Abstract
Missing cross-subgraph information is a unique problem in Subgraph Federated Learning (SFL) and severely affects the performance of the learned model. Existing cutting-edge methods typically allow clients to exchange data with all other clients to predict missing neighbor nodes. However, such client-to-client data exchanges are highly complex and lead to expensive communication overhead. In this paper, we propose FedGGR: subgraph federated learning with global graph reconstruction. FedGGR is a practical and effective framework. Specifically, the core idea behind it is to directly learn a global graph on the server by a graph structure learning module instead of predicting the missing neighbors on each client. Compared to existing methods, FedGGR does not require any data exchange among clients and achieves remarkable enhancements in model performance. The experimental results on four benchmark datasets show that the proposed method excels with other state-of-the-art methods. We release our source code at https://github.com/poipoipoi233/FedGGR.
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
Kong, X., Gao, H., Shen, G., Duan, G., Das, S.K.: FedVCP: a federated-learning-based cooperative positioning scheme for social internet of vehicles. IEEE Trans. Comput. Soc. Syst. 9(1), 197–206 (2021)
Hou, M., **a, F., Gao, H., Chen, X., Chen, H.: Urban region profiling with spatio-temporal graph neural networks. IEEE Trans. Comput. Soc. Syst. 9(6), 1736–1747 (2022)
**a, J., et al.: Mole-BERT: rethinking pre-training graph neural networks for molecules. In: The Eleventh International Conference on Learning Representations, pp. 1–18 (2023)
Zhou, J., et al.: Graph neural networks: a review of methods and applications. AI Open 1, 57–81 (2020)
**a, F., et al.: CenGCN: centralized convolutional networks with vertex imbalance for scale-free graphs. IEEE Trans. Knowl. Data Eng. 35(5), 4555–4569 (2022)
McMahan, B., Moore, E., Ramage, D., Hampson, S., Arcas, B.A.: Communication-efficient learning of deep networks from decentralized data. In: Artificial Intelligence and Statistics, pp. 1273–1282. PMLR (2017)
Kong, X., et al.: A federated learning-based license plate recognition scheme for 5G-enabled internet of vehicles. IEEE Trans. Ind. Inf. 17(12), 8523–8530 (2021)
Chen, F., Li, P., Miyazaki, T., Wu, C.: Fedgraph: federated graph learning with intelligent sampling. IEEE Trans. Parallel Distrib. Syst. 33(8), 1775–1786 (2021)
Yao, Y., Joe-Wong, C.: FedGCN: convergence and communication tradeoffs in federated training of graph convolutional networks, pp. 1–31 (2022). ar**v preprint ar**v:2201.12433
Zhang, K., Yang, C., Li, X., Sun, L., Yiu, S.M.: Subgraph federated learning with missing neighbor generation. Adv. Neural. Inf. Process. Syst. 34, 6671–6682 (2021)
Peng, L., Wang, N., Dvornek, N., Zhu, X., Li, X.: FedNI: federated graph learning with network inpainting for population-based disease prediction. IEEE Trans. Med. Imaging 1–12 (2022)
Gupta, O., Raskar, R.: Distributed learning of deep neural network over multiple agents. J. Netw. Comput. Appl. 116, 1–8 (2018)
Baek, J., Jeong, W., **, J., Yoon, J., Hwang, S.J.: Personalized subgraph federated learning, pp. 1–20 (2022). ar**v preprint ar**v:2206.10206
Zhang, T., Chen, C., Chang, Y., Shu, L., Zheng, Z.: FedEgo: privacy-preserving personalized federated graph learning with ego-graphs, pp. 1–25 (2022). ar**v preprint ar**v:2208.13685
Liu, Y., Zheng, Y., Zhang, D., Chen, H., Peng, H., Pan, S.: Towards unsupervised deep graph structure learning. In: Proceedings of the ACM Web Conference 2022, pp. 1392–1403 (2022)
Fatemi, B., El Asri, L., Kazemi, S.M.: SLAPS: self-supervision improves structure learning for graph neural networks. Adv. Neural. Inf. Process. Syst. 34, 22667–22681 (2021)
Chen, F., Long, G., Wu, Z., Zhou, T., Jiang, J.: Personalized federated learning with a graph. In: Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22, pp. 2575–2582 (2022)
Zhao, G., Huang, Y., Tsai, C.H.: FedGSL: federated graph structure learning for local subgraph augmentation. In: 2022 IEEE International Conference on Big Data (Big Data), pp. 818–824. IEEE (2022)
Thapa, C., Arachchige, P.C.M., Camtepe, S., Sun, L.: SplitFed: when federated learning meets split learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 8485–8493 (2022)
Meng, C., Rambhatla, S., Liu, Y.: Cross-node federated graph neural network for spatio-temporal data modeling. In: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pp. 1202–1211 (2021)
Yi, J., Wu, F., Wu, C., Liu, R., Sun, G., **e, X.: Efficient-FedRec: efficient federated learning framework for privacy-preserving news recommendation. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 2814–2824 (2021)
Kipf, T.N., Welling, M.: Variational graph auto-encoders, pp. 1–3 (2016). ar**v preprint ar**v:1611.07308
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: 5th International Conference on Learning Representations, pp. 1–14 (2017)
Clevert, D., Unterthiner, T., Hochreiter, S.: Fast and accurate deep network learning by exponential linear units (ELUs). In: 4th International Conference on Learning Representations, pp. 1–14 (2016)
**e, Y., et al.: FederatedScope: a flexible federated learning platform for heterogeneity. Proc. VLDB Endow. 16(5), 1059–1072 (2023)
Sen, P., Namata, G., Bilgic, M., Getoor, L., Gallagher, B., Eliassi-Rad, T.: Collective classification in network data. AI Mag. 29(3), 93–106 (2008)
Namata, G., London, B., Getoor, L., Huang, B., Edu, U.: Query-driven active surveying for collective classification. In: 10th International Workshop on Mining and Learning with Graphs, vol. 8, pp. 1–8 (2012)
Shchur, O., Mumme, M., Bojchevski, A., Günnemann, S.: Pitfalls of graph neural network evaluation, pp. 1–11 (2018). ar**v preprint ar**v:1811.05868
Blondel, V.D., Guillaume, J.L., Lambiotte, R., Lefebvre, E.: Fast unfolding of communities in large networks. J. Stat. Mech: Theory Exp. 2008(10), P10008 (2008)
Wang, X., Zhu, M., Bo, D., Cui, P., Shi, C., Pei, J.: AM-GCN: adaptive multi-channel graph convolutional networks. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1243–1253 (2020)
Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., Bengio, Y.: Graph attention networks. In: 6th International Conference on Learning Representations, pp. 1–12 (2018)
Hamilton, W., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. Adv. Neural. Inf. Process. Syst. 30, 1–11 (2017)
**e, H., Ma, J., **ong, L., Yang, C.: Federated graph classification over MNon-IID graphs. Adv. Neural. Inf. Process. Syst. 34, 18839–18852 (2021)
Chien, E., Peng, J., Li, P., Milenkovic, O.: Adaptive universal generalized pagerank graph neural network. In: 9th International Conference on Learning Representations, pp. 1–24 (2021)
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
Liu, Z. et al. (2024). Subgraph Federated Learning with Global Graph Reconstruction. In: Song, X., Feng, R., Chen, Y., Li, J., Min, G. (eds) Web and Big Data. APWeb-WAIM 2023. Lecture Notes in Computer Science, vol 14331. Springer, Singapore. https://doi.org/10.1007/978-981-97-2303-4_11
Download citation
DOI: https://doi.org/10.1007/978-981-97-2303-4_11
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-2302-7
Online ISBN: 978-981-97-2303-4
eBook Packages: Computer ScienceComputer Science (R0)