<![CDATA[This study presents a comprehensive bibliometric analysis of federated learning within distributed computing, aiming to explore research trends, intellectual structures, and emerging themes in the field. Data were retrieved from the Scopus database covering publications from 2010 to 2025. The analysis employs performance metrics and science mapping techniques, including co-authorship, keyword co-occurrence, citation, and density visualization using VOSviewer. The results reveal a significant increase in research output, particularly after 2018, driven by the growing demand for privacy-preserving machine learning and the expansion of edge computing and Internet of Things (IoT) ecosystems. Key research clusters focus on data privacy, system optimization, distributed machine learning, and real-world applications such as healthcare and industrial systems. The findings also highlight strong global collaboration networks and the dominance of contributions from leading countries such as China and the United States. Furthermore, recent trends indicate a shift toward integrating federated learning with advanced technologies such as blockchain, reinforcement learning, and energy-efficient systems. This study provides a structured overview of the field and offers valuable insights for researchers and practitioners in identifying research gaps and future directions in federated learning within distributed computing.]]>
Copyrights © 2026
