Abstract
With the proliferation of interactive systems, heterogeneous graph clustering has become an important research topic in the field of unsupervised learning. However, the existing methods generally have one or more of the following problems: 1) they fail to fully mine the similarity between nodes in heterogeneous graphs; 2) they cannot effectively deal with heterogeneous graphs without node attribute information; 3) the predicted labels generated during model iterations are not used as guidance information for subsequent iterations. To address the above problems, we propose an Adaptive Heterogeneous graph Contrastive clustering with Multi-Similarity (AHCMS) model. The model adaptively learns a high-level representation containing specific semantic information through a feature extraction module and an attention mechanism. Secondly, the feature enhancement module is used to extract the consistency information between different meta-paths from two aspects of attribute information and topology structure, so as to encourage the adjacent nodes of different meta-paths to be as similar as possible and reduce the dependence on the attribute information. Moreover, the topological similarity contained in the semantic information is fully explored in the high-order proximity module, making the high-level representation more discriminative. In addition, AHCMS also introduces a self-supervised clustering mechanism to guide the high-level representation to become clustering task-oriented representations. Extensive experimental results on four heterogeneous datasets show that the model’s clustering performance consistently outperforms most baseline methods.
Supported by the National Natural Science Foundation of China (62062066, 61762090, 61966036 and 62276227), Yunnan Fundamental Research Projects (202201AS070015), Yunnan Key Laboratory of Intelligent Systems and Computing (202205AG070003), Program for Young and Middle-aged Academic and Technical Reserve Leaders of Yunnan Province (202205AC160033).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chen, Z., Luo, L., Li, X., Jiang, B., Guo, Q., Wang, C.: Siamese network based multiscale self-supervised heterogeneous graph representation learning. IEEE Access 10, 98490–98500 (2022)
Cheng, J., Wang, Q., Tao, Z., Xie, D., Gao, Q.: Multi-view attribute graph convolution networks for clustering. In: Proceedings of The Twenty-ninth International Conference on International Joint Conferences on Artificial Intelligence, pp. 2973–2979 (2021)
Du, G., Zhou, L., Li, Z., Wang, L., Lü, K.: Neighbor-aware deep multi-view clustering via graph convolutional network. Inform. Fusion 93, 330–343 (2023)
Du, G., Zhou, L., Yang, Y., Lü, K., Wang, L.: Deep multiple auto-encoder-based multi-view clustering. Data Sci. Eng. 6(3), 323–338 (2021)
Ezugwu, A.E., et al.: A comprehensive survey of clustering algorithms: State-of-the-art machine learning applications, taxonomy, challenges, and future research prospects. Eng. Appl. Artif. Intell. 110, 104743 (2022)
Fan, S., Wang, X., Shi, C., Lu, E., Lin, K., Wang, B.: One2multi graph autoencoder for multi-view graph clustering. In: Proceedings of the Web Conference 2020, pp. 3070–3076 (2020)
Fettal, C., Labiod, L., Nadif, M.: Efficient graph convolution for joint node representation learning and clustering. In: Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining, pp. 289–297 (2022)
Hartigan, J.A., Wong, M.A., et al.: A k-means clustering algorithm. Appl. Stat. 28(1), 100–108 (1979)
Hassani, K., Khasahmadi, A.H.: Contrastive multi-view representation learning on graphs. In: International Conference on Machine Learning, pp. 4116–4126. PMLR (2020)
Hwang, D., Park, J., Kwon, S., Kim, K., Ha, J.W., Kim, H.J.: Self-supervised auxiliary learning with meta-paths for heterogeneous graphs. Adv. Neural. Inf. Process. Syst. 33, 10294–10305 (2020)
Jin, D., Huo, C., Liang, C., Yang, L.: Heterogeneous graph neural network via attribute completion. In: Proceedings of the Web Conference 2021, pp. 391–400 (2021)
Jing, B., Park, C., Tong, H.: Hdmi: High-order deep multiplex infomax. In: Proceedings of the Web Conference 2021, pp. 2414–2424 (2021)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)
Lee, N., Lee, J., Park, C.: Augmentation-free self-supervised learning on graphs. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 7372–7380 (2022)
Lin, Z., Kang, Z.: Graph filter-based multi-view attributed graph clustering. In: IJCAI, pp. 2723–2729 (2021)
Liu, Y., Zhou, S., Liu, X., Tu, W., Yang, X.: Improved dual correlation reduction network. arXiv preprint arXiv:2202.12533 (2022)
Ma, S., Liu, J.w., Zuo, X.: Self-supervised learning for heterogeneous graph via structure information based on metapath. arXiv preprint arXiv:2209.04218 (2022)
Van der Maaten, L., Hinton, G.: Visualizing data using t-sne. J. Mach. Learn. Res. 9, 2579–2605 (2008)
Park, C., Han, J., Yu, H.: Deep multiplex graph infomax: attentive multiplex network embedding using global information. Knowl.-Based Syst. 197, 105861 (2020)
Ren, Y., Liu, B., Huang, C., Dai, P., Bo, L., Zhang, J.: Heterogeneous deep graph infomax. arXiv preprint arXiv:1911.08538 (2019)
Sun, K., Lin, Z., Zhu, Z.: Multi-stage self-supervised learning for graph convolutional networks on graphs with few labeled nodes. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 5892–5899 (2020)
Sun, M., Xing, J., Wang, H., Chen, B., Zhou, J.: Mocl: contrastive learning on molecular graphs with multi-level domain knowledge. arXiv preprint arXiv:2106.04509 (2021)
Sun, Y., Han, J., Yan, X., Yu, P.S., Wu, T.: Heterogeneous information networks: the past, the present, and the future. Proc. VLDB Endow. 15(12), 3807–3811 (2022)
Veličković, P., Fedus, W., Hamilton, W.L., Liò, P., Bengio, Y., Hjelm, R.D.: Deep graph infomax. arXiv preprint arXiv:1809.10341 (2018)
Wang, X., et al.: Heterogeneous graph attention network. In: The World Wide Web Conference, pp. 2022–2032 (2019)
Wang, X., Liu, N., Han, H., Shi, C.: Self-supervised heterogeneous graph neural network with co-contrastive learning. In: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pp. 1726–1736 (2021)
Wang, Y., Sun, W., Xu, K., Zhu, Z., Chen, L., Zheng, Z.: Fastgcl: Fast self-supervised learning on graphs via contrastive neighborhood aggregation. arXiv preprint arXiv:2205.00905 (2022)
Xia, W., Wang, S., Yang, M., Gao, Q., Han, J., Gao, X.: Multi-view graph embedding clustering network: Joint self-supervision and block diagonal representation. Neural Netw. 145, 1–9 (2022)
Xu, W., Xia, Y., Liu, W., Bian, J., Yin, J., Liu, T.Y.: Shgnn: structure-aware heterogeneous graph neural network. arXiv preprint arXiv:2112.06244 (2021)
Zhou, L., Wang, J., Wang, L., Chen, H., Kong, B.: Heterogeneous information network representation learning: a survey. Chin. J. Comput. 45(1), 160–189 (2022)
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 Switzerland AG
About this paper
Cite this paper
Liu, C., Kong, B., Yu, Y., Zhou, L., Chen, H. (2023). Adaptive Heterogeneous Graph Contrastive Clustering with Multi-similarity. In: Yang, X., et al. Advanced Data Mining and Applications. ADMA 2023. Lecture Notes in Computer Science(), vol 14179. Springer, Cham. https://doi.org/10.1007/978-3-031-46674-8_34
Download citation
DOI: https://doi.org/10.1007/978-3-031-46674-8_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-46673-1
Online ISBN: 978-3-031-46674-8
eBook Packages: Computer ScienceComputer Science (R0)