Personalized Federated Learning With Graph

TL;DR

This paper introduces a structured federated learning framework that leverages client relation graphs to improve knowledge sharing and personalization in federated learning systems.

Contribution

It proposes a novel SFL framework that models client relations and topology, including learning hidden relations, enhancing personalization and knowledge sharing.

Findings

Effective in traffic and image benchmarks

Improves personalization with graph-based relations

Learned hidden client relations enhance performance

Abstract

Knowledge sharing and model personalization are two key components in the conceptual framework of personalized federated learning (PFL). Existing PFL methods focus on proposing new model personalization mechanisms while simply implementing knowledge sharing by aggregating models from all clients, regardless of their relation graph. This paper aims to enhance the knowledge-sharing process in PFL by leveraging the graph-based structural information among clients. We propose a novel structured federated learning (SFL) framework to learn both the global and personalized models simultaneously using client-wise relation graphs and clients' private data. We cast SFL with graph into a novel optimization problem that can model the client-wise complex relations and graph-based structural topology by a unified framework. Moreover, in addition to using an existing relation graph, SFL could be expanded to learn the hidden relations among clients. Experiments on traffic and image benchmark datasets can demonstrate the effectiveness of the proposed method. All implementation codes are available on Github