International Journal of Federated Learning and Distributed IoT Intelligence

Editorial Board Members Current Archives Author Guidelines Editor Guidelines Login Register

About Us

International Journal of Federated Learning and Distributed IoT Intelligence is a peer-reviewed international journal dedicated to advancing research in federated learning, distributed artificial intelligence, Internet of Things, edge intelligence, and privacy-preserving computing. The journal provides a platform for researchers and practitioners to present innovative theories, algorithms, architectures, methodologies, and real-world applications for intelligent distributed systems. It particularly welcomes research addressing the integration of AI, IoT, edge/cloud computing, privacy, security, and next-generation communication technologies.

Aim

The aim of journal is concerned with the development of intelligent, secure, scalable, and decentralized solutions which allow IoT devices and edge systems to collaboratively learn from distributed data without it being necessary to transfer the raw data to a central server. It publishes research and review articles focusing on (but not limited to) the following areas:

Focus and Scope

Federated learning algorithms and architectures Hierarchical and decentralized federated learning Cross-device and cross-silo federated learning Federated transfer learning Federated reinforcement learning Federated deep learning Federated optimization techniques Communication-efficient federated learning Privacy-preserving and secure federated learning

Distributed task offloading, node selection strategies, AI-driven cybersecurity Digital twins and distributed intelligence Blockchain-enabled federated learning Industrial IoT and smart manufacturing Integration with 6G and Next-Gen Networks Distributed AI for IoT Distributed data analytics IoT device collaboration