network (HiAN) solution for attributed community detection, and unique hierarchical attention network may significantly change the community detection paradigm. In order to fuse rich interpretable interactive information, the hierarchical attentive aggregator in HiAN is designed to learn node representation at both attribute-and structure-spaces. More importantly, the self-training process is jointly learned and optimized with embedding representation in a unified community detection framework, to mutually benefit both components. The experimental results demonstrate that HiAN outperforms several state-of-the-art baselines on four real-world datasets.
Similar content being viewed by others
References
Bo D, Wang X, Shi C et al (2020) Structural deep clustering network. Proceedings of the web conference, vol 2020, pp 1400–1410
Cai X, Huang D, Wang CD et al (2020) Spectral clustering by subspace randomization and graph fusion for high-dimensional data. Adv Knowl Disc Data Min 12084:330
Cavallari S, Zheng VW, Cai H et al (2017) Learning community embedding with community detection and node embedding on graphs. Proceedings of the 2017 ACM on conference on information and knowledge management, pp 377–386
Chen H, Yu Z, Yang Q et al (2020) Attributed graph clustering with subspace stochastic block model. Inf Sci 535:130–141
Comito C (2020) NexT: A framework for next-place prediction on location based social networks. Knowl Based Syst 204:106205
Fan S, Wang X, Shi C et al (2020) One2multi graph autoencoder for multi-view graph clustering. Proceedings of the web conference 2020. pp 3070–3076
Gao H, Huang H (2018) Deep attributed network embedding. Twenty-seventh international joint conference on artificial intelligence (IJCAI)). 2018
Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 2010, pp 249–256
Hatcher WG, Yu W (2018) A survey of deep learning: Platforms, applications and emerging research trends. IEEE Access 6:24411–24432
Huang X, Li J, Hu X. Accelerated attributed network embedding. In: Proceedings of the 2017 SIAM international conference on data mining. Society for Industrial and Applied Mathematics, 2017: 633–641
Zachary WW (1977) An information flow model for conflict and fission in small groups. J Anthropol Res 33(4):452–473
Kim B, Khanna R, Koyejo OO (2016) Examples are not enough, learn to criticize! criticism for interpretability. Adv Neural Inf Process Syst 29
Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. In: 3rd international conference on learning representations, ICLR 2015, San Diego, CA, USA, May 7–9, 2015
Liao L, He X, Zhang H et al (2018) Attributed social network embedding. IEEE Trans Knowl Data Eng 30(12):2257–2270
Liu F, Xue S, Wu J, Zhou C, Hu W, Paris C, Nepal S, Yang J, Philip S. Deep learning for community detection: progress, challenges and opportunities. In: Proceedings of the twenty-ninth international joint conference on artificial intelligence, IJCAI 2020, pp 4981–4987
Liu L, Xu L, Wangy Z et al (2015) Community detection based on structure and content: a content propagation perspective. 2015 IEEE international conference on data mining. IEEE, pp 271–280
Luo D, Ni J, Wang S et al (2020) Deep multi-graph clustering via attentive cross-graph association. Proceedings of the 13th international conference on web search and data mining, pp 393–401
Mehta N, Duke LC, Rai P (2019) Stochastic blockmodels meet graph neural networks. International conference on machine learning. PMLR, pp 4466–4474
Newman Mark EJ (2010) Networks: an introduction. Oxford University Press, Oxford
Newman MEJ, Clauset A (2016) Structure and inference in annotated networks. Nat Commun 7(1):1–11
Peng S, Yang A, Cao L et al (2017) Social influence modeling using information theory in mobile social networks. Inf Sci 379:146–159
Perozzi B, Akoglu L (2016) Scalable anomaly ranking of attributed neighborhoods. In: Proceedings of the 2016 SIAM international conference on data mining. Society for Industrial and Applied Mathematics, pp 207–215
Qiao M, Yu J, Bian W et al (2018) Adapting stochastic block models to power-law degree distributions. IEEE Trans Cybern 49(2):626–637
Shalizi CR, Thomas AC (2011) Homophily and contagion are generically confounded in observational social network studies. Sociol Methods Res 40(2):211–239
Stanley N, Bonacci T, Kwitt R et al (2019) Stochastic block models with multiple continuous attributes. Appl Netw Sci 4(1):1–22
Tian F, Gao B, Cui Q et al (2014) Learning deep representations for graph clustering. In: Proceedings of the AAAI conference on artificial intelligence, 28(1)
Wang C, Pan S, Hu R, Long G, Jiang J, Zhang C (2019) Attributed graph clustering: a deep attentional embedding approach. In: proceedings of the twenty-eighth international joint conference on artificial intelligence, IJCAI 2019, Macao, China, August 10–16, 2019, pp 3670–3676
Wang X, Ji H, Shi C et al (2019) Heterogeneous graph attention network. The World Wide Web conference, pp 2022–2032
Whang JJ, Hou Y, Gleich DF et al (2018) Non-exhaustive, overlapping clustering. IEEE Trans Pattern Anal Mach Intell 41(11):2644–2659
Wu Z, Pan S, Chen F et al (2020) A comprehensive survey on graph neural networks. IEEE Trans Neural Netw Learn Syst 32(1):4–24
Xie J, Girshick R, Farhadi A (2016) Unsupervised deep embedding for clustering analysis. International conference on machine learning. PMLR, pp 478–487
Yang J, McAuley J, Leskovec J (2013) Community detection in networks with node attributes. 2013 IEEE 13th international conference on data mining. IEEE, pp 1151–1156
You X, Ma Y, Liu Z (2020) A three-stage algorithm on community detection in social networks. Knowl Based Syst 187:104822
Zhang H, Wang S, Xu X et al (2018) Tree2Vector: learning a vectorial representation for tree-structured data. IEEE Trans Neural Netw Learn Syst 29(11):5304–5318
Zhang XL (2018) Multilayer bootstrap networks. Neural Netw 103:29–43
Zhang Y, Lyu T, Zhang Y (2018) Cosine: community-preserving social network embedding from information diffusion cascades. Proceedings of the AAAI conference on artificial intelligence, 32(1)
Zhang Z, Cui P, Zhu W (2020) Deep learning on graphs: a survey. IEEE Trans Knowl Data Eng
Zhe C, Sun A, Xiao X (2019) Community detection on large complex attribute network. Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, pp 2041–2049
Acknowledgements
This work is supported by the National Natural Science Foundation of China (61762078, 61363058, 61966004), Natural Science Foundation of Gansu Province(21JR7RA114), Northwest Normal University young teachers research capacity promotion plan (NWN-ULKQN2019-2) and Research Fund of Guangxi Key Laboratory of Trusted Software (kx202003).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
We declare that we have no financial and personal relationships with other people or organizations that can inappropriately influence our work. There is no professional or other personal interest of any nature or kind in any product, service and/or company that could be construed as influencing the position presented in, or the review of, the manuscript entitled.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zhao, Q., Ma, H., Guo, L. et al. Hierarchical attention network for attributed community detection of joint representation. Neural Comput & Applic 34, 5587–5601 (2022). https://doi.org/10.1007/s00521-021-06723-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-021-06723-y