Federated Graph Learning with Adaptive Importance-based Sampling

TL;DR

This paper introduces FedAIS, an adaptive importance sampling method for federated graph learning that significantly reduces costs while maintaining or improving accuracy by focusing on important nodes and synchronizing embeddings efficiently.

Contribution

FedAIS is the first adaptive importance-based sampling approach that jointly considers graph structure and optimization dynamics for federated GCN training.

Findings

Achieves up to 3.23% higher test accuracy

Reduces communication costs by 91.77%

Reduces computation costs by 85.59%

Abstract

For privacy-preserving graph learning tasks involving distributed graph datasets, federated learning (FL)-based GCN (FedGCN) training is required. A key challenge for FedGCN is scaling to large-scale graphs, which typically incurs high computation and communication costs when dealing with the explosively increasing number of neighbors. Existing graph sampling-enhanced FedGCN training approaches ignore graph structural information or dynamics of optimization, resulting in high variance and inaccurate node embeddings. To address this limitation, we propose the Federated Adaptive Importance-based Sampling (FedAIS) approach. It achieves substantial computational cost saving by focusing the limited resources on training important nodes, while reducing communication overhead via adaptive historical embedding synchronization. The proposed adaptive importance-based sampling method jointly considers the graph structural heterogeneity and the optimization dynamics to achieve optimal trade-off between efficiency and accuracy. Extensive evaluations against five state-of-the-art baselines on five real-world graph datasets show that FedAIS achieves comparable or up to 3.23% higher test accuracy, while saving communication and computation costs by 91.77% and 85.59%.