Personalized Subgraph Federated Learning with Sheaf Collaboration

TL;DR

FedSheafHN introduces a sheaf-based collaboration framework for personalized subgraph federated learning, enhancing client representations and model customization, leading to improved performance, faster convergence, and better generalization across diverse graph datasets.

Contribution

The paper proposes FedSheafHN, a novel sheaf collaboration mechanism that unifies client descriptors and generates personalized models in subgraph federated learning.

Findings

Outperforms existing methods on various datasets.

Exhibits fast convergence.

Generalizes well to new clients.

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.