Abstract
Graph neural networks have demonstrated state-of-the-art performance in many graph analysis tasks. However, relying on both node features and topology completeness can be challenging, especially as node features may be completely missing. Existing efforts that direct node feature completion suffer from several limitations on feature-missing graphs. In this paper, we propose a novel and general extension for running graph neural networks on feature-missing graphs via complete missing node feature information in the embedding space, called GNN-FIC. Specifically, it utilizes a Feature Information Generator to simulate missing feature information in the embedding space and then completes the node embedding using the predicted missing feature information. Additionally, GNN-FIC introduces two alignment mechanisms and a relation constraint mechanism, aiding in generating high-quality missing feature information. Extensive experiments on four benchmark datasets have shown that our proposed method provides consistent performance gains compared with several advanced methods.
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
Akiba, T., Sano, S., Yanase, T., et al.: Optuna: a next-generation hyperparameter optimization framework. In: International Conference on Knowledge Discovery and Data Mining, pp. 2623–2631 (2019)
Batista, G.E.A.P.A., Monard, M.C.: A study of k-nearest neighbour as an imputation method. In: International Conference on Health Information Science, pp. 251–260 (2002)
Candès, E.J., Recht, B.: Exact matrix completion via convex optimization. Found. Comput. Math. 9, 717–772 (2008)
Chen, X., Chen, S., Yao, J., et al.: Learning on attribute-missing graphs. IEEE Trans. Pattern Anal. Mach. Intell. 44, 740–757 (2020)
Donahue, J., Krähenbühl, P., Darrell, T.: Adversarial feature learning. In: International Conference on Learning Representations (2016)
Feng, W., Zhang, J., Dong, Y., et al.: Graph random neural networks for semi-supervised learning on graphs. In: Neural Information Processing Systems, pp. 22092–22103 (2020)
García-Laencina, P.J., Sancho-Gómez, J.L., Figueiras-Vidal, A.R.: Pattern classification with missing data: a review. Neural Comput. Appl. 19, 263–282 (2010)
Hu, X., Shen, Y., Pedrycz, W., Li, Y., Wu, G.: Granular fuzzy rule-based modeling with incomplete data representation. IEEE Trans. Cybern. 52, 6420–6433 (2021)
Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: International Conference on Learning Representations (2014)
Koren, Y., Bell, R.M., Volinsky, C.: Matrix factorization techniques for recommender systems. Computer 42, 30–37 (2009)
Mazumder, R., Hastie, T.J., Tibshirani, R.: Spectral regularization algorithms for learning large incomplete matrices. J. Mach. Learn. Res. 11, 2287–2322 (2010)
Spinelli, I., Scardapane, S., Uncini, A.: Missing data imputation with adversarially-trained graph convolutional networks. Neural Netw. 129, 249–260 (2020)
Taguchi, H., Liu, X., Murata, T.: Graph convolutional networks for graphs containing missing features. Futur. Gener. Comput. Syst. 117, 155–168 (2020)
Yoon, J., Jordon, J., van der Schaar, M.: Gain: missing data imputation using generative adversarial nets. In: International Conference on Machine Learning, pp. 5689–5698 (2018)
Acknowledgements
This paper was supported by the National Natural Science Foundation of China (No. 62162005 and U21A20474), Guangxi Science and Technology Project (GuikeAA22067070 and GuikeAD21220114), Center for Applied Mathematics of Guangxi (Guangxi Normal University), Guangxi “Bagui Scholar” Teams for Innovation and Research Project, and Guangxi Collaborative Innovation Center of Multisource Information Integration and Intelligent Processing.
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
Hu, J., Wang, J., Wei, Q., Kai, D., Li, X. (2023). Learning Graph Neural Networks on Feature-Missing Graphs. In: Jin, Z., Jiang, Y., Buchmann, R.A., Bi, Y., Ghiran, AM., Ma, W. (eds) Knowledge Science, Engineering and Management. KSEM 2023. Lecture Notes in Computer Science(), vol 14117. Springer, Cham. https://doi.org/10.1007/978-3-031-40283-8_22
Download citation
DOI: https://doi.org/10.1007/978-3-031-40283-8_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-40282-1
Online ISBN: 978-3-031-40283-8
eBook Packages: Computer ScienceComputer Science (R0)