S2FGL: Spatial Spectral Federated Graph Learning

TL;DR

S2FGL is a novel federated graph learning framework that addresses spatial and spectral heterogeneity issues by introducing a global knowledge repository and frequency alignment, improving model generalization across distributed graph data.

Contribution

The paper proposes S2FGL, integrating spatial and spectral strategies with a global knowledge repository and frequency alignment to enhance federated graph learning.

Findings

Outperforms existing federated GNN methods on multiple datasets.

Effectively mitigates spectral and spatial heterogeneity issues.

Improves global model generalization in federated settings.

Abstract

Federated Graph Learning (FGL) combines the privacy-preserving capabilities of federated learning (FL) with the strong graph modeling capability of Graph Neural Networks (GNNs). Current research addresses subgraph-FL from the structural perspective, neglecting the propagation of graph signals on spatial and spectral domains of the structure. From a spatial perspective, subgraph-FL introduces edge disconnections between clients, leading to disruptions in label signals and a degradation in the semantic knowledge of the global GNN. From a spectral perspective, spectral heterogeneity causes inconsistencies in signal frequencies across subgraphs, which makes local GNNs overfit the local signal propagation schemes. As a result, spectral client drift occurs, undermining global generalizability. To tackle the challenges, we propose a global knowledge repository to mitigate the challenge of poor semantic knowledge caused by label signal disruption. Furthermore, we design a frequency alignment to address spectral client drift. The combination of Spatial and Spectral strategies forms our framework S2FGL. Extensive experiments on multiple datasets demonstrate the superiority of S2FGL. The code is available at https://github.com/Wonder7racer/S2FGL.git.