A Federated Graph Neural Network Framework for Privacy-Preserving Personalization

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 FedGNN 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 FedGNN achieves 4.0%~9.6% lower errors than the state-of-the-art federated personalization methods under good privacy protection. FedGNN provides a novel direction to mining decentralized graph data in a privacy-preserving manner for responsible and intelligent personalization.

Insights into Multi-Model Federated Learning: An Advanced Approach for Air Quality Index Forecasting

“…Then, to reach an agreement on the global update, each client executes a model aggregation utilizing the model updates received from nearby clients through P2P communication. Decentralized FL may be made to entirely or partially rely on how it is used (see FL graph in [62]). The whole training process can be written in pseudocode as in (Algorithm 2).…”