Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 10, 2025Iraqi Journal for Computers and InformaticsOpen Access

A Systematic Review of Federated Learning: Emerging Techniques, Challenges, and Research Directions

View Full Paper
Ask AI
Bookmark
Share

Authors

MJM. A. JabbarUniversity of LahoreAJAhmed Sami JaddoaUniversity of Information Technology and CommunicationsUMUsama Samir MahmoudSultan Idris Education University

Discussion

Loading...

Member takes

Implication

This review consolidates insights on federated learning in healthcare and IoT, highlighting persistent challenges and research directions.

Key Points

  • Federated learning enhances privacy by enabling collaborative training across decentralized data sources, transforming various sectors.
  • The review synthesizes insights from 50 high-quality studies, identifying critical methodologies and persistent challenges in federated learning.
  • The approach includes a systematic analysis of aggregation techniques and privacy-preserving mechanisms while addressing security threats.
  • Identified gaps in research emphasize the need for standardized evaluation and scalable deployment strategies to promote federated learning.

Cite This Study

Jabbar et al. (2025) studied this question.

synapsesocial.com/papers/68c23cf6b210217d6478b486https://doi.org/10.25195/ijci.v51i2.628
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1A COMPREHENSIVE REVIEW OF FEDERATED LEARNING: ADVANCEMENTS, CHALLENGES, AND FUTURE DIRECTIONS2025 · 1 citations
  2. 2Federated Machine Learning Solutions: A Systematic Review2025
  3. 3Federated Learning in the Era of Decentralized Intelligence: Challenges and Opportunities2025 · 3 citations
  4. 4Federated Learning for Secure Data Sharing Across Distributed Networks2025
  5. 5Evaluation of Recent Developments in Federated Learning2025