FedSA-GCL: A Semi-Asynchronous Federated Graph Learning Framework with Personalized Aggregation and Cluster-Aware Broadcasting

TL;DR

FedSA-GCL introduces a semi-asynchronous federated graph learning framework that effectively incorporates topological information and personalized aggregation, significantly improving efficiency and robustness over existing methods.

Contribution

It proposes a novel semi-asynchronous federated graph learning framework with a cluster-aware broadcasting mechanism tailored for graph data.

Findings

Outperforms 9 baselines by 2.92% with Louvain split.

Achieves 3.4% improvement with Metis split.

Demonstrates strong robustness and efficiency on real-world datasets.

Abstract

Federated Graph Learning (FGL) is a distributed learning paradigm that enables collaborative training over large-scale subgraphs located on multiple local systems. However, most existing FGL approaches rely on synchronous communication, which leads to inefficiencies and is often impractical in real-world deployments. Meanwhile, current asynchronous federated learning (AFL) methods are primarily designed for conventional tasks such as image classification and natural language processing, without accounting for the unique topological properties of graph data. Directly applying these methods to graph learning can possibly result in semantic drift and representational inconsistency in the global model. To address these challenges, we propose FedSA-GCL, a semi-asynchronous federated framework that leverages both inter-client label distribution divergence and graph topological characteristics through a novel ClusterCast mechanism for efficient training. We evaluate FedSA-GCL on multiple real-world graph datasets using the Louvain and Metis split algorithms, and compare it against 9 baselines. Extensive experiments demonstrate that our method achieves strong robustness and outstanding efficiency, outperforming the baselines by an average of 2.92% with the Louvain and by 3.4% with the Metis.