Call for Papers

Distributed machine learning at the network edge has emerged as a promising new paradigm. Various machine learning (ML) technologies will distill Artificial Intelligence (AI) from enormous mobile data to automate future wireless networking and a wide range of Internet-of-Things (IoT) applications. In distributed edge learning, multiple edge devices train a common learning model collaboratively without sending their raw data to a central server, which not only helps to preserve data privacy but also reduces network traffic. However, distributed edge training and edge inference typically still require extensive communications among devices and servers connected by wireless links. As a result, the salient features of wireless networks, including interference and channels’ heterogeneity, time-variability, and unreliability, have significant impacts on the learning performance. To address this issue, we solicit state-of-the-art research contributions that present innovative solutions for addressing the communication issues of distributed edge learning. The research is expected to draw on various methods and techniques from diverse fields, including wireless communications and networking, machine learning, and mobile computing. Thereby, this Special Issue aims to advance the frontiers of distributed edge learning in wireless networks for both fundamental theories and practical applications. Suitable topics for this Special Issue include, but are not limited to the following:

• Joint design of communication, computing, and sensing for distributed edge learning;
• Communication-efficient methods for distributed edge learning, including data compression/quantization/sparsification;
• Distributed edge inference based on machine learning models;
• Distributed edge learning over decentralized network structures, such as hierarchical networks, peer-to-peer networks
• Wireless network resource management for distributed edge learning, including spectrum/power allocation, communication scheduling;
• Distributed edge learning for novel learning paradigms, such as deep/reinforcement/personalized learning;
• Distributed edge learning based on novel physical layer techniques, including over-the-air computation, intelligent reflecting surfaces (IRS), multiple-input and multiple-output (MIMO);
• Distributed edge learning for emerging network applications, such as connected and autonomous vehicles, collaborative robots, multi-user virtual/augmented reality;
• Network architectures and protocols for distributed edge learning;
• Economic issues for distributed edge learning, including incentive mechanisms and game-theoretical analysis
• Security and privacy in distributed edge learning;
• Experiments and testbeds for distributed edge learning.

Submission Guidelines

Prospective authors should submit their manuscripts following the IEEE OJCOMS guidelines. Authors should submit a manuscript trough Manuscript Central.

Important Dates

Manuscript Submission Deadline: 31 March 2023 (Extended Deadline)
Publication Date: Second Quarter 2023

Lead Guest Editor

Xiaowen Gong, Auburn University, USA

Guest Editors

Kaibin Huang, The University of Hong Kong, Hong Kong
Carlo Fischione, KTH Royal Institute of Technology, Sweden
Mingzhe Chen, University of Miami, USA
Jun Zhang, Hong Kong University of Science and Technology, Hong Kong
Wan Choi, Seoul National University, South Korea