Saved in:
Bibliographic Details
Main Authors: Guo, Zhishuai, Wu, Wenhan, Chen, Chen, Zhang, Lei, Kotevska, Olivera, Madduri, Ravi K
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.26243
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918522959953920
author Guo, Zhishuai
Wu, Wenhan
Chen, Chen
Zhang, Lei
Kotevska, Olivera
Madduri, Ravi K
author_facet Guo, Zhishuai
Wu, Wenhan
Chen, Chen
Zhang, Lei
Kotevska, Olivera
Madduri, Ravi K
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_26243
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Provably Communication-Efficient and Privacy-Preserving Federated Graph Neural Networks
Guo, Zhishuai
Wu, Wenhan
Chen, Chen
Zhang, Lei
Kotevska, Olivera
Madduri, Ravi K
Machine Learning
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.
title Provably Communication-Efficient and Privacy-Preserving Federated Graph Neural Networks
topic Machine Learning
url https://arxiv.org/abs/2605.26243