Skip to main content
Publications lead hero image abstract pattern


Publication Date

Fourth Quarter 2023

Manuscript Submission Deadline

Special Issue

Call for Papers

5G and beyond (B5G) networks (or so called 6G) are rapidly growing to connect billions of sensors, IoT devices and machines as well as millions of people. B5G networks are expected to support a wide range of unprecedented services, including connected and autonomous systems, eXtended reality (encompassing virtual, mixed, and augmented reality), haptics, telemedicine, flying vehicles, etc. However, the emerging services are coming with various new and heterogeneous requirements in terms of high reliability, ultra low latency, and high data rates, for heterogeneous devices, through both downlink and uplink directions. Thus, B5G networks must provide such requirements in addition to an end-to-end co-design of control, computing, and communication functionalities. Indeed, B5G networks are expected to address unique challenges to transform wireless systems into intelligent and self-configured systems, in order to dynamically/automatically provide and orchestrate control-computing-storage-communication-sensing resources tailored to such emerging services.

Besides, collaborative machine learning is considered as the bedrock of the intelligent B5G networks, where distributed agents collaborate with each other to train learning models in a distributed fashion, without sharing data at a central entity. Despite its broad applicability, the main issue of collaborative learning is the need of local computing to build local learning models as well as iterative information exchange among agents, which may lead to high resource overhead unaffordable in many practical resource-limited systems such as unmanned aerial vehicles (UAVs) and internet of things (IoT). To alleviate this resource issue, it is essential to devise resource-efficient collaborative learning techniques, that can optimize the resource overhead in terms of communication, computing, and energy cost, and hence achieve satisfactory optimization/learning performance simultaneously.

Achieving this objective requires synergistic techniques from various fields, including deep learning, optimization, game theory, wireless communications, and graph/network theory. This Special Issue calls for research contributions on resource-efficient collaborative learning from many perspectives, including algorithm design and analysis, fundamental theories, and practical considerations. We solicit original high-quality contributions on topics including, but not limited to (contributions from industry are highly encouraged):

  • Resource-efficient collaborative reinforcement/deep learning for emerging applications such as flying vehicles and eXtended reality
  • New network architectures and protocols for resource-efficient collaborative deep learning
  • Security-, trust-, and privacy-aware Resource-efficient collaborative learning over B5G/6G networks
  • Impact of agent mobility on resource-efficient collaborative learning
  • Resource-efficient collaborative reinforcement/deep learning for new Radio B5G/6G networks such as Open RAN
  • New techniques for collaborative learning with limited resources such as bandwidth, computing, and energy
  • Edge-enabled resource-efficient collaborative deep learning over B5G/6G networks
  • Network resource management (e.g., radio/energy allocation) for resource-efficient collaborative learning
  • Scalable and resource-efficient collaborative learning for B5G/6G networks
  • Game-theoretic approaches incentivizing resource-limited agents to participate in the collaborative learning process

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: 30 June 2023
Publication Date: Fourth Quarter 2023

Lead Guest Editor

Bouziane Brik
University of Bourgogne, France

Guest Editors

Mehdi Bennis
University of Oulu, Finland

Xianbin Wang
Western University, Canada

Mohsen Guizani
Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, UAE