Abstract
In community detection, clustering method is usually applied. Because graph embedding is not designed for specific community detection tasks, which usually have a poor effect. In this paper, a graph-attention auto-encoder (GATE) is proposed, which uses the attention mechanism to capture the importance of adjacent nodes to the target nodes. For the over-smoothing problem of multi-layer attention network, the deep auto-encoder (DGAE) is integrated into GATE, which can enhance the accuracy of clustering. We also designed a selfsupervised module to train the GATE and DGAE encoding process in a unified framework, jointly optimize the training task, and guide the updating of the whole model. The experimental results on multiple datasets show the superiority of this method for community detection task.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Perozzi, B., Al-Rfou, R., Skiena, S.: Deep Walk: online learning of social Representations, pp. 701–710 (2014)
Tang, J., Qu, M., Wang, M., et al.: Line: Large-scale information network embedding. In: Proceedings of the 24th International Conference on World Wide Web, pp. 1067–1077 (2015)
Kipf, T.N., Welling, M.: Variational graph auto-encoders. arXiv preprint arXiv:1611.07308 (2016)
Wang, D., Cui, P., Zhu, W.: Structural deep network embedding. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1225–1234 (2016)
Zhang, Z., Yang, H., Bu, J., et al.: ANRL: attributed network representation learning via deep neural networks. In: IJCAI, vol. 18, pp. 3155–3161 (2018)
Cao, S., Lu, W., Xu, Q.: Deep neural networks for learning graph representations. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 30, no. 1 (2016)
Xie, J., Girshick, R., Farhadi, A.: Unsupervised deep embedding for clustering analysis. In: International Conference on Machine Learning (2016)
Wang, C., Pan, S., Hu, R., Long, G., Jiang, J., Zhang, C.: Attributed graph clustering: a deep attentional embedding approach. In: International Joint Conference on Artificial Intelligence, pp. 3670–3676 (2019)
Li, X., Zhang, H., Zhang, R.: Embedding graph auto-encoder with joint clustering via adjacency sharing. arXiv:2002.08643 (2020)
Wu, J., Wang, Y., Wu, Z., et al.: Deep k-means: re-training and parameter sharing with harder cluster assignments for compressing deep convolutions. In: International Conference on Machine Learning, pp. 5363–5372. PMLR (2018)
Bo, D., Wang, X., Shi, C., Zhu, M., Lu, E., Cui, P.: Structural deep clustering network. In: The Web Conference (2020)
Blondel, V.D., Guillaume, J.-L., Lambiotte, R., Lefebvre, E.: Fast unfolding of community hierarchies in large networks. J. Stat. Mech. (2008). https://arxiv.org/abs/0803.0476
van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579–2605 (2008)
Hartigan, J.A., Wong, M.A.: Algorithm AS 136: a k-means clustering algorithm. J. Roy. Stat. Soc. Ser. C (Appl. Stati.) 28(1), 100–108 (1979)
Wang, C., Pan, S., Hu, R., Long, G., Jiang, J., Zhang, C.: Attributed graph clustering: a deep attentional embedding approach. In: IJCAI (2019)
Huo, G., Zhang, Y., Gao, J., et al.: CaEGCN: cross-attention fusion based enhanced graph convolutional network for clustering. IEEE Trans. Knowl. Data Eng. 35, 3471–3483 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Lu, Y., Xu, G., Zhang, Q. (2023). Community Detection Based on Graph Attention and Self-supervised Embedding. In: Hong, W., Weng, Y. (eds) Computer Science and Education. ICCSE 2022. Communications in Computer and Information Science, vol 1811. Springer, Singapore. https://doi.org/10.1007/978-981-99-2443-1_52
Download citation
DOI: https://doi.org/10.1007/978-981-99-2443-1_52
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-2442-4
Online ISBN: 978-981-99-2443-1
eBook Packages: Computer ScienceComputer Science (R0)