通过拓扑协作提升异构子图联邦学习的个性化建模效果
Personalized Subgraph Federated Learning with Sheaf Collaboration
- 构建协作图并用层流扩散增强客户端表征
- 基于服务器优化的超网络生成个性化模型，收敛快
- 适用于数据分布差异大的联邦学习场景
图结构数据广泛存在于各类应用中。在子图联邦学习（Subgraph Federated Learning, FL）中，数据分布在多个客户端，每个客户端拥有局部子图。个性化子图联邦学习旨在为每个客户端开发定制化模型以应对数据分布差异。然而，由于本地子图的异质性，客户端间性能差异仍是一个关键挑战。为此，我们提出 FedSheafHN，一种基于层流协作机制的新框架，用于统一增强的客户端描述符与高效的个性化模型生成。具体而言，FedSheafHN利用图级嵌入将每个客户端的本地子图嵌入到服务器构建的协作图中，并在协作图内执行层流扩散以丰富客户端表示。随后，通过服务器优化的超网络生成定制化客户端模型。实验结果表明，FedSheafHN 在多个图数据集上优于现有个性化子图联邦学习方法，同时展现出快速模型收敛能力，并能有效泛化至新客户端。
原文摘要 · Abstract (English)
Graph-structured data is prevalent in many applications. In subgraph federated learning (FL), this data is distributed across clients, each with a local subgraph. Personalized subgraph FL aims to develop a customized model for each client to handle diverse data distributions. However, performance variation across clients remains a key issue due to the heterogeneity of local subgraphs. To overcome the challenge, we propose FedSheafHN, a novel framework built on a sheaf collaboration mechanism to unify enhanced client descriptors with efficient personalized model generation. Specifically, FedSheafHN embeds each client's local subgraph into a server-constructed collaboration graph by leveraging graph-level embeddings and employing sheaf diffusion within the collaboration graph to enrich client representations. Subsequently, FedSheafHN generates customized client models via a server-optimized hypernetwork. Empirical evaluations demonstrate that FedSheafHN outperforms existing personalized subgraph FL methods on various graph datasets. Additionally, it exhibits fast model convergence and effectively generalizes to new clients.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。