FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preference

TL;DR

FedSSP introduces a novel federated graph learning framework that leverages spectral graph knowledge and personalized preferences to effectively handle structural heterogeneity and domain shifts in decentralized GNN training.

Contribution

The paper proposes FedSSP, a federated graph learning method that shares spectral knowledge and incorporates personalized preferences, addressing structural heterogeneity and domain shifts.

Findings

FedSSP outperforms existing methods in cross-dataset and cross-domain experiments.

Spectral knowledge sharing effectively captures domain structural shifts.

Personalized preference modules improve local model customization.

Abstract

Personalized Federated Graph Learning (pFGL) facilitates the decentralized training of Graph Neural Networks (GNNs) without compromising privacy while accommodating personalized requirements for non-IID participants. In cross-domain scenarios, structural heterogeneity poses significant challenges for pFGL. Nevertheless, previous pFGL methods incorrectly share non-generic knowledge globally and fail to tailor personalized solutions locally under domain structural shift. We innovatively reveal that the spectral nature of graphs can well reflect inherent domain structural shifts. Correspondingly, our method overcomes it by sharing generic spectral knowledge. Moreover, we indicate the biased message-passing schemes for graph structures and propose the personalized preference module. Combining both strategies, we propose our pFGL framework FedSSP which Shares generic Spectral knowledge while satisfying graph Preferences. Furthermore, We perform extensive experiments on cross-dataset and cross-domain settings to demonstrate the superiority of our framework. The code is available at https://github.com/OakleyTan/FedSSP.