•  
  •  
 

Corresponding Author

Sarah H. Mnkash

Document Type

Article

Keywords

Federated learning, Deep learning, Privacy-preserving AI, Non-IID data, Machine learning

Abstract

Federated Learning (FL) introduces a decentralized machine learning paradigm where model training occurs directly on user devices, ensuring data privacy by keeping sensitive information local. This approach ensures data privacy and security by keeping all sensitive or personally identifiable information local to the device, thereby eliminating the need to transfer or centralize raw data. In this survey, we examine federated deep learning — its challenges, recent developments, application domains, privacy preservation strategies, and future trends. We will give some primitive reference papers of the heterogeneity of statistics and systems, communication cost, fairness, and trust. Applications in health, Internet of Things (IoT), Natural Language Processing (NLP), computer vision, and finance will be discussed. Modern approaches to enhancing privacy – differential privacy, secure aggregation, or homomorphic encryption – will be outlined. Finally, we talk about open problems and future directions for scalability, lifelong learning, and large foundation models. This paper helps researchers and professionals to set out the domain of the federated learning.

Download

Share

COinS