arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.26243cs.LG
收藏

可证明通信高效且隐私保护的联邦图神经网络

Provably Communication-Efficient and Privacy-Preserving Federated Graph Neural Networks

Northern Illinois University(北伊利诺伊大学);University of North Carolina at Charlotte(北卡罗来纳州立大学查珀尔山分校);University of Central Florida(中央佛罗里达大学);Oak Ridge National Laboratory(橡树岭国家实验室);Argonne National Laboratory(阿贡国家实验室)

Zhishuai Guo, Wenhan Wu, Chen Chen, Lei Zhang, Olivera Kotevska, Ravi K Madduri

AI总结:

提出CE-FedGNN框架,通过稀疏交换聚合节点表示和移动平均估计器处理跨客户端依赖,结合度量差分隐私实现通信高效与隐私保护,并证明收敛速率和隐私保证。

摘要:

图神经网络(GNN)在关系数据上取得了强性能,但现实世界的图通常分布在多个组织之间,由于隐私和政策约束,这些组织无法共享原始数据。现有的联邦GNN方法要么忽略跨客户端链接导致精度下降,要么需要频繁的嵌入交换,带来巨大的通信和隐私成本。我们提出了CE-FedGNN,一个通信高效且隐私保护的联邦GNN框架,用于学习此类耦合图。我们的方法避免共享原始数据或每轮嵌入,而是通过稀疏交换聚合的节点表示。为了处理跨客户端依赖和过时性,我们引入了一个移动平均估计器,持续跟踪节点表示并使其能够在多轮中稳定重用。为了为发布的表示提供正式的隐私保证,我们采用了度量差分隐私(metric-DP)框架,该框架根据学习嵌入空间中的距离而非最坏情况输入扰动来衡量隐私。这在标准差分隐私变得过于保守的噪声水平下提供了有意义的保证。我们建立了以$O(1/\sqrt{T})$速率收敛到稳定点,通信复杂度为$O(T^{3/4})$。此外,我们在公共队列威胁模型下通过Rényi差分隐私组合推导了$(\varepsilon,\delta)$-度量差分隐私保证。在合成银行间反洗钱基准和引文网络上的实验表明,CE-FedGNN在显著降低通信的同时保持了强性能,并在隐私保护噪声下保持鲁棒性。

英文摘要:

Graph neural networks (GNNs) achieve strong performance on relational data, but real-world graphs are often distributed across organizations that cannot share raw data due to privacy and policy constraints. Existing federated GNN methods either ignore cross-client links, leading to degraded accuracy, or require frequent embedding exchanges, incurring substantial communication and privacy costs. We propose CE-FedGNN, a communication-efficient and privacy-preserving federated GNN framework for learning over such coupled graphs. Our approach avoids sharing raw data or per-round embeddings by infrequently exchanging aggregated node representations. To handle cross-client dependency and staleness, we introduce a moving-average estimator that continuously tracks node representations and enables their stable reuse across rounds. To provide formal privacy guarantees for the released representations, we adopt the metric differential privacy (metric-DP) framework, which measures privacy with respect to distances in the learned embedding space rather than worst-case input perturbations. This yields meaningful guarantees at noise levels where standard differential privacy becomes overly conservative. We establish convergence to a stationary point at a rate of $O(1/\sqrt{T})$ with $O(T^{3/4})$ communication complexity. In addition, we derive $(\varepsilon,δ)$-metric-DP guarantees via Rényi differential privacy composition under a public-cohort threat model. Experiments on synthetic interbank anti-money laundering benchmarks and citation networks demonstrate that CE-FedGNN achieves strong performance while significantly reducing communication and maintaining robustness under privacy-preserving noise.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑