Personalized Subgraph Federated Learning with Sheaf Collaboration

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liang, Wenfei, Zhao, Yanan, She, Rui, Li, Yiming, Tay, Wee Peng
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915451270856704
author Liang, Wenfei
Zhao, Yanan
She, Rui
Li, Yiming
Tay, Wee Peng
author_facet Liang, Wenfei
Zhao, Yanan
She, Rui
Li, Yiming
Tay, Wee Peng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_13642
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Personalized Subgraph Federated Learning with Sheaf Collaboration
Liang, Wenfei
Zhao, Yanan
She, Rui
Li, Yiming
Tay, Wee Peng
Machine Learning
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.
title Personalized Subgraph Federated Learning with Sheaf Collaboration
topic Machine Learning
url https://arxiv.org/abs/2508.13642