Skip to main content
Publications lead hero image abstract pattern


Publication Date

Fourth Quarter 2021

Manuscript Submission Deadline

Special Issue

Call for Papers

Machine learning and data-driven approaches have recently received considerable attention as key enablers for nextgeneration intelligent networks. Currently, most existing learning solutions for wireless networks rely on centralizing the training and inference processes by uploading data collected at edge devices to data centers. However, such a centralized solution may lead to privacy concerns, violate the latency constraints of mobile applications, or may be infeasible due to bandwidth or power constraints of edge devices. To address these issues, distributing machine learning at the network edge provides a promising solution, where edge devices collaboratively train a shared model using real-time generated mobile data. The avoidance of data uploading to a central server not only helps preserve privacy but also reduces network traffic congestion. However, distributed training and inference still require communication between wireless devices and edge servers over wireless links. Therefore, the unreliability of wireless channels and scarcity of radio resources will significantly affect the performance of distributed learning. This special issue aims at gathering cuttingedge contributions to distributed edge learning from both the academia and industry. Thereby, the special issue will, advance on the development of fundamental theories for communication efficient edge learning and the application of distributed learning algorithms to wireless network optimization. Suitable topics for this special issue include, but are not limited to, the following areas:

  • Development of integrated communication and learning algorithms for realizing an intelligent network edge;
  • Wireless network optimization for improving the performance of distributed edge learning;
  • Radio resource management for distributed edge learning;
  • Data compression for distributed edge learning;
  • New theories and techniques such as edge computing, age of information, and multiple-input and multiple-output (MIMO) for improving the performance of distributed edge learning;
  • Distributed reinforcement learning for network decision making, network control, and management;
  • Network protocol design and optimization for distributed edge learning;
  • Distributed edge learning for intelligent signal processing, such as signal detection and channel estimation;
  • Distributed edge learning for user behavior analysis and inference;
  • Joint communication, computing, and sensing for distributed edge learning;
  • New network architectures for supporting distributed edge learning;
  • Privacy and security issues of distributed edge learning;
  • Distributed edge learning in emerging applications, such as the Internet of things, autonomous vehicle systems, intelligent reflecting surfaces, and virtual reality systems;
  • Experimental testbeds for distributed edge learning.

Submission Guidelines

Prospective authors should prepare their manuscripts in accordance with the IEEE JSAC format. Papers should be submitted through EDAS according to the following schedule:

Important Dates

Manuscript Submission: 1 March 2021 (Extended Deadline)
First Round of Review Results Notification: 1 June 2021
Revised Papers Due: 1 July 2021
Final Acceptance Notification: 1 August 2021
Final Manuscript Due: 15 August 2021
Publication: Fourth Quarter 2021

Guest Editors

Mehdi Bennis
University of Oulu, Finland

Mingzhe Chen
Princeton University, USA, and the Chinese University of Hong Kong, Shenzhen, China

Aneta Vulgarakis Feljan
Ericsson Research, Sweden

Deniz Gündüz
Imperial College London, UK.

Kaibin Huang
The University of Hong Kong, Hong Kong

H. Vincent Poor
Princeton University, USA

Walid Saad
Virginia Tech, USA