Deakin University
Browse

File(s) under embargo

FedAGA: A federated learning framework for enhanced inter-client relationship learning

journal contribution
posted on 2024-03-07, 22:45 authored by J Ge, G Xu, J Lu, C Xu, QZ Sheng, X Zheng
Exploring relationships is important for effective model aggregation in Personalized Federated Learning (PFL). However, state-of-the-art (SOTA) PFL methods primarily focus on simple model aggregation through inter-client relationships within Euclidean space, overlooking the intricate nature of unstructured relationships. To remedy this, we propose a novel framework named Federated Learning with Adaptive Graph-based Aggregation (FedAGA) tailored for non-Euclidean space. FedAGA captures inter-client relationships through similarities based on accumulated gradients of various client models, constructing a dynamic graph topology. To enhance the reliability and accuracy of graph topology, we introduce two criteria from the perspectives of model convergence and model divergence. Our proposed approach is extensively evaluated on two PFL benchmark datasets and four real medical datasets. The results demonstrate that FedAGA accurately captures inter-client relationships across diverse models, leading to superior performance compared to the SOTA baselines. In particular, we observe notable accuracy improvements of 6.8% on CIFAR10 and 4.0% on PathMNIST compared to the existing methods.

History

Journal

Knowledge-Based Systems

Volume

286

Article number

111399

Pagination

111399-111399

Location

Amsterdam, The Netherlands

ISSN

0950-7051

eISSN

1872-7409

Language

en

Publisher

Elsevier BV

Usage metrics

    Research Publications

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC