One Node Per User: Node-Level Federated Learning for Graph Neural Networks

TL;DR

This paper introduces a novel node-level federated learning framework for GNNs that preserves privacy by decentralizing message passing and feature transformation, improving performance over existing methods.

Contribution

It proposes a decoupled message-passing and feature transformation approach for federated GNN training, incorporating a graph Laplacian regularization to enhance model updates.

Findings

Achieves better performance than baseline methods.

Effectively preserves user data privacy.

Demonstrates robustness across multiple datasets.

Abstract

Graph Neural Networks (GNNs) training often necessitates gathering raw user data on a central server, which raises significant privacy concerns. Federated learning emerges as a solution, enabling collaborative model training without users directly sharing their raw data. However, integrating federated learning with GNNs presents unique challenges, especially when a client represents a graph node and holds merely a single feature vector. In this paper, we propose a novel framework for node-level federated graph learning. Specifically, we decouple the message-passing and feature vector transformation processes of the first GNN layer, allowing them to be executed separately on the user devices and the cloud server. Moreover, we introduce a graph Laplacian term based on the feature vector's latent representation to regulate the user-side model updates. The experiment results on multiple datasets show that our approach achieves better performance compared with baselines.