Scope of the Workshop

Within a few years, machine learning has become a prominent and rapidly growing research field among wireless communication practitioners, both in academia and industry. The application of machine learning to wireless communications is expected to deeply transform wireless communication engineering. In a discipline traditionally driven by well-established mathematical models, machine learning brings along a methodology that is data-driven and carries a major shift in the way wireless systems are designed and optimized. Research in the field of machine learning for wireless communications are still largely in an exploration phase. While machine learning has already been widely applied in domains such as self-organized networks, its use is only emerging or not yet investigated in many research areas in wireless communications, and its viability for many such wireless applications continues to increase as the basic enabling technology and methods from machine learning continues to grow.

The goal of this workshop is to provide a platform for the latest results in the field of machine learning for wireless communications, encourage fruitful or even controversial discussions on the challenges and prospect of this new research field, open new perspectives and inspire innovation. The call for papers is driven towards the needs of 5G or post-5G wireless networks and associated new communication concepts where machine learning has the potential to be a true enabler. Furthermore, we encourage submissions in algorithmic developments in machine learning that are motivated by the specific constraints posed by wireless communications (e.g. low latency, massive connectivity, distributed and coordinated architectures).

We invite submissions of unpublished works on the application of machine learning to wireless communications topics. The wireless topics are listed below (not necessarily limited to this list). We do not restrict the type of machine learning techniques.

• Construction of radio environmental maps based on machine learning and its applications to wireless communications.

• Machine learning based features extraction for channel estimation, channel modelling, and channel prediction.

• Transceiver design and channel decoding using deep learning

• Machine learning for Internet of things (IoT) and massive connectivity.

• Machine learning for Ultra-reliable and low latency communications.

• Machine learning for Massive MIMO, active and passive Large Intelligent Surfaces (LIS).

• Distributed learning.

• (Deep) Reinforcement Learning for radio resource management.

• Reinforcement Learning for self-organized networks.

• Machine learning driven design and optimization of modulation and coding schemes

• Machine learning techniques for non-linear signal processing

• Low-complexity and approximate learning techniques

• Machine Learning for Edge Intelligence

• Algorithmic advances in machine learning for wireless communications.