=====================CALL FOR PAPERS========================
2021 GLOBECOM Workshop on
“Wireless Communications for Distributed Intelligence”
=========================================================
WORKSHOP CO-CHAIRS:
- Zheng Chen, Linköping University, Sweden.
- Carlo Fischione, Royal Institute of Technology (KTH), Sweden.
- Osvaldo Simeone, King’s College London, UK.
ADVISORY BOARD:
- Erik G. Larsson, Linköping University, Sweden.
- H. Vincent Poor, Princeton University, USA.
KEYNOTE SPEAKERS:
- Deniz Gündüz, professor at Imperial College London.
- Kaibin Huang, professor at The University of Hong Kong.
Scope and Topics:
Sixth-generation (6G) mobile communications will feature emerging new PHY- and MAC-layer technology, especially ultra-large arrays, cell-free Massive MIMO, RadioWeaves, reconfigurable intelligent surfaces, TeraHertz, and machine-learning-optimized networking solutions. 6G will address connectivity scenarios that 5G never solved -- especially massive access with imperceptible latency and ultra-reliability. More significantly, it is envisioned that 6G will support entirely new use cases, including augmented/virtual reality, and providing a connectivity backbone for decentralized Artificial Intelligence (AI) applications, including distributed sensing, information processing, automatic controls, learning and inference. Due to the distributed nature of the data sets and computational units in wireless networks, state-of-the-art distributed intelligent (DI) services are heavily dependent on the underlying wireless communication protocols. The result is that current and upcoming wireless networks may be greatly stressed when trying to support state-of-the-art DI algorithms. Data or computation information for DI tasks such as distributed automatic controls, training, and inference, especially in dynamic set-up where these computations have to be re-executed frequently, do not need to be transmitted according to the traditional wireless protocols built upon the principle of error-free communication. In such distributed systems, the communication design should be coupled with the eventual tasks performed by machines. This suggests that we need to reinvestigate fundamentally new wireless communication protocols (e.g., signal processing methods for physical layer and medium access controls) capable to achieve efficient and reliable DI task-oriented wireless connectivity.
This workshop aims at covering both theoretical and practical perspectives of wireless communications for distributed intelligence in mobile networks. We invite submissions of original works on the related topics, which include but are not limited to the following:
- Network architecture and protocol design for AI-enabled 6G
- Federated learning (FL) in wireless networks
- Multi-agent reinforcement learning in wireless networks
- Communication efficiency of distributed machine learning (ML)
- Energy efficiency of distributed ML
- Cross-layer (PHY, MAC, network layer) design for distributed ML
- Wireless resource allocation for distributed ML
- Signal processing for distributed ML
- Over-the-Air (OTA) computation for wireless data fusion
- Emerging PHY technologies for OTA computation
- Privacy and security issues of distributed ML
- Adversary-resilient distributed sensing, learning, and inference
- Fault tolerance in distributed stochastic gradient descent (DSGD) systems
- Fault tolerance in multi-agent distributed optimization systems
- Fundamental limits of distributed ML with imperfect communication
IMPORTANT DATES:
Paper submission deadline: August 14, 2021
Paper acceptance notification: September 15, 2021
Camera-ready submission: October 8, 2021
