TY - GEN
T1 - Communication-efficient and Privacy-enhanced Federated Graph Learning via GAN-based Data Augmentation
AU - Yuan, Yanli
AU - Song, Zijun
AU - Lei, Dian
AU - Chen, Zihan
AU - Zhang, Chuan
AU - Zhu, Liehuang
N1 - Publisher Copyright:
© 2025 IEEE.
PY - 2025
Y1 - 2025
N2 - Graph neural network (GNN) is widely used to solve challenging problems in wireless communications, but traditional centralized training of GNN models may pose significant privacy risks. Federated graph learning offers a reliable solution for safeguarding sensitive information within subgraphs in each client. Nonetheless, there may be connections between subgraphs, and existing federated graph learning frameworks generally require additional client-server communication to reconstruct those missing graph information (e.g., edges and nodes), resulting in high communication overhead and privacy leakage risks. To address this issue, we propose a communication-efficient and privacy-enhanced Federated Graph Learning framework based on generative adversarial networks (GANs), termed FGL-GAN. Specifically, FGL-GAN introduces a GAN-based graph data augmentation module to synthesize realistic neighbor nodes between subgraphs, thereby alleviating local missing graph information and enhancing model performance. Notably, the training and execution of the entire graph data augmentation module are performed locally on each client, which significantly reduces the server-client communication overhead and ensures privacy protection. Extensive experiments demonstrate the effectiveness of FGL-GAN across a diverse set of benchmarks.
AB - Graph neural network (GNN) is widely used to solve challenging problems in wireless communications, but traditional centralized training of GNN models may pose significant privacy risks. Federated graph learning offers a reliable solution for safeguarding sensitive information within subgraphs in each client. Nonetheless, there may be connections between subgraphs, and existing federated graph learning frameworks generally require additional client-server communication to reconstruct those missing graph information (e.g., edges and nodes), resulting in high communication overhead and privacy leakage risks. To address this issue, we propose a communication-efficient and privacy-enhanced Federated Graph Learning framework based on generative adversarial networks (GANs), termed FGL-GAN. Specifically, FGL-GAN introduces a GAN-based graph data augmentation module to synthesize realistic neighbor nodes between subgraphs, thereby alleviating local missing graph information and enhancing model performance. Notably, the training and execution of the entire graph data augmentation module are performed locally on each client, which significantly reduces the server-client communication overhead and ensures privacy protection. Extensive experiments demonstrate the effectiveness of FGL-GAN across a diverse set of benchmarks.
KW - Federated graph learning
KW - data augmentation
KW - generative adversarial networks
KW - privacy-preserving
UR - https://www.scopus.com/pages/publications/105017644527
U2 - 10.1109/ICCC65529.2025.11148596
DO - 10.1109/ICCC65529.2025.11148596
M3 - Conference contribution
AN - SCOPUS:105017644527
T3 - 2025 IEEE/CIC International Conference on Communications in China:Shaping the Future of Integrated Connectivity, ICCC 2025
BT - 2025 IEEE/CIC International Conference on Communications in China:Shaping the Future of Integrated Connectivity, ICCC 2025
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2025 IEEE/CIC International Conference on Communications in China, ICCC 2025
Y2 - 10 August 2025 through 13 August 2025
ER -