Abstract
Despite significant advancements in Graph Contrastive Learning (GCL) in recent years, effective and interpretable graph data augmentation methods remain a challenge in the field. Traditional graph augmentation methods typically involve randomly modifying node attributes, edge properties, or extracting subgraphs, with their fundamental principles and operations derived from random processing of image data. However, graph data lacks the Euclidean structure and attribute intuitiveness of image data, making it difficult to ensure that augmentation data retains key features. In this paper, we propose a novel method called Invariant Risk Minimization Augmentation for Graph Contrastive Learning (IRMGCL). IRMGCL incorporates invariant risk minimization loss during the training process to ensure that data augmentation methods preserve invariant features. Specifically, we use different augmentation channels as environmental variables and train these channels to maintain invariant features through different environments. Experiments conducted on citation network datasets Cora and Citeseer demonstrate the effectiveness of our method. We compared our method with state-of-the-art graph contrastive learning methods, showing superior performance. Simultaneously, we conducted ablation experiments to verify the role of each component loss function in IRMGCL. Furthermore, our framework can incorporate labeled data for semi-supervised contrastive learning. Our experiments show that model performance can be further enhanced.
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
Achille, A., Lam, M., Chaudhari, P., Soatto, S.: Out-of-distribution generalization via risk extrapolation. arXiv preprint arXiv:2003.00688 (2020)
Arjovsky, M., Bottou, L., Gulrajani, I., Lopez-Paz, D.: Invariant risk minimization. arXiv preprint arXiv:1907.02893 (2019)
Arora, S., Khodak, M., Parameswaran, K., Ravindran, B.: A simple but tough-to-beat baseline for sentence embeddings. In: International Conference on Learning Representations (ICLR) (2017)
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: Simclr: a simple framework for contrastive learning of visual representations. In: International Conference on Learning Representations (ICLR) (2020)
Chen, X., Fan, B., Vaswani, A., Xiong, C.: Big self-supervised models are strong semi-supervised learners. In: Advances in Neural Information Processing Systems (NeurIPS) (2020)
Gasteiger, R., Liò, P.: Predict then propagate: graph neural networks meet personalized pagerank. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1482–1490 (2018)
Giles, C.L., Bollacker, K.D., Lawrence, S.: Citeseer: an automatic citation indexing system. In: Proceedings of the third ACM conference on Digital libraries, pp. 89–98. ACM (1998)
He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)
Henaff, M., Chen, K., LeCun, Y.: Data-efficient image recognition with contrastive predictive coding. arXiv preprint arXiv:1905.09272 (2020)
Hu, Z., Huang, Z., Wang, F., Zhang, C., Wang, H., Li, B., Cheng, Y.: Mvgrl: Contrastive multi-view representation learning. In: Advances in Neural Information Processing Systems, pp. 335–345 (2020)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: International Conference on Learning Representations (ICLR) (2017)
Liang, J., Li, W., Gao, J., Chen, G., Li, W., Li, Y., Wu, Y.: iGCL: interpretable graph contrastive learning for graph classification. In: Proceedings of the AAAI Conference on Artificial Intelligence (2023)
Liu, F., Li, Z., Zhang, C., Zheng, Z., Cheng, Y.: Infogcl: Contrastive learning with invariance information maximization for graph representation learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 15424–15432 (2021)
McCallum, A.K., Nigam, K., Rennie, J., Seymore, K.: Automating the construction of internet portals with machine learning. Inf. Retrieval 3(2), 127–163 (2000)
Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)
Qi, Y., Ganin, Y., Raghunathan, A., Dai, Z., Schuurmans, D.: Invariant risk minimization ratio. arXiv preprint arXiv:1907.02893 (2019)
Sun, S., Zhang, Z., Ji, S.: Infograph: Unsupervised and semi-supervised graph-level representation learning via mutual information maximization. In: Proceedings of the AAAI Conference on Artificial Intelligence (2019)
Tian, Y., Krishnan, D., Isola, P.: Contrastive multiview coding. In: European Conference on Computer Vision (ECCV) (2020)
Velickovic, P., Fedus, W., Hamilton, W., Liò, P., Bengio, Y., Hjelm, R.D.: Deep graph infomax. In: International Conference on Learning Representations (2019)
Velivckovic, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. In: International Conference on Learning Representations (ICLR) (2018)
Wu, X., Li, P., Zhang, C., Yuan, C., Wang, X., Ma, X., Guo, Y., Gu, Q.: Ma-gcl: Mutual-attention graph contrastive learning for graph classification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 15656–15664 (2021)
Wu, Z., Xiong, Y., Stella, X.L., Socher, R., Ma, L., Huang, W.: Unsupervised feature learning via non-parametric instance discrimination. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
Xu, K., Hu, W., Leskovec, J., Jegelka, S.: How powerful are graph neural networks? In: International Conference on Learning Representations (ICLR) (2019)
Ying, R., You, J., Morris, C., Ren, X., Hamilton, W.L., Leskovec, J.: Hierarchical graph representation learning with differentiable pooling. Adv. Neural Inform. Process. Syst. (NeurIPS) 31 (2018)
You, J., Wu, T.C., Li, Z., Bu, J., Wang, Y.: Graphcl: Contrastive learning of graph representations. Adv. Neural Inform. Process. Syst. (2020)
You, J., Ying, R., Morris, C., Leskovec, J.: Deep graph contrastive representation learning. In: International Conference on Learning Representations (2020)
Zhu, C., Ying, R., Gao, S., Huang, D., Wang, J.: Deep graph contrastive representation learning. Adv. Neural Inform. Process. Syst. 33–44 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2025 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Qin, P., Chen, W. (2025). Invariant Risk Minimization Augmentation for Graph Contrastive Learning. In: Lin, Z., et al. Pattern Recognition and Computer Vision. PRCV 2024. Lecture Notes in Computer Science, vol 15034. Springer, Singapore. https://doi.org/10.1007/978-981-97-8505-6_10
Download citation
DOI: https://doi.org/10.1007/978-981-97-8505-6_10
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-8504-9
Online ISBN: 978-981-97-8505-6
eBook Packages: Computer ScienceComputer Science (R0)