5G and Beyond

Machine Learning for the Networks of the Next Decade

Organizers and Chairs:

Alessio Zappone, Large Networks and Systems Group, CentraleSupelec, Université Paris-Saclay, Paris, France
Merouane Debbah, Mathematical and Algorithmic Sciences Lab, Huawei France R&D, Paris, France, & Large Networks and Systems Group, CentraleSupelec, Université Paris-Saclay, Paris, FranceIvan Seskar, Rutgers University, USA

Scope of the Papers

Our society is undergoing a digitization revolution, with a dramatic increase of both Internet users and connected devices. The fifth generation of wireless communication networks will be rolled out shortly, featuring innovative and performing transmission technologies. However, the global IP traffic will continue increasing at an exponential rate between 2020 and 2030, eventually reaching levels that were not envisioned before. In addition, the wireless networks of the next decade will have to provide extremely heterogeneous vertical services (e.g. massive IoT, enhanced mobile broadband, vehicular-to-anything communications, ultra-reliable low-latency communications), which pose very diverse requirements in terms of throughput, latency, energy consumption, etc.

In such a complex scenario, present approaches to network design are not adequate as they entail an unaffordable computational complexity and/or feedback overhead. To address this challenge, a paradigm shift is required towards artificial-intelligence-enabled wireless networks, that can self-manage and self-configure. An emerging technology in wireless communications with the potential of enabling such a paradigm shift is machine learning, in particular through deep learning and artificial neural networks (ANN), thanks to its ability to learn how to execute tasks directly from data, without the need to be explicitly programmed.

Motivated by this background, this special session solicits contributions in line with, but not necessarily limited to, the following topics:

  • Machine learning for end-to-end wireless communication system design.
  • Machine learning for resource management in wireless communications.
  • Machine learning in complex network setups.
  • Machine learning for distributed designs and federated learning.
  • Machine learning for channel acquisition.
  • Machine learning for fingerprinting and positioning.

Submission Guidelines

Full Papers: Full paper submissions of original work (not previously published, or under review at another conference or journal) must not be longer than five pages and will be published in the conference proceedings. Best papers will be fast tracked to Computer Networks (Elsevier) and Ad Hoc Networks (Elsevier) Journals.

Short Papers and Extended Abstracts: Submissions must not be longer than two pages. They should convince the reader that the author(s) would give an exciting presentation and stimulate lively discussion (will be published in the conference proceedings). Note that it is fully expected that extended abstract papers accepted for the session will eventually be extended as full papers suitable for formal academic publication and presentation at other conferences/publications.

Submissions are now accepted through EDAS: [Start a new submission here]

At least one author of each accepted paper/poster/demo must register for the conference and present the paper. Authors are encouraged to use the IEEE Manuscript Templates for Conference Proceedings format for either Latex or Microsoft Word. All full paper submissions will undergo a full TPC review process while all extended abstract submissions will undergo a light review process that will give a greater weight to papers that lend themselves to interactive discussions among workshop attendees.

Important Dates

   Paper submission deadline:   April 28, 2019
   Notification of acceptance:     May 15, 2019
   Camera-ready papers due:    May 22, 2019

Contact Us

You are visitor:

since November 10, 2016.