Back to Search Start Over

A Heterogeneous Federated Transfer Learning Approach with Extreme Aggregation and Speed

Authors :
Tarek Berghout
Toufik Bentrcia
Mohamed Amine Ferrag
Mohamed Benbouzid
Source :
Mathematics, Vol 10, Iss 19, p 3528 (2022)
Publication Year :
2022
Publisher :
MDPI AG, 2022.

Abstract

Federated learning (FL) is a data-privacy-preserving, decentralized process that allows local edge devices of smart infrastructures to train a collaborative model independently while keeping data localized. FL algorithms, encompassing a well-structured average of the training parameters (e.g., the weights and biases resulting from training-based stochastic gradient descent variants), are subject to many challenges, namely expensive communication, systems heterogeneity, statistical heterogeneity, and privacy concerns. In this context, our paper targets the four aforementioned challenges while focusing on reducing communication and computational costs by involving recursive least squares (RLS) training rules. Accordingly, to the best of our knowledge, this is the first time that the RLS algorithm is modified to completely accommodate non-independent and identically distributed data (non-IID) for federated transfer learning (FTL). Furthermore, this paper also introduces a newly generated dataset capable of emulating such real conditions and of making data investigation available on ordinary commercial computers with quad-core microprocessors and less need for higher computing hardware. Applications of FTL-RLS on the generated data under different levels of complexity closely related to different levels of cardinality lead to a variety of conclusions supporting its performance for future uses.

Details

Language :
English
ISSN :
22277390
Volume :
10
Issue :
19
Database :
Directory of Open Access Journals
Journal :
Mathematics
Publication Type :
Academic Journal
Accession number :
edsdoj.1957e3a754ed472b943468000fa25e61
Document Type :
article
Full Text :
https://doi.org/10.3390/math10193528