Abstract
Attributed graph representation has attracted increasing attention recently due to its broad applications such as node classification, link prediction and recommendation. Most existing methods adopt Graph Neural Network (GNN) or its variants to propagate the attributes over the structure network. However, the attribute information will be overshadowed by the structure perspective. To address the limitation and build a link between nodes features and network structure, we aim to learn a holistic representation from two perspectives: topology perspective and feature perspective. To be specific, we separately construct the feature graph and topology graph. Inspired by the network homophily, we argue that there is a deep correlation information between the network structure perspective and the node attributes perspective. Attempting to exploit the potential information between them, we extend our approaches by maximizing the consistency between structural perspective and attribute perspective. In addition, an information fusion module is presented to allow flexible information exchange and integration between the two perspectives. Experimental results on four benchmark datasets demonstrate the effectiveness of our proposed method on graph representation learning, compared with several representative baselines.
This work was supported in part by the 173 program No. 2021-JCJQ-JJ-0029, the Shenzhen General Research Project under Grant JCYJ20190808182805919 and in part by the National Natural Science Foundation of China under Grant 61602013.
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
Notes
- 1.
- 2.
- 3.
- 4.
Cora dataset is available at https://linqs.soe.ucsc.edu/data.
References
Song, Q., Wang, X., Wang, R.: Knowledge network and visual analysis of knowledge graph research. In: ICVRS, pp. 61–66 (2021)
Qiu, J., Tang, J., Ma, H., et al.: DeepINF: social influence prediction with deep learning. In: SIGKDD, pp. 2110–2119 (2018)
Bo, D., Wang, X., Shi, C., et al.: Beyond low-frequency information in graph convolutional networks. In: AAAI (2021)
Ying, R., He, R., Chen, K., et al.: Graph convolutional neural networks for web-scale recommender systems. In: SIGKDD, pp. 974–983 (2018)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: ICLR (2016)
Perozzi, B., Al-Rfou, R., Skiena, S.: Deepwalk: online learning of social representations. In: SIGKDD, pp. 701–710 (2014)
Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. In: ICLR (2017)
Wang, X., Zhu, M., Bo, D., Cui, P., Shi, C., Pei, J.: AM-GCN: adaptive multi-channel graph convolutional networks. In: SIGKDD, pp. 1243–1253 (2020)
Tang, J., Qu, M., Wang, M., et al.: Line: large-scale information network embedding. In: WWW, pp. 1067–1077 (2015)
Defferrard, M., Bresson, X., Vandergheynst, P.: Convolutional neural networks on graphs with fast localized spectral filtering. In: NeruIPS, p. 29 (2016)
Wu, J., He, J., Xu, J.: Net: degree-specific graph neural networks for node and graph classification. In: SIGKDD, pp. 406–415 (2019)
Abu-El-Haija, S., Perozzi, B., Kapoor, A., et al.: Mixhop: higher-order graph convolutional architectures via sparsified neighborhood mixing. In: PLMR, pp. 21–29 (2019)
Zhu, Y., Xu, Y., Yu, F., Liu, Q., Wu, S., Wang, L.: Deep graph contrastive representation learning. In: ICML (2020)
Zhu, Y., Xu, Y., Yu, F., et al.: Graph contrastive learning with adaptive augmentation. In: WWW, pp. 2069–2080 (2021)
Velickovic, P., Fedus, W., Hamilton, W.L., et al.: Deep graph infomax. In: ICLR (2019)
Peng, Z., Huang, W., Luo, M., et al.: Graph representation learning via graphical mutual information maximization. In: WWW, pp. 259–270 (2020)
Hamilton, W., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: NeruIPS, pp. 1024–1034 (2017)
Huang, X., Song, Q., Li, Y., et al.: Graph recurrent networks with attributed random walks. In: SIGKDD, pp. 732–740 (2019)
He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: CVPR, pp. 9726–9735 (2020)
Liu, C., Wen, L., Kang, Z., et al.: Self-supervised consensus representation learning for attributed graph. In: MM, pp. 2654–2662 (2021)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: ICLR (2017)
Vaswani, A., et al.: Attention is all you need. In: NeurIPS, pp. 5998–6008 (2017)
Wang, W., Liu, X., Jiao, P., et al.: A unified weakly supervised framework for community detection and semantic matching. In: PAKDD, pp. 218–230 (2018)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)
Zhu, R., Tao, Z., Li, Y., et al.: Automated graph learning via population based self-tuning GCN. In: SIGKDD, pp. 2096–2100 (2021)
Hassani,K., Khasahmadi,A.H.: Contrastive multi-view representation learning on graphs. In: PMLR (2020)
Wang, X., Ji, H., Shi,C., et al.: Heterogeneous graph attention network. In: WWW, pp. 2022–2032 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Lin, S., Dong, C., Shen, Y. (2022). Cross-perspective Graph Contrastive Learning. In: Memmi, G., Yang, B., Kong, L., Zhang, T., Qiu, M. (eds) Knowledge Science, Engineering and Management. KSEM 2022. Lecture Notes in Computer Science(), vol 13368. Springer, Cham. https://doi.org/10.1007/978-3-031-10983-6_5
Download citation
DOI: https://doi.org/10.1007/978-3-031-10983-6_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-10982-9
Online ISBN: 978-3-031-10983-6
eBook Packages: Computer ScienceComputer Science (R0)