| Federated Learning: A Comprehensive Survey of Applications, Challenges, and Emerging Research Frontiers |
| Paper ID : 1076-ICEEM2025 (R1) |
| Authors |
|
Mostafa Samy Atlam *1, Gamal Attiya2, Mohamed Elrashidy3 1Assistant Lecturer at Dept. of Computer Science and Engineering, Faculty of Electronic Engineering, Menoufia University 2Dept. of Computer Science and Engineering, Faculty of Electronic Engineering, Menoufia University 3Department of Computer, Arab East Colleges, Riyadh, Kingdom of Saudi Arabia |
| Abstract |
| Federated Learning (FL) is seen to have revolutionized collaborative machine learning, wherein models are trained on distributed resources without compromising data privacy. This survey gives an impression of the FL landscape and analyzes its various architectures: horizontal, vertical, and federated transfer learning, each targeting different data distribution scenarios. We detail FL's ever-increasing applications in prominent areas: better diagnostics and drug discovery in healthcare, fraud prediction and risk estimation in finance, improved traffic and energy management in smart cities, intelligent edge computing for IoT devices, and so forth. While FL holds great potential, it also faces a tangled web of challenges. We take a close look at the widespread issue of data heterogeneity, where varying data distributions among clients can hinder the global model's ability to converge and perform well. Additionally, we tackle the considerable communication overhead that comes with the back-and-forth of model exchanges and delve into innovative privacy-preserving methods like differential privacy and secure multi-party computation. Lastly, there are scaling issues discussed in FL as it grows to accommodate a large number of clients, highlighting the need for robust aggregation schemes and strong system designs. This work seeks to provide a comprehensive overview of the current state of FL, its intricate nature, and exciting avenues for future research. |
| Keywords |
| Federated Learning, FL Architectures, Data Heterogeneity, Communication Overhead, Privacy Preservation, Differential Privacy, Healthcare, Finance, Smart Cities |
| Status: Accepted |