Structural Entropy-Driven Graph Diffusion Generation for One-Shot Federated Graph Learning

2026-09-06

AI Summary

本文提出SPIRE方法，通过结构熵驱动的图扩散生成解决一次性联邦图学习中客户端贡献估计问题，超越了传统的基于数据量的方法。

Abstract

One-shot federated graph learning (FGL) requires the server to estimate client contributions from highly compressed information, yet conventional volume-based weighting captures the amount of client data while overlooking how its connectivity is organized. In this paper, we propose SPIRE, a Structural Entropy-Driven Graph Diffusion Generation method that introduces topology-aware client differentiation into one-shot FGL. Specifically, we employ first-order degree-distribution structural entropy as a compact descriptor of degree-mass dispersion and use it to derive structural client weights, providing an inductive bias that accounts for differences in graph topology beyond data volume. On the generation side, a graph diffusion model on the server synthesizes pseudographs conditioned on the weighted client prototypes, capturing both semantic and structural information without requiring additional client-side training. The generated pseudographs are then assembled via disjoint union fusion to train a global graph neural network. Extensive experiments on seven real-world graph datasets demonstrate that SPIRE consistently outperforms conventional and one-shot FGL methods, with particularly strong gains under highly heterogeneous (non-IID) and graph-perturbed settings.

Problem

• one-shot federated graph learning
• client contributions
• topology-aware

Innovation

• Structural Entropy-Driven
• Graph Diffusion Generation
• Topology-Aware Client Differentiation
• One-Shot Federated Graph Learning