Heterogeneity-Aware Knowledge Sharing for Graph Federated Learning

2026-01-29

AI Summary

This work addresses the significant performance degradation and hindered knowledge sharing in graph federated learning caused by the dual heterogeneity of node features and graph structures across clients. To jointly model and mitigate both sources of heterogeneity, the authors propose FedSSA, a novel approach that aligns category-level semantic distributions via variational inference and achieves structural alignment through spectral graph neural networks combined with spectral energy metrics. Furthermore, FedSSA introduces cluster-level representative distributions and a spectral energy-based clustering mechanism to foster collaborative learning of semantic and structural knowledge across clients. Extensive experiments on six homophilic and five heterophilic graph datasets demonstrate that FedSSA consistently outperforms eleven state-of-the-art methods under both non-overlapping and overlapping client partitions, confirming its effectiveness and robustness.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

Graph Federated Learning (GFL) enables distributed graph representation learning while protecting the privacy of graph data. However, GFL suffers from heterogeneity arising from diverse node features and structural topologies across multiple clients. To address both types of heterogeneity, we propose a novel graph Federated learning method via Semantic and Structural Alignment (FedSSA), which shares the knowledge of both node features and structural topologies. For node feature heterogeneity, we propose a novel variational model to infer class-wise node distributions, so that we can cluster clients based on inferred distributions and construct cluster-level representative distributions. We then minimize the divergence between local and cluster-level distributions to facilitate semantic knowledge sharing. For structural heterogeneity, we employ spectral Graph Neural Networks (GNNs) and propose a spectral energy measure to characterize structural information, so that we can cluster clients based on spectral energy and build cluster-level spectral GNNs. We then align the spectral characteristics of local spectral GNNs with those of cluster-level spectral GNNs to enable structural knowledge sharing. Experiments on six homophilic and five heterophilic graph datasets under both non-overlapping and overlapping partitioning settings demonstrate that FedSSA consistently outperforms eleven state-of-the-art methods.

Problem

• Graph Federated Learning
• heterogeneity
• node features
• structural topology
• knowledge sharing

Innovation

• Graph Federated Learning
• Heterogeneity
• Semantic Alignment
• Structural Alignment
• Spectral GNN