Litcius/Paper detail

A Survey of Federated Learning for IoT: Addressing Resource Constraints and Heterogeneous Challenges

Sristi Vashisth, Anjali Goyal

2025Informatica10 citationsDOIOpen Access PDF

Abstract

Federated Learning (FL) has emerged as a promising approach to address the challenges of data privacy, security, and scalability in Internet of Things (IoT) environments. This paper provides a comprehensive survey of recent advances in FL for resource-constrained IoT systems, focusing on addressing the challenges of heterogeneous data, limited computational resources, and dynamic network environments. The survey highlights key achievements, including accuracy improvements of over 90% in domains such as smart homes, industrial IoT, and healthcare. Furthermore, FL solutions leveraging edge and fog computing have demonstrated significant energy efficiency improvements, reducing power consumption by up to 30%. A comparative analysis of state-of-the-art FL frameworks is presented, identifying critical research gaps in scalability, adaptive frameworks, and the integration of blockchain for enhanced security. Finally, the paper proposes future research directions to develop robust, efficient, and scalable FL solutions tailored for diverse IoT applications.

Topics & Concepts

Internet of ThingsResource (disambiguation)Computer scienceFederated learningData scienceDistributed computingWorld Wide WebComputer networkPrivacy-Preserving Technologies in DataIoT and Edge/Fog ComputingCaching and Content Delivery