Federated Learning: A Comprehensive Review of Strategies, Challenges, and Applications

Khatter, Sewa

doi:https://doi.org/10.55041/ijcope.v2i5.550

Volume 02, Issue 05

Published on: May 2026

FEDERATED LEARNING: A COMPREHENSIVE REVIEW OF STRATEGIES, CHALLENGES, AND APPLICATIONS

Sewa Khatter

Department of Electrical and Electronics Engineering Maharaja Surajmal Institute of Technology New Delhi

DOI:https://doi.org/10.55041/ijcope.v2i5.550

Article Status

Plagiarism Passed Peer Reviewed Open Access

Available Documents

Download PDF Review Report

Abstract

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.

How to Cite this Paper

Khatter, S. (2026). Federated Learning: A Comprehensive Review of Strategies, Challenges, and Applications. International Journal of Creative and Open Research in Engineering and Management, <i>02</i>(05). https://doi.org/10.55041/ijcope.v2i5.550

Khatter, Sewa. "Federated Learning: A Comprehensive Review of Strategies, Challenges, and Applications." International Journal of Creative and Open Research in Engineering and Management, vol. 02, no. 05, 2026, pp. . doi:https://doi.org/10.55041/ijcope.v2i5.550.

Khatter, Sewa. "Federated Learning: A Comprehensive Review of Strategies, Challenges, and Applications." International Journal of Creative and Open Research in Engineering and Management 02, no. 05 (2026). https://doi.org/https://doi.org/10.55041/ijcope.v2i5.550.

Search & Index

References

Kairouz et al., “Advances and Open Problems in Federated Learning,” Foundations and Trends in Machine Learning, vol. 14, no. 1–2, pp. 1–210, 2021.

Yurdem, M. Kuzlu, M. K. Gullu, F. O. Catak, and M. Tabassum, “Federated learning: Overview, strategies, applications, tools and future directions,” Heliyon, vol. 10, e38137, 2024.

Wen, Z. Zhang, Y. Lan, Z. Cui, J. Cai, and W. Zhang, “A survey on federated learning: challenges and applications,” International Journal of Machine Learning and Cybernetics, vol. 14, pp. 513–535, 2023.

Li, W. Yang, Z. Zhang, K. Huang, and S. Wang, “On the Convergence of FedAvg on Non-IID Data,” in Proceedings of the International Conference on Learning Representations (ICLR), 2020.

B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. Agu¨ era y Arcas, “Communication-Efficient Learning of Deep Networks from Decentralized Data,” in Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS), 2017.

Bonawitz et al., “Towards Federated Learning at Scale: System Design,” in Proceedings of the 2nd SysML Conference, 2019.

M. Mammen, “Federated Learning: Opportunities and Chal-lenges,” arXiv preprint arXiv:2101.05428, 2021.

Ethical Compliance & Review Process

•All submissions are screened under plagiarism detection.
•Review follows editorial policy.
•Authors retain copyright.
•Peer Review Type: Double-Blind Peer Review
•Published on: May 18 2026

CCBYNC

This article is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. You are free to share and adapt this work for non-commercial purposes with proper attribution.

View License

Back to Volume 02, Issue 05 View All Issues Next Article

← Previous Article

Fake News Detection using NLP Techniques

Next Article →

Festival, Faith and Identity: Understanding Mage Porob among the Ho Community