Skip to the content.

Special Session on Machine Learning for Wireless Communication Systems

The aim of this special issue is to bring together researchers working at the intersection between machine learning and wireless communication (WiC) systems.

Future generations of WiC networks hold many promises: ever-larger data rates, unprecedented guarantees of ultra-reliable and low-latency wireless links, new Internet of Things (IoT) systems, networks of drones and self-driving cars. To hold up to these promises, the wireless ecosystem is evolving towards an incredibly complex and heterogeneous system which poses many new challenges compared to previous generations. A promising approach to successfully handle such a magnitude of complexity and data volume is to develop new network management and optimization tools based on Machine Learning (ML). However, while ML has made tremendous progress over the last decade, traditional methods for optimization and management of wireless systems cannot scale efficiently to the magnitude of complexity and heterogeneity of future wireless connectivity while providing the quality of service that is expected. These challenges have promoted some preliminary investigations which open to a number of possible developments.

This special issue will be an opportunity to expose these and other recent trends in ML for communication systems, and to identify novel trends inspired by the limitation of current approaches to WiC networks.

Future WiC networks must handle (1) immense growth of the wireless traffic due to connectivity of billions of devices (2) massive increase in antenna densification to absorb the upcoming traffic surge while responding to the (3) necessity for high data rates and reliability of services, (4) the fact that future wireless networks will comprise novel sensing and data collection services, (5) non-ideal data availability (irregular time series with gaps and outliers), (6) limited computational and communication dedicated to learning, (7) complex interactions among protocols working at different time scales.


List of confirmed PC members:

Short biography of the organizers

Maurizio Filippone is Associate Professor in the department of Data Science at EURECOM, Sophia Antipolis, France. Maurizio received a Master’s degree in Physics and a Ph.D. in Computer Science from the University of Genova, Italy, in 2004 and 2008, respectively. In 2007, he was a Research Scholar with George Mason University, Fairfax, VA. From 2008 to 2011, he was a Research Associate with the University of Sheffield, (2008-2009), with the University of Glasgow, (2010), and with University College London (2011). Before joining EURECOM in 2015, he was a Lecturer at the University of Glasgow. His research interests include the development of tractable and scalable inference and optimization techniques for machine learning, with a focus on scalable Bayesian inference techniques for Gaussian processes and Deep/Convolutional Neural Networks. Maurizio served as an Associate Editor for the IEEE Transactions on Neural Networks and Learning Systems and Pattern Recognition journals, and he serves as an Area Chair for the AISTATS conference.

Andrea Zanella (S’98-M’01-SM’13) is Full Professor at the Department of Information Engineering (DEI), University of Padova (ITALY). He received the Laurea degree in Computer Engineering in 1998 from the same University and the PhD in 2001. During 2000, he was visiting scholar at the University of California, Los Angeles (UCLA), within Prof. Mario Gerla’s research team. Andrea Zanella long-established research activity is in the field of protocol design, optimization, and performance evaluation of wired and wireless networks. He has authored 200+ papers and has been serving in the editorial board of several top journals, such as IEEE Internet of Things Journal, IEEE Communications Surveys and Tutorials, IEEE Transactions on Cognitive Communications and Networking.

Čedomir Stefanović (Senior Member, IEEE) received the Diploma Ing., Mr.-Ing., and Ph.D. degrees from the University of Novi Sad, Serbia. He is currently a Professor with the Department of Electronic Systems, Aalborg University, where he leads the Edge Computing and Networking Group. He is a principal researcher on a number of European projects related to IoT, 5G, and mission-critical communications. He has coauthored more than 100 peer-reviewed publications. His research interests include communication theory and wireless communications. He serves as an editor for the IEEE Internet of Things Journal.