Abstract
Data imbalance, i.e., some classes may have much fewer samples than others, is a serious problem that can lead to unfavorable node classification. However, most existing GNNs are based on the assumption that node samples for different classes are balanced. In this case, directly training a GNN classifier with raw data would under-represent samples from those minority classes and result in sub-optimal performance. This paper proposes GraphMixup, a novel mixup-based framework for improving class-imbalanced node classification on graphs. However, directly performing mixup in the input space or embedding space may produce out-of-domain samples due to the extreme sparsity of minority classes; hence we construct semantic relation spaces that allow Feature Mixup to be performed at the semantic level. Moreover, we apply two context-based self-supervised techniques to capture both local and global information in the graph structure and specifically propose Edge Mixup to handle graph data. Finally, we develop a Reinforcement Mixup mechanism to adaptively determine how many samples are to be generated by mixup for those minority classes. Extensive experiments on three real-world datasets have shown that GraphMixup yields truly encouraging results for the task of class-imbalanced node classification. Codes are available at: https://github.com/LirongWu/GraphMixup.
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
Similar content being viewed by others
References
Bunkhumpornpat, C., Sinapiromsaran, K., Lursinsap, C.: Safe-Level-SMOTE: safe-level-synthetic minority over-sampling technique for handling the class imbalanced problem. In: Theeramunkong, T., Kijsirikul, B., Cercone, N., Ho, T.-B. (eds.) PAKDD 2009. LNCS (LNAI), vol. 5476, pp. 475–482. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-01307-2_43
Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: Smote: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357 (2002)
Ghorbani, M., Kazi, A., Baghshah, M.S., Rabiee, H.R., Navab, N.: Ra-GCN: graph convolutional network for disease prediction problems with imbalanced data. Med. Image Anal. 75, 102272 (2022)
Hamilton, W., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: Advances in Neural Information Processing Systems, pp. 1024–1034 (2017)
Huang, X., Li, J., Hu, X.: Label informed attributed network embedding. In: Proceedings of the Tenth ACM International Conference on Web Search and Data Mining, pp. 731–739 (2017)
Japkowicz, N., Stephen, S.: The class imbalance problem: a systematic study. Intell. Data Anal. 6(5), 429–449 (2002)
Johnson, J.M., Khoshgoftaar, T.M.: Survey on deep learning with class imbalance. J. Big Data 6(1), 1–54 (2019). https://doi.org/10.1186/s40537-019-0192-5
Karypis, G., Kumar, V.: A fast and high quality multilevel scheme for partitioning irregular graphs. SIAM J. Sci. Comput. 20(1), 359–392 (1998)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)
Kipf, T.N., Welling, M.: Variational graph auto-encoders. arXiv preprint arXiv:1611.07308 (2016)
Leevy, J.L., Khoshgoftaar, T.M., Bauder, R.A., Seliya, N.: A survey on addressing high-class imbalance in big data. J. Big Data 5(1), 1–30 (2018). https://doi.org/10.1186/s40537-018-0151-6
Mernyei, P., Cangea, C.: Wiki-CS: a wikipedia-based benchmark for graph neural networks. arXiv preprint arXiv:2007.02901 (2020)
More, A.: Survey of resampling techniques for improving classification performance in unbalanced datasets. arXiv preprint arXiv:1608.06048 (2016)
Qu, L., Zhu, H., Zheng, R., Shi, Y., Yin, H.: ImGAGN: imbalanced network embedding via generative adversarial graph networks. arXiv preprint arXiv:2106.02817 (2021)
Rout, N., Mishra, D., Mallick, M.K.: Handling imbalanced data: a survey. In: Reddy, M.S., Viswanath, K., K.M., S.P. (eds.) International Proceedings on Advances in Soft Computing, Intelligent Systems and Applications. AISC, vol. 628, pp. 431–443. Springer, Singapore (2018). https://doi.org/10.1007/978-981-10-5272-9_39
Sen, P., Namata, G., Bilgic, M., Getoor, L., Galligher, B., Eliassi-Rad, T.: Collective classification in network data. AI Mag. 29(3), 93 (2008)
Shi, M., Tang, Y., Zhu, X., Wilson, D., Liu, J.: Multi-class imbalanced graph convolutional network learning. In: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (IJCAI-20) (2020)
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)
Watkins, C.J., Dayan, P.: Q-learning. Mach. Learn. 8(3–4), 279–292 (1992)
White, C.C., III., White, D.J.: Markov decision processes. Eur. J. Oper. Res. 39(1), 1–16 (1989)
Wu, L., Lin, H., Gao, Z., Tan, C., Li, S., et al.: Self-supervised on graphs: contrastive, generative, or predictive. arXiv preprint arXiv:2105.07342 (2021)
Wu, L., Lin, H., Xia, J., Tan, C., Li, S.Z.: Multi-level disentanglement graph neural network. Neural Comput. Appl. 34(11), 9087–9101 (2022). https://doi.org/10.1007/s00521-022-06930-1
Wu, L., Yuan, L., Zhao, G., Lin, H., Li, S.Z.: Deep clustering and visualization for end-to-end high-dimensional data analysis. In: IEEE Transactions on Neural Networks and Learning Systems (2022)
Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)
Zhao, T., Zhang, X., Wang, S.: GraphSMOTE: imbalanced node classification on graphs with graph neural networks. In: Proceedings of the 14th ACM International Conference on Web Search and Data Mining, pp. 833–841 (2021)
Acknowledgement
This work is supported by the Science and Technology Innovation 2030 - Major Project (No. 2021ZD0150100) and National Natural Science Foundation of China (No. U21A20427).
Author information
Authors and Affiliations
Corresponding authors
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
Wu, L., Xia, J., Gao, Z., Lin, H., Tan, C., Li, S.Z. (2023). GraphMixup: Improving Class-Imbalanced Node Classification by Reinforcement Mixup and Self-supervised Context Prediction. In: Amini, MR., Canu, S., Fischer, A., Guns, T., Kralj Novak, P., Tsoumakas, G. (eds) Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2022. Lecture Notes in Computer Science(), vol 13716. Springer, Cham. https://doi.org/10.1007/978-3-031-26412-2_32
Download citation
DOI: https://doi.org/10.1007/978-3-031-26412-2_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-26411-5
Online ISBN: 978-3-031-26412-2
eBook Packages: Computer ScienceComputer Science (R0)
