Year: 2025
Type: preprint
Abstract: Federated Learning (FL) is a decentralized machine learning paradigm that enables collaborative model training across distributed data sources while preserving data privacy and ownership. Unlike traditional centralized approaches, FL ensures that data remains local to the devices or institutions that generate it, making it particularly suitable for applications in privacysensitive domains such as healthcare, finance, and edge computing. This survey provides a comprehensive overview of the field of FL, discussing its foundational concepts, taxonomy, and diverse applications. Key challenges, including data heterogeneity, communication efficiency, privacy preservation, and scalability, are highlighted alongside emerging trends and future research directions. By addressing these challenges, FL has the potential to revolutionize distributed learning, empowering industries to harness the value of data without compromising security or privacy.
Source: HAL
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4406735500