发表机构
Sun Yat-sen University; Nanyang Technological University（中山大学; 南洋理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对一次性联邦图学习忽视拓扑结构的问题，提出结构熵驱动的图扩散生成方法SPIRE，利用度分布熵加权客户端并生成伪图训练全局模型，在异构和扰动场景下显著优于现有方法。
AI 中文摘要
一次性联邦图学习（FGL）要求服务器从高度压缩的信息中估计客户端的贡献，然而传统的基于体积的加权方法只捕捉客户端数据的数量，却忽略了其连接性是如何组织的。在本文中，我们提出了SPIRE，一种结构熵驱动的图扩散生成方法，将拓扑感知的客户端区分引入一次性FGL。具体来说，我们采用一阶度分布结构熵作为度质量分散的紧凑描述符，并利用它推导出结构化的客户端权重，提供了一种归纳偏置，以考虑超越数据量的图拓扑差异。在生成方面，服务器上的图扩散模型以加权客户端原型为条件合成伪图，捕获语义和结构信息，无需额外的客户端训练。生成的伪图随后通过不相交并集融合进行组装，以训练全局图神经网络。在七个真实世界图数据集上的大量实验表明，SPIRE始终优于传统和一次性FGL方法，在高度异构（非IID）和图扰动设置下尤其表现出强劲的提升。
英文摘要
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.
Comments11 pages, 5 figures
