Abstract
Recently, graph contrastive learning has emerged as a successful method for graph representation learning, but it still faces three challenging problems. First, existing contrastive methods cannot preserve the semantics of the graph well after view augmentation. Second, most models use the same encoding method to encode homophilic and heterophilic graphs, failing to obtain better-quality representations. Finally, most models require that the two augmented views have the same set of nodes, which limits flexible augmentation methods. To address the above problems, we propose a novel graph contrastive learning framework with adaptive augmentation and encoding for unaligned views, called GCAUV in this paper. First, we propose multiple node centrality metrics to compute edge centrality for view augmentation, adaptively removing edges with low centrality to preserve the semantics of the graph well. Second, we use a multi-headed graph attention network to encode homophilic graphs, and use MLP to encode heterophilic graphs. Finally, we propose g-EMD distance instead of cosine similarity to measure the distance between positive and negative samples. We also perform adversarial training by adding perturbation to node features to improve the accuracy of GCAUV. Experimental results show that our method outperforms the state-of-the-art graph contrastive methods on node classification tasks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bryan Perozzi, R.A.R., Skiena, S.: DeepWalk: Online learning of social representations. In: Proceedings of KDD, pp. 701–710 (2014)
Fey, M., Lenssen, J.E.: Fast graph representation learning with PyTorch geometric. arXiv e-prints arXiv:1903.02428 (2019)
Grover, A., Leskovec, J.: node2vec: Scalable feature learning for networks. In: Proceedings of KDD, pp. 855–864 (2016)
Hassani, K., Ahmadi, A.H.K.: Contrastive multi-view representation learning on graphs. In: Proceedings of ICML, pp. 4116–4126 (2020)
Jiao, Y., Xiong, Y., Zhang, J., Zhang, Y., Zhang, T.: Sub-graph contrast for scalable self-supervised graph representation learning. In: Proceedings of ICDM (2020)
Kipf, T.N., Welling, M.: Variational graph auto-encoders. arXiv e-prints arXiv:1611.07308 (2016)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: Proceedings of ICLR (2017)
Kong, K., Li, G., Ding, M., Wu, Z., Zhu, C.: Robust optimization as data augmentation for large-scale graphs. arXiv e-prints arXiv:2010.09891 (2020)
Liu, M., Liu, Y.: Inductive representation learning in temporal networks via mining neighborhood and community influences. In: Proceedings of SIGIR (2022)
Liu, M., Quan, Z.W., Wu, J.M., Liu, Y., Han, M.: Embedding temporal networks inductively via mining neighborhood and community influences. In: Applied Intelligence 52 (2022)
Pei, H., Wei, B., Chang, K.C.-C., Lei, Y., Yang, B.: Geom-GCN: geometric graph convolutional networks. arXiv e-prints arXiv:2002.05287 (2020)
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., Bengio, Y.: Graph attention networks. In: Proceedings of ICLR (2018)
Thakoor, S., Tallec, C., Azar, M.G., Munos, R., Veličković, P., Valko, M.: Bootstrapped representation learning on graphs. In: Proceedings of ICLR (2021)
Velickovic, P., Fedus, W., Hamilton, W.L., Liò, P., Bengio, Y., Hjelm, R.D.: Deep graph infomax. In: Proceedings of ICLR (2019)
Wang, H., Zhang, J., Zhu, Q., Huang, W.: Augmentation-free graph contrastive learning with performance guarantee. arXiv e-prints arXiv:2204.04874 (2022)
Xia, J., Wu, L., Chen, J., Hu, B., Li, S.Z.: SimGRACE: a simple framework for graph contrastive learning without data augmentation. In: Proceedings of WWW (2022)
You, Y., Chen, T., Wang, Z., Shen, Y.: Graph contrastive learning with augmentations. In: Proceedings of NIPS, pp. 5812–5823 (2020)
Zhu, Y., Xu, Y., Yu, F., Liu, Q., Wu, S., Wang, L.: Deep graph contrastive representation learning. In: Proceedings of ICML (2020)
Zhu, Y., Xu, Y., Yu, F., Liu, Q., Wu, S., Wang, L.: Graph contrastive learning with adaptive augmentation. In: Proceedings of WWW, pp. 2069–2080 (2021)
Zhu, Y., Guo, J., Wu, F.: Rosa: a robust self-aligned framework for node-node graph contrastive learning. In: Proceedings of IJCAI, pp. 3795–3801 (2022)
Acknowledgements
This work was supported by the National Natural Science Foundation of China (No. 61972135), the Natural Science Foundation of Heilongjiang Province in China (No. LH2020F043).
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
Guo, Y., Liu, Y. (2023). A Graph Contrastive Learning Framework with Adaptive Augmentation and Encoding for Unaligned Views. In: Kashima, H., Ide, T., Peng, WC. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2023. Lecture Notes in Computer Science(), vol 13936. Springer, Cham. https://doi.org/10.1007/978-3-031-33377-4_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-33377-4_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-33376-7
Online ISBN: 978-3-031-33377-4
eBook Packages: Computer ScienceComputer Science (R0)