No Cover Image

Journal article 142 views 50 downloads

FedBoosting: Federated learning with gradient protected boosting for text recognition

Hans Ren, Jingjing Deng Orcid Logo, Xianghua Xie Orcid Logo, Xiaoke Ma, Yichuan Wang

Neurocomputing, Volume: 569

Swansea University Authors: Hans Ren, Xianghua Xie Orcid Logo

Abstract

Conventional machine learning methodologies require the centralization of data for model training, which may be infeasible in situations where data sharing limitations are imposed due to concerns such as privacy and gradient protection. The Federated Learning (FL) framework enables the collaborative...

Full description

Published in: Neurocomputing
ISSN: 0925-2312
Published: Elsevier BV 2024
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa65267
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract: Conventional machine learning methodologies require the centralization of data for model training, which may be infeasible in situations where data sharing limitations are imposed due to concerns such as privacy and gradient protection. The Federated Learning (FL) framework enables the collaborative learning of a shared model without necessitating the centralization or sharing of data among the data proprietors. Nonetheless, in this paper, we demonstrate that the generalization capability of the joint model is suboptimal for Non-Independent and Non-Identically Distributed (Non-IID) data, particularly when employing the Federated Averaging (FedAvg) strategy as a result of the weight divergence phenomenon. Consequently, we present a novel boosting algorithm for FL to address both the generalization and gradient leakage challenges, as well as to facilitate accelerated convergence in gradient-based optimization. Furthermore, we introduce a secure gradient sharing protocol that incorporates Homomorphic Encryption (HE) and Differential Privacy (DP) to safeguard against gradient leakage attacks. Our empirical evaluation demonstrates that the proposed Federated Boosting (FedBoosting) technique yields significant enhancements in both prediction accuracy and computational efficiency in the visual text recognition task on publicly available benchmarks.
Keywords: Deep learning, Federated learning, Privacy preserving
College: Faculty of Science and Engineering
Funders: EPSRC, EP/N028139/1