Federated Learning: A Comprehensive Review of Strategies, Challenges, and Applications
International Journal of Creative and Open Research in Engineering and Management · 18.05.2026 · 02 (05) · 1-3
DOI: 10.55041/ijcope.v2i5.550 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Creative and Open Research in Engineering and Management, online erschienen am 18.05.2026. Verfasst von Sewa Khatter Sewa Khatter.
Abstract (Originalsprache)
Federated learning(FL) represents a subsection of machine learning that allows multiple clients to work collaboratively whilst not sharing the private raw data [2]. This review paper systematically goes over FL architectures, specifically cross-device and cross-silo deploy-ments [3]. We explain core optimization algorithms such as federated averaging (FedAvg) & its variants, and analyse their mathematical im-plementation and performance [4]. We also address the key challenges faced during FL such as data heterogeneity (non-IID data), commu-nication efficiency, system heterogeneity, fairness & bias, and system vulnerability to privacy breaches [5]. Additionally, the paper discusses the various applications of FL across healthcare, mobile edge computing and Internet of Things (IoT) [6]. Lastly, this paper outlines the future research trajectories so that FL models can be deployed at a global scale [7]. Index Terms—Federated Learning, Distributed Optimization, Cross-Device, Cross-Silo, Non-IID Data.
Zitieren
APA
Khatter, S. K. S. (2026). Federated Learning: A Comprehensive Review of Strategies, Challenges, and Applications. International Journal of Creative and Open Research in Engineering and Management, 02(05), 1-3. https://doi.org/10.55041/ijcope.v2i5.550
Vancouver
Khatter SKS. Federated Learning: A Comprehensive Review of Strategies, Challenges, and Applications. International Journal of Creative and Open Research in Engineering and Management. 2026;02(05):1-3. doi:10.55041/ijcope.v2i5.550
BibTeX
@article{Khatter2026,
author = {Khatter, Sewa Khatter Sewa},
title = {Federated Learning: A Comprehensive Review of Strategies, Challenges, and Applications},
journal = {International Journal of Creative and Open Research in Engineering and Management},
year = {2026},
volume = {02},
number = {05},
pages = {1--3},
doi = {10.55041/ijcope.v2i5.550}
}
EUVIMED