FedEgo: Privacy-preserving Personalized Federated Graph Learning with Ego-graphs

TL;DR

FedEgo is a federated graph learning framework that leverages ego-graphs and personalization strategies to enhance privacy and performance across distributed, heterogeneous graph data sources.

Contribution

It introduces FedEgo, combining ego-graphs, Mixup privacy, and adaptive personalization to improve federated GNN performance under data heterogeneity.

Findings

FedEgo outperforms baseline methods in accuracy.

Personalization improves model adaptability to local data.

Mixup enhances privacy without sacrificing performance.

Abstract

As special information carriers containing both structure and feature information, graphs are widely used in graph mining, e.g., Graph Neural Networks (GNNs). However, in some practical scenarios, graph data are stored separately in multiple distributed parties, which may not be directly shared due to conflicts of interest. Hence, federated graph neural networks are proposed to address such data silo problems while preserving the privacy of each party (or client). Nevertheless, different graph data distributions among various parties, which is known as the statistical heterogeneity, may degrade the performance of naive federated learning algorithms like FedAvg. In this paper, we propose FedEgo, a federated graph learning framework based on ego-graphs to tackle the challenges above, where each client will train their local models while also contributing to the training of a global model. FedEgo applies GraphSAGE over ego-graphs to make full use of the structure information and utilizes Mixup for privacy concerns. To deal with the statistical heterogeneity, we integrate personalization into learning and propose an adaptive mixing coefficient strategy that enables clients to achieve their optimal personalization. Extensive experimental results and in-depth analysis demonstrate the effectiveness of FedEgo.