Federated heterogeneous graph contrastive network with fine-grained bidirectional knowledge distillation

Graphical abstract

References

[1] Fu X, King I. FedHGN: a federated framework for heterogeneous graph neural networks. In: Proceedings of the 32nd International Joint Conference on Artificial Intelligence. 2023, 3705−3713

[2] Li T, Sahu A K, Zaheer M, Sanjabi M, Talwalkar A, Smith V. Federated optimization in heterogeneous networks. In: Proceedings of the 3rd Conference on Machine Learning and Systems. 2020, 429−450

[3] Wu Z, Li X, Zhu Y, Li R H, Wang G, Zhou C. Federated prototype graph learning. 2025, arXiv preprint arXiv: 2504.09493

[4] Huang W, Wan G, Ye M, Du B. Federated graph semantic and structural learning. In: Proceedings of the 32nd International Joint Conference on Artificial Intelligence. 2023, 3830−3838

[5] Li S, Guo J . Subgraph federated learning with information bottleneck constrained generative learning. ACM Transactions on Knowledge Discovery from Data, 2025, 19( 6): 124

[6] Zhu Z, Hong J, Zhou J. Data-free knowledge distillation for heterogeneous federated learning. In: Proceedings of the 38th International Conference on Machine Learning. 2021, 12878−12889

[7] Fu J, Li C, Zhao Z, Zeng Q . Heterogeneous graph knowledge distillation neural network incorporating multiple relations and cross-semantic interactions. Information Sciences, 2024, 658: 120004

[8] Karypis G, Kumar V . A fast and high quality multilevel scheme for partitioning irregular graphs. SIAM Journal on Scientific Computing, 1998, 20( 1): 359–392

[9] McMahan B, Moore E, Ramage D, Hampson S, Arcas B A Y. Communication-efficient learning of deep networks from decentralized data. In: Proceedings of the 20th International Conference on Artificial Intelligence and Statistics. 2017, 1273−1282

[10] Li X, Wu Z, Zhang W, Zhu Y, Li R H, Wang G . FedGTA: topology-aware averaging for federated graph learning. Proceedings of the VLDB Endowment, 2023, 17( 1): 41–50

RIGHTS & PERMISSIONS

Higher Education Press