Abstract
Graph Neural Networks (GNNs) have achieved promising performance for semi-supervised graph learning. However, the training of GNNs usually heavily relies on a large number of labeled nodes in a graph. When the labeled data are scarce, GNNs easily over-fit rto the few labeled samples, resulting in the degenerating performance. To address this issue, we propose a novel graph pseudo-labeling framework. The proposed framework combines both the predication confidence and approximate Bayesian uncertainty of GNNs, resulting in a metric for generating more reliable and balanced pseudo-labeled nodes in graph. Furthermore, an iterative re-training strategy is employed on the extended training label set (including original labeled and pseudo-labeled nodes) to train a more generalized GNNs. Extensive experiments on benchmark graph datasets demonstrate that the proposed pseudo-labeling framework can enhance node classification performance of two alternative GNNs models by a considerable margin, specifically when labeled data are scarce.
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
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks, ar**v preprint ar**v:1609.02907 (2016)
Zhou, K., Huang, X., Li, Y., Zha, D., Chen, R., Hu, X.: Towards deeper graph neural networks with differentiable group normalization. Adv. Neural. Inf. Process. Syst. 33, 4917–4928 (2020)
**, T., et al.: Deepwalk-aware graph convolutional networks. Sci. China Inf. Sci. 65(5), 152104 (2022)
Chang, L., Dan, G.: Encoding social information with graph convolutional networks forpolitical perspective detection in news media. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (2019)
Bai, T., Zhang, Y., Wu, B., Nie, J.-Y.: Temporal graph neural networks for social recommendation. In: 2020 IEEE International Conference on Big Data (Big Data), pp. 898–903 (2020)
Fout, A.M.: Protein interface prediction using graph convolutional networks (2018)
Li, Q., Han, Z., Wu, X.-M.: Deeper insights into graph convolutional networks for semi-supervised learning. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)
Sun, K., Lin, Z., Zhu, Z.: Multi-stage self-supervised learning for graph convolutional networks on graphs with few labeled nodes. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 5892–5899 (2020)
Zhou, Z., Shi, J., Zhang, S., Huang, Z., Li, Q.: Effective semi-supervised node classification on few-labeled graph data, ar**v preprint ar**v:1910.02684 (2019)
Gal, Y., Ghahramani, Z.: Dropout as a bayesian approximation: representing model uncertainty in deep learning. In: International Conference on Machine Learning, pp. 1050–1059 (2016)
Rizve, M.N., Duarte, K., Rawat, Y.S., Shah, M.: In defense of pseudo-labeling: an uncertainty-aware pseudo-label selection framework for semi-supervised learning, ar**v preprint ar**v:2101.06329 (2021)
Lakshminarayanan, B., Pritzel, A., Blundell, C.: Simple and scalable predictive uncertainty estimation using deep ensembles. In: Advances in Neural Information Processing Systems 30 (2017)
Yang, H., Yan, X., Dai, X., Chen, Y., Cheng, J.: Self-enhanced gnn: improving graph neural networks using model outputs. In: 2021 International Joint Conference on Neural Networks (IJCNN), pp. 1–8. IEEE (2021)
Gawlikowski, J., et al.: A survey of uncertainty in deep neural networks, ar**v preprint ar**v:2107.03342 (2021)
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks, ar**v preprint ar**v:1710.10903 (2017)
Tang, J., Qu, M., Wang, M., Zhang, M., Yan, J., Mei, Q.: Line: large-scale information network embedding. In: Proceedings of the 24th International Conference on World Wide Web, pp. 1067–1077 (2015)
Peng, Z., et al.: Graph representation learning via graphical mutual information maximization. In: Proceedings of the Web Conference 2020, pp. 259–270 (2020)
Acknowledgement
This work was supported by the National Natural Science Foundation of China (Nos.62072384, 61872309, 62072385, 61772441), the Zhejiang Lab (No. 2022RD0AB02) and XMU Undergraduate Innovation and Entrepreneurship Training Programs (No.202310384191).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Long, P., Jian, Z., Liu, X. (2024). Uncertainty-Confidence Fused Pseudo-labeling for Graph Neural Networks. In: Liu, Q., et al. Pattern Recognition and Computer Vision. PRCV 2023. Lecture Notes in Computer Science, vol 14433. Springer, Singapore. https://doi.org/10.1007/978-981-99-8546-3_27
Download citation
DOI: https://doi.org/10.1007/978-981-99-8546-3_27
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8545-6
Online ISBN: 978-981-99-8546-3
eBook Packages: Computer ScienceComputer Science (R0)