A federated graph neural network framework for privacy-preserving personalization

TLDR

Graph neural networks model high‑order interactions and are widely used for personalized recommendation, but centralized training on global graphs exposes privacy‑sensitive user data. This work introduces FedPerGNN, a federated GNN framework that delivers effective personalization while protecting user privacy. FedPerGNN trains GNNs collaboratively on decentralized graphs derived from local data using a privacy‑preserving model‑update scheme, and further expands the graph with a privacy‑preserving protocol to capture high‑order relationships. Across six datasets, FedPerGNN reduces personalization errors by 4.0–9.6 % compared to leading federated methods, demonstrating a promising approach for responsible, privacy‑preserving graph‑based personalization.

Abstract

Abstract Graph neural network (GNN) is effective in modeling high-order interactions and has been widely used in various personalized applications such as recommendation. However, mainstream personalization methods rely on centralized GNN learning on global graphs, which have considerable privacy risks due to the privacy-sensitive nature of user data. Here, we present a federated GNN framework named FedPerGNN for both effective and privacy-preserving personalization. Through a privacy-preserving model update method, we can collaboratively train GNN models based on decentralized graphs inferred from local data. To further exploit graph information beyond local interactions, we introduce a privacy-preserving graph expansion protocol to incorporate high-order information under privacy protection. Experimental results on six datasets for personalization in different scenarios show that FedPerGNN achieves 4.0% ~ 9.6% lower errors than the state-of-the-art federated personalization methods under good privacy protection. FedPerGNN provides a promising direction to mining decentralized graph data in a privacy-preserving manner for responsible and intelligent personalization.