TY  - JOUR
AU  - Zhang, Bolin
AU  - Gu, Ruichun
AU  - Liu, Haiying
PY  - 2025
TI  - Decentralized Federated Graph Learning via Surrogate Model
JO  - Computers, Materials & Continua
SN  - 1546-2218
SP  - 2521
EP  - 2535
VL  - 82
IS  - 2
AB  - Federated Graph Learning (FGL) enables model training without requiring each client to share local graph data, effectively breaking data silos by aggregating the training parameters from each terminal while safeguarding data privacy. Traditional FGL relies on a centralized server for model aggregation; however, this central server presents challenges such as a single point of failure and high communication overhead. Additionally, efficiently training a robust personalized local model for each client remains a significant objective in federated graph learning. To address these issues, we propose a decentralized Federated Graph Learning framework with efficient communication, termed Decentralized Federated Graph Learning via Surrogate Model (SD_FGL). In SD_FGL, each client is required to maintain two models: a private model and a surrogate model. The surrogate model is publicly shared and can exchange and update information directly with any client, eliminating the need for a central server and reducing communication overhead. The private model is independently trained by each client, allowing it to calculate similarity with other clients based on local data as well as information shared through the surrogate model. This enables the private model to better adjust its training strategy and selectively update its parameters. Additionally, local differential privacy is incorporated into the surrogate model training process to enhance privacy protection. Testing on three real-world graph datasets demonstrates that the proposed framework improves accuracy while achieving decentralized Federated Graph Learning with lower communication overhead and stronger privacy safeguards.
UR  - https://doi.org/10.32604/cmc.2024.060331
DO  - 10.32604/cmc.2024.060331