Track Co-Chairs:
Hongjian Sun, University of Durham, U.K., hongjian.sun@durham.ac.uk
Tugba Erpek, Nexcepta, USA, terpek@vt.edu
Wei Bao, University of Sydney, Australia, wei.bao@sydney.edu.au
Description:
As wireless communications and networks become increasingly complex, with a growing number of connected devices, higher data demands, and evolving technologies like 5G/6G and IoT, traditional methods of managing these systems are reaching their limits. On the other hand, networks generate an abundance of data, and new hardware with immense processing capabilities is now available. Machine learning offers a powerful solution to this challenge by enabling networks to learn from data, adapt to changing conditions, and optimize performance in real time. ML outperforms traditional model-based approaches in this context by leveraging vast amounts of network data to identify patterns, optimize performance, and make real-time decisions without relying on predefined models. Unlike model-based methods, which require explicit mathematical formulations and assumptions, machine learning algorithms can adapt to complex, dynamic environments and uncover insights that may not be captured by traditional models. This adaptability allows machine learning to improve the accuracy and efficiency of network operations, leading to better resource management, enhanced signal quality, and more robust communication networks. Research in the field of machine learning for wireless communications is still in its early stages. This track aims to showcase the latest advancements in machine learning for wireless communications and networking, highlight the challenges and opportunities in this emerging field, broaden perspectives, and inspire innovation.
• AI/ML for radio resource management and optimization
• AI/ML for channel estimation, channel modeling, and channel prediction
• AI/ML for wireless communications waveform design
• AI/ML for end-to-end wireless communications
• AI/ML for Internet of Things (IoT) and massive connectivity
• AI/ML for Multi-Access Edge Computing (MEC)
• AI/ML for signal detection and classification
• AI/ML for localization
• AI/ML for routing and management of wireless and sensor networks
• AI/ML for ultra-reliable and low latency communications
• AI/ML for massive MIMO, active and passive reconfigurable intelligent surfaces
• AI/ML for multiple access
• AI/ML for integrated sensing and communications
• AI/ML for physical layer security
• Optimization of neural networks for low-complexity hardware implementation
• Distributed and federated learning in wireless and sensor networks
• Transfer learning and meta learning in wireless and sensor networks
• Large language models for communications and networks
• Privacy-preserving AI/ML for communications and networking
• Trustworthy and explainable AI for communications and networking
TPC list:
• Ahmed Alkhateeb, Arizona State University, USA
• Dola Saha, University at Albany, SUNY, USA
• Eyuphan Bulut, Virginia Commonwealth University, USA
• Yi Shi, Virginia Tech, USA
• Tim O'Shea, Virginia Tech, USA
• Zhengjie Yang, City University of Hong Kong, Hong Kong
• Chuang Hu, University of Macau, China
• Wanxin Gao, City University of Macau, China
• Minglei You, University of Nottingham, UK
• Xiaolin Mou, Shenzhen Tech University, China
• Xuyun Zhang, Macquarie University, Australia