Call for Papers

Submit a Paper

The advances in communication and smart device technologies, combined with the fast-paced development of industrial informatization, have led to the widespread growth of the Industrial Internet of Things (IIoT). IIoT systems allow for interconnecting distributed devices and machines via communication networks to boost productivity and efficiency. To achieve intelligent IIoT services in industries, federated learning (FL) has emerged as a promising solution for cost-effective and privacy protected intelligent IIoT applications. FL enables the training of high-quality machine learning (ML) models by aggregating local updates from multiple learning clients, such as IIoT devices, without the need for direct access to the local data. This mitigates privacy leakage risks. Furthermore, FL attracts large computation and dataset resources from several IIoT devices to train ML models, thus significantly improving IIoT data training quality, such as accuracy. This approach could not be achieved using centralized AI techniques with limited computational capabilities and less data.

Further effort needs to be dedicated to the research and development of FL in IIoTs as it is currently in its early stages. Hence, this Special Issue (SI) aims to provide a venue to exchange recent advances in this topic. In this SI, we look for original and high-quality research works in the novel area of FL in IIoTs. Theoretical research, real-life experiments, and testbeds on FL-IIoT networks and applications are highly encouraged. Relevant topics include, but are not limited to:

• Applications of FL in IIoT, such as smart manufacturing, smart transportation, smart grid, and smart healthcare.
• Privacy-preserving and security frameworks for FL-IIoT considering unique data transmission protocols between IIoT edge devices, artificial intelligence (AI) software, and industrial computing servers.
• Responsible, explainable, and interpretable FL in IIoT networks.
• Fundamental trade-offs between privacy and FL training efficiency in 6G-IIoT systems.
• Integration of FL with emerging IIoT technologies, e.g., edge computing, blockchain, and intelligent reflecting surfaces.
• Energy efficient and low-latency FL over IIoT devices with extreme resource constraints (e.g., industrial wearable sensors with low computation/communication capabilities).
• Deterministic and probabilistic design methodologies to improve the performance of FL over IIoT networks with unique environmental constraints, such as high temperatures and corrosive substances in manufacturing processes.
• Cross-silo, vertical, and horizontal FL over IIoT networks.

Submission Guidelines

Prospective authors should submit their manuscripts following the IEEE IoT Magazine guidelines. Authors should submit a manuscript through Manuscript Central.

Important Dates

Submission Deadline: 31 March 2024 (Extended Deadline)
First Round Review Due: 1 February 2024
Revision Due: 30 March 2024
Acceptance Notification: 30 April 2024
Final Manuscript Due: 15 May 2024
Publication Date: Third Quarter 2024

Guest Editors

Dinh C. Nguyen
University of Alabama in Huntsville, USA

Viet Quoc Pham
Trinity College Dublin, Ireland

Seyyedali Hosseinalipour (Ali Alipour)
University at Buffalo–SUNY, USA

Zehui Xiong
Singapore University of Technology and Design, Singapore

Tuan M. Hoang Trong
IBM Research, USA

Yonina Eldar
Weizmann Institute of Science, Rehovot, Israel