Federated Spectral Graph Transformers Meet Neural Ordinary Differential Equations for Non-IID Graphs

2025-04-16

AI Summary

This paper addresses the challenge of training federated graph neural networks (GNNs) on non-IID heterogeneous graph data in privacy-sensitive settings. We propose the first federated learning framework integrating spectral graph Transformers and neural ordinary differential equations (Neural ODEs). Our method employs spectral graph convolutions to model local structural patterns, Transformers to capture long-range dependencies, and Neural ODEs to enable continuous-time dynamic representation learning; additionally, we design a lightweight heterogeneous graph adaptation mechanism to handle node- and edge-type heterogeneity. The framework preserves data privacy and communication efficiency while significantly improving generalization on non-IID heterogeneous graphs. Extensive experiments demonstrate state-of-the-art performance on real-world tasks—including social network analysis, recommendation systems, and fraud detection—outperforming existing federated GNN approaches on heterogeneous graphs and remaining competitive on homogeneous graphs. The code is publicly available.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing

Abstract

Graph Neural Network (GNN) research is rapidly advancing due to GNNs' capacity to learn distributed representations from graph-structured data. However, centralizing large volumes of real-world graph data for GNN training is often impractical due to privacy concerns, regulatory restrictions, and commercial competition. Federated learning (FL), a distributed learning paradigm, offers a solution by preserving data privacy with collaborative model training. Despite progress in training huge vision and language models, federated learning for GNNs remains underexplored. To address this challenge, we present a novel method for federated learning on GNNs based on spectral GNNs equipped with neural ordinary differential equations (ODE) for better information capture, showing promising results across both homophilic and heterophilic graphs. Our approach effectively handles non-Independent and Identically Distributed (non-IID) data, while also achieving performance comparable to existing methods that only operate on IID data. It is designed to be privacy-preserving and bandwidth-optimized, making it suitable for real-world applications such as social network analysis, recommendation systems, and fraud detection, which often involve complex, non-IID, and heterophilic graph structures. Our results in the area of federated learning on non-IID heterophilic graphs demonstrate significant improvements, while also achieving better performance on homophilic graphs. This work highlights the potential of federated learning in diverse and challenging graph settings. Open-source code available on GitHub (https://github.com/SpringWiz11/Fed-GNODEFormer).

Problem

• Federated learning for GNNs with non-IID graph data
• Privacy-preserving spectral GNNs with neural ODEs
• Handling heterophilic and homophilic graphs in FL

Innovation

• Federated learning for spectral GNNs
• Neural ODEs enhance information capture
• Handles non-IID heterophilic graphs effectively