Personalized Subgraph Federated Learning with Sheaf Collaboration

2025-08-19

AI Summary

To address performance degradation caused by statistical heterogeneity across clients in subgraph federated learning, this paper proposes FedSheafHN. Methodologically, it introduces (1) a server-side collaborative graph with a layer-wise sheaf diffusion mechanism to fuse graph-level embeddings and uniformly enhance client representations, and (2) a lightweight hypernetwork that generates personalized model parameters for efficient client-specific modeling. By jointly optimizing representation learning and model personalization, FedSheafHN achieves significant improvements over state-of-the-art baselines across multiple graph benchmarks. Empirically, it demonstrates faster convergence, superior generalization, and strong adaptability to unseen clients—without increasing communication overhead or compromising privacy guarantees.

Technology Category

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

Application Category

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

Abstract

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.

Problem

• Handling heterogeneous local subgraph distributions across clients
• Developing customized models for each client in federated learning
• Unifying client descriptors with personalized model generation

Innovation

• Sheaf collaboration mechanism for client representation
• Graph-level embeddings for client subgraph embedding
• Hypernetwork for personalized model generation