Abstract
The purpose of community detection is to discover closely connected groups of entities in complex networks such as interest groups, proteins and vehicles in social, biological and transportation networks. Recently, autoencoders have become a popular technique to extract nonlinear relationships between nodes by learning their representation vectors through an encoder-decoder neural structure, which is beneficial to discovering communities with vague boundaries. However, most of the existing autoencoders take restoring a network’s adjacency matrix as their objective, which puts emphasis on the first-order relationships between the nodes and neglects their higher-order relationships that may be more useful for community detection. In this paper, we propose a novel attentional-walk-based autoencoder (AWBA) which integrates random walk considering attentional coefficients between each pair of nodes into the encoder to mine their high-order relationships. First, the attention layers are added to the encoder to learn the influence of a node’s different neighbors on it in encoding. Second, we develop a new random walk strategy that embeds the attention coefficients and the community membership of the nodes obtained by a seed-expansion-based clustering algorithm into the computation of the transition probability matrix to instill both low and high order relationships between the nodes into the representation vectors. The experimental results on synthetic and real-world networks verify the superiority of our algorithm over the baseline algorithms.
Similar content being viewed by others
Notes
The source code of AWBA, the competitor algorithms, the LFR tool and the evaluation metrics are available at https://anonymous.4open.science/r/awba-0C48.
The networks were put at https://anonymous.4open.science/r/community-detection-datasets-5D1F.
The source code of AWBA, the competitor algorithms, the LFR tool and the evaluation metrics are available at https://anonymous.4open.science/r/awba-0C48.
References
Fortunato S. (2010) Community detection in graphs[J]. Phys Rep 486(3-5):75–174
Newman M E J (2004) Fast algorithm for detecting community structure in networks[J]. Phys Rev E, 69(6):066133
Barber M J, Clark J W (2009) Detecting network communities by propagating labels under constraints[J]. Phys Rev E, 80(2):026129
Khan B S, Niazi M A (2017) Network community detection: A review and visual survey[J]. arXiv:1708.00977
Palla G, Derényi I, Farkas I, et al. (2005) Uncovering the overlapping community structure of complex networks in nature and society[J]. Nature 435(7043):814–818
Lancichinetti A, Fortunato S, Kertész J (2009) Detecting the overlapping and hierarchical community structure in complex networks[J]. J Phys 11(3):033015
Evans T S, Lambiotte R (2009) Line graphs, link partitions, and overlapping communities[J]. Phys Rev E, 80(1):016105
Lloyd S. (1982) Least squares quantization in PCM [J]. IEEE Trans Inf Theory 28(2):129–137
Yang Z, Ding M, Zhou C, et al. (2020) Understanding negative sampling in graph representation learning[C]//Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp 1666–1676
Perozzi B, Al-Rfou R, Skiena S (2014) Deepwalk: Online learning of social representations[C]//Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining, pp 701–710
Mikolov T, Sutskever I, Chen K, et al. (2013) Distributed representations of words and phrases and their compositionality[C]//Advances in neural information processing systems, pp 3111–3119
Kipf T N, Welling M. (2016) Semi-supervised classification with graph convolutional networks[J]. arXiv:1609.02907
Tu C, Zeng X, Wang H, et al. (2018) A unified framework for community detection and network representation learning [J]. IEEE Trans Knowl Data Eng 31(6):1051–1065
Huang X, Song Q, Yang F, et al. (2019) Large-scale heterogeneous feature embedding[C]. Proc AAAI Conf Artif Intell 33(01):3878–3885
Li G, Muller M, Thabet A, et al. (2019) Deepgcns: Can gcns go as deep as cnns. [C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, pp 9267–9276
Li G, Xiong C, Thabet A, et al. (2020) Deepergcn: All you need to train deeper gcns[J]. arXiv:2006.07739
Cai C, Wang Y. (2020) A note on over-smoothing for graph neural networks[J]. arXiv:2006.13318
Veličković P, Cucurull G, Casanova A, et al. (2017) Graph attention networks[J]. arXiv:1710.10903
Abu-El-Haija S, Perozzi B, Al-Rfou R, et al. (2017) Watch your step: Learning node embeddings via graph attention[J]. arXiv:1710.09599
Grover A, Leskovec J (2016) node2vec: Scalable feature learning for networks[C]//Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining, pp 855–864
Tang J, Qu M, Wang M, et al. (2015) Line: Large-scale information network embedding[C]//Proceedings of the 24th international conference on world wide web. 1067–1077
Zhang D, Yin J, Zhu X, et al. (2019) Attributed network embedding via subspace discovery[J]. Data Min Knowl Disc 33(6):1953–1980
Bandyopadhyay S, Biswas A, Kara H, et al. (2020) A multilayered informative random walk for attributed social network embedding[M]//ECAI 2020. IOS Press:1738–1745
Hamilton W L, Ying R, Leskovec J (2017) Inductive representation learning on large graphs[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems, pp 1025–1035
Xu K, Hu W, Leskovec J, et al. (2018) How powerful are graph neural networks?[J]. arXiv:1810.00826
You J, Ying R, Leskovec J. (2019) Position-aware graph neural networks [C]//International Conference on Machine Learning. PMLR, pp 7134–7143
Kingma D P, Welling M. (2013) Auto-encoding variational bayes[J]. arXiv:1312.6114
Kipf T N, Welling M. (2016) Variational graph auto-encoders[J]. arXiv:1611.07308
Pan S, Hu R, Long G, et al. (2018) Adversarially regularized graph autoencoder for graph embedding[J]. arXiv:1802.04407
Wang C, Pan S, Long G, et al. (2017) Mgae: Marginalized graph autoencoder for graph clustering[C]//Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, pp 889–898
Park J, Lee M, Chang HJ, et al. (2019) Symmetric graph convolutional autoencoder for unsupervised graph representation learning[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, pp 6519–6528
Cui G, Zhou J, Yang C (2020) Adaptive graph encoder for attributed graph embedding[C]//Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp 976–985
Cavallari S, Zheng V W, Cai H, et al. (2017) Learning community embedding with community detection and node embedding on graphs[C]//Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, pp 377–386
Rozemberczki B, Davies R, Sarkar R, et al. (2019) Gemsec: Graph embedding with self clustering[C]//Proceedings of the 2019 IEEE/ACM international conference on advances in social networks analysis and mining, pp 65–72
Sun F Y, Qu M, Hoffmann J, et al. (2019) vgraph: A generative model for joint community detection and node representation learning[J]. arXiv:1906.07159
Jia Y, Zhang Q, Zhang W, et al. (2019) Communitygan: Community detection with generative adversarial nets[C]//The World Wide Web Conference, pp 784–794
Sun H, He F, Huang J, et al. (2020) Network embedding for community detection in attributed networks [J]. ACM Trans Knowl Discov Data (TKDD) 14(3):1–25
Lancichinetti A, Fortunato S, Radicchi F (2008) Benchmark graphs for testing community detection algorithms[J]. Phys Rev E 78(4):046110
Zachary W. W. (1977) An information flow model for conflict and fission in small groups [J]. J Anthropol Res 33(4):452–473
Lusseau D, Schneider K, Boisseau O J, et al. (2003) The bottlenose dolphin community of Doubtful Sound features a large proportion of long-lasting associations [J]. Behav Ecol Sociobiol 54(4):396–405
Girvan M, Newman M. E. J. (2002) Community structure in social and biological networks [J]. Proc Ntl Acad Sci 99(12):7821–7826
Newman M E J, Girvan M (2004) Finding and evaluating community structure in networks[J]. Phys Rev E 69(2):026113
Adamic L A, Glance N (2005) The political blogosphere and the 2004 US election: divided they blog[C]//Proceedings of the 3rd international workshop on Link discovery, pp 36–43
McCallum A K, Nigam K, Rennie J, et al. (2000) Automating the construction of internet portals with machine learning [J]. Inf Retr 3(2):127–163
Yang C, Liu Z, Zhao D, et al. (2015) Network representation learning with rich text information [C]//Twenty-fourth international joint conference on artificial intelligence
Tang L, Liu H (2009) Relational learning via latent social dimensions[C]//Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining, pp 817–826
Danon L, Diaz-Guilera A, Duch J, et al. (2005) Comparing community structure identification [J]. J Stat Mech Theory Exper 2005(09):P09008
Tian F, Gao B, Cui Q et al (2014) Learning deep representations for graph clustering[C]//Proceedings of the AAAI Conf Artif Intell 28(1)
Van der Maaten L, Hinton G (2008) Visualizing data using t-SNE[J]. J Mach Learn Res 9(11)
Yang L, Cao X, He D, et al. (2016) Modularity Based Community Detection with Deep Learning[C]. IJCAI 16:2252–2258
He D, Feng Z, Jin D, et al. (2017) Joint identification of network communities and semantics via integrative modeling of network topologies and node contents [C]//Thirty-First AAAI Conference on Artificial Intelligence
Jin D, Wang X, He R et al (2018) Robust detection of link communities in large social networks by exploiting link semantics[C]//Proc AAAI Conf Artif Intell 32(1)
Qin M, Jin D, Lei K, et al. (2018) Adaptive community detection incorporating topology and content in social networks [J]. Knowl-based Syst 161:342–356
Li Y, Sha C, Huang X et al (2018) Community detection in attributed graphs: An embedding approach[C]//Thirty-second AAAI conference on artificial intelligence
Qin M, Lei K. (2021) Dual-channel hybrid community detection in attributed networks[J]. Inf Sci 551:146–167
Li W, Qin M, Lei K (2019) Identifying Interpretable Link Communities with User Interactions and Messages in Social Networks[C]//2019 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom). IEEE, pp 271–278
Ye F, Chen C, Zheng Z (2018) Deep autoencoder-like nonnegative matrix factorization for community detection[C]//Proceedings of the 27th ACM international conference on information and knowledge management, pp 1393–1402
Mehta N, Duke L C, Rai P. (2019) Stochastic blockmodels meet graph neural networks[C]//International Conference on Machine Learning. PMLR, pp 4466–4474
Blondel V D, Guillaume J L, Lambiotte R, et al. (2008) Fast unfolding of communities in large networks[J]. J Stat Mech Theory Exper 2008(10):P10008
Xie J, Szymanski B K, Liu X. (2011) Slpa: Uncovering overlapping communities in social networks via a speaker-listener interaction dynamic process[C]//2011 ieee 11th international conference on data mining workshops. IEEE, pp 344–349
Qian F, et al., Huang X, Zhao S (2019) Path-based mutual attention algorithm for network embedding[J] Journal of Nanjing University(Natural Science)
GUO J, DONG H, ZHANG T, et al. (2020) Representation learning for topic-attention network[J]. J Comput Appl 40(2):441–447
Moscato V, Picariello A, Sperlí G (2019) Community detection based on game theory[J]. Eng Appl Artif Intell 85:773–782
Author information
Authors and Affiliations
Corresponding author
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 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.
About this article
Cite this article
Guo, K., Zhang, P., Guo, W. et al. An attentional-walk-based autoencoder for community detection. Appl Intell 53, 11505–11523 (2023). https://doi.org/10.1007/s10489-021-02957-4
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-021-02957-4