Abstract
Learning low-dimensional representations of graphs is crucial for network analysis and various downstream tasks. Existing methods typically assume that only single type of relation between nodes, but, graphs often contain multiple relationship types. While recent researches have attempted to consider the multiple relations in graph, they ignore the problem of topological redundancy. This paper proposes a simple yet effective method called Attributed Multi-relational Graph embedding based on GCN (AMGGCN), which aims to solve the problem of topological redundancy and information aggregation in each relation. Specifically, AMGGCN enhances the effectiveness of node embedding by differential operations, and can learn the weights of different relations adaptively by fusing information in multiple relations using an attention mechanism. The effectiveness of AMGGCN is evaluated on two downstream tasks, unsupervised clustering and supervised classification. The experimental results show that our approach achieves state-of-the-art performance.
Z. Xie and M. Wu—Co-first authors.
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
References
Su, X., Xue, S., Liu, F.Z., et al.: A comprehensive survey on community detection with deep learning. In IEEE Transactions on Neural Networks and Learning Systems (2022)
Maaten, L., Geoffrey, H.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579–2605 (2008)
Muhammad, F.N., Xian, Y.Q., Akatal, Z.: Learning graph embeddings for compositional zero-shot learning. In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 953–962 (2021)
Wang, T., Yang, G., Wu, J., et al.: Dual Contrastive Attributed Graph Clustering Network. arXiv preprint arXiv:2206.07897 (2022)
Tang, J., Qu, M., Wang, M., et al.: Line: Large-scale information network embedding. Proceedings of the 24th international conference on world wide web,1067–1077 (2015)
Perozzi, B., Al-Rfou, R., Skiena, S.: Deepwalk: Online learning of social representations. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 701–710 (2014)
Velickovic, P., Fedus, W., Hamilton, W.L., et al.: Deep graph infomax. Int. Conf. Learn. Represent. 2(3), 4 (2019)
Gao, H., Huang, H.: Deep attributed network embedding. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence, pp. 3364–3370 (2018)
Grover, A., Leskovec, J.: Node2vec: scalable feature learning for networks. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 855–864 (2016)
Yang, C., Liu, Z., Zhao, D., et al.: Network representation learning with rich text information. In: Twenty-Fourth International Joint Conference on Artificial Intelligence (2015)
Kipf, T.N., Welling, M.:Semi-supervised classification with graph convolutional networks. In: 5th International Conference on Learning Representations (2017)
Veličković, P., Cucurull, G., Casanova, A., et al.: Graph attention networks. In: 6th International Conference on Learning Representations (2018)
Ma, Y., Wang, S., Aggarwal, C.C., Yin, D., Tang, J.: Multi-dimensional graph convolutional networks. In: BergerWolf, T., Chawla, N. (eds.) Proceedings of the 2019 SIAM international conference on data mining, pp. 657–665. Society for Industrial and Applied Mathematics, Philadelphia, PA (2019). https://doi.org/10.1137/1.9781611975673.74
Park, C., Kim, D., Han, J., Yu, H.: Unsupervised attributed multiplex network embedding. Proc. AAAI Conf. Artif. Intell. 34(04), 5371–5378 (2020). https://doi.org/10.1609/aaai.v34i04.5985
Jing, B., Park, C., Tong, H.: HDMI: high-order deep multiplex infomax. Proc. Web Conf. 2021, 2414–2424 (2021)
Ma, Y., Ren, Z.C., Jiang, Z.H., et al.: Multi-dimensional network embedding with hierarchical structure. In: Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining, pp. 387–395 (2018)
Wang, X., Ji, H., Shi, C., et al.: Heterogeneous graph attention network. In: The World Wide Web Conference, pp. 2022–2032 (2019)
Hartigan, J.A., Wong, M.A.: Algorithm AS 136: A k-means clustering algorithm. Appl. Statist. 28(1), 100 (1979). https://doi.org/10.2307/2346830
Ng, A., Jordan, M., Weiss, Y.: On spectral clustering: analysis and an algorithm. In: Advances in Neural Information Processing Systems, p. 14 (2001)
Ester, M., Kriegel, H.P., Sander, J., et al.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: Proceedings of the Second International Conference on Knowledge Discovery and Data Mining, pp. 226–231 (1996)
Acknowledgement
This paper was supported by the National Natural Science Foundation of China (Grant No. 62006211).
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
Xie, Z., Wu, M., Zhao, G., Zhou, L., Gong, Z., Zhang, Z. (2023). Attributed Multi-relational Graph Embedding Based on GCN. In: Huang, DS., Premaratne, P., Jin, B., Qu, B., Jo, KH., Hussain, A. (eds) Advanced Intelligent Computing Technology and Applications. ICIC 2023. Lecture Notes in Computer Science, vol 14087. Springer, Singapore. https://doi.org/10.1007/978-981-99-4742-3_14
Download citation
DOI: https://doi.org/10.1007/978-981-99-4742-3_14
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-4741-6
Online ISBN: 978-981-99-4742-3
eBook Packages: Computer ScienceComputer Science (R0)