Home
Author Guide
Editor Guide
Reviewer Guide
Published Issues
Special Issue
Introduction
Special Issues List
Sections and Topics
Sections
Topics
Internet of Things (IoT) in Smart Systems and Applications
journal menu
Aims and Scope
Editorial Board
Indexing Service
Article Processing Charge
Open Access
Copyright and Licensing
Preservation and Repository Policy
Publication Ethics
Editorial Process
Contact Us
General Information
ISSN:
1798-2340 (Online)
Frequency:
Monthly
DOI:
10.12720/jait
Indexing:
ESCI (Web of Science)
,
Scopus
,
CNKI
,
etc
.
Acceptance Rate:
12%
APC:
1000 USD
Average Days to Accept:
87 days
Journal Metrics:
Impact Factor 2023: 0.9
4.2
2023
CiteScore
57th percentile
Powered by
Article Metrics in Dimensions
Editor-in-Chief
Prof. Kin C. Yow
University of Regina, Saskatchewan, Canada
I'm delighted to serve as the Editor-in-Chief of
Journal of Advances in Information Technology
.
JAIT
is intended to reflect new directions of research and report latest advances in information technology. I will do my best to increase the prestige of the journal.
What's New
2025-02-10
All the 141 papers published in JAIT in 2024 have been indexed by Scopus.
2025-01-23
JAIT Vol. 16, No. 1 has been published online!
2024-06-07
JAIT received the CiteScore 2023 with 4.2, ranked #169/394 in Category Computer Science: Information Systems, #174/395 in Category Computer Science: Computer Networks and Communications, #226/350 in Category Computer Science: Computer Science Applications
Home
>
Published Issues
>
2022
>
Volume 13, No. 6, December 2022
>
JAIT 2022 Vol.13(6): 539-548
doi: 10.12720/jait.13.6.539-548
An Adaptive Model Averaging Procedure for Federated Learning (AdaFed)
Alessandro Giuseppi
1
, Lucrezia Della Torre
1
, Danilo Menegatti
1
, Francesco Delli Priscoli
1
, Antonio Pietrabissa
1
, and Cecilia Poli
2
1. University of Rome La Sapienza, Rome, Italy
2. Istituto Superiore di Sanità, Rome, Italy
Abstract
—Federated Learning (FL) is an enabling technology for Machine Learning in scenarios in which it is impossible, for privacy and/or regulatory reasons, to analyze data in a centralized manner. FL envisages that distributed clients cooperate to learn a model without any data exchange, in favor of a model averaging procedure that is coordinated by a server. In this work, we present the Adaptive Federated Learning (AdaFed) algorithm, that extends the original Federated Averaging algorithm by: (i) dynamically weighting the local models, based on their performance, for the averaging procedure; (ii) adapting the loss function at every communication round depending on the training behavior. This work specializes AdaFed for both classification and regression tasks, and reports several validation tests on benchmarking dataset, showing its enhanced robustness against unbalanced data distributions and adversarial clients.
Index Terms
—federated learning, distributed learning systems, adaptive learning, deep neural networks
Cite: Alessandro Giuseppi, Lucrezia Della Torre, Danilo Menegatti, Francesco Delli Priscoli, Antonio Pietrabissa, and Cecilia Poli, "An Adaptive Model Averaging Procedure for Federated Learning (AdaFed)," Journal of Advances in Information Technology, Vol. 13, No. 6, pp. 539-548, December 2022.
Copyright © 2022 by the authors. This is an open access article distributed under the Creative Commons Attribution License (
CC BY-NC-ND 4.0
), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.
附件说明
PREVIOUS PAPER
First page
NEXT PAPER
Frequent Block Access Pattern-Based Replication Algorithm for Improving the Performance of Cloud Storage Systems