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

2026-05-25

AI Summary

This work addresses the tension in federated graph neural networks between accuracy degradation caused by ignoring cross-client links and the high communication overhead and privacy risks incurred by frequent embedding exchanges. To resolve this, we propose CE-FedGNN, a novel framework that replaces raw data or per-round embedding transmission with low-frequency exchange of aggregated node representations. It employs a moving average estimator to mitigate cross-client dependency and representation staleness, and—uniquely—integrates metric differential privacy (metric-DP) in the embedding space to provide both practical and formal privacy guarantees. Theoretically, the algorithm converges to a stationary point at a rate of O(1/√T) with communication complexity O(T^{3/4}). Experiments on anti-money laundering and citation network datasets demonstrate that CE-FedGNN significantly reduces communication costs while maintaining competitive model performance and robust privacy protection.

Abstract

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.

Problem

• Federated Graph Neural Networks
• Communication Efficiency
• Privacy Preservation
• Cross-client Links
• Differential Privacy

Innovation

• Federated Graph Neural Networks
• Communication Efficiency
• Metric Differential Privacy
• Moving-Average Estimator
• Privacy-Preserving Machine Learning