The forthcoming Sixth Generation (6G) wireless networks are anticipated to deliver exceptionally high data rates ranging from 100 to 1000 Gbps and ultra-low latency of 1 millisecond, leveraging integrated Artificial Intelligence (AI) capabilities. These networks will enable a variety of services, including Holographic Type Communication, Tactile Internet, and remote surgery. However, the dynamic nature of 6G networks, characterized by heterogeneous small cells, poses significant challenges to the reliability required for these services. Static AI-based solutions, which are designed to fit all scenarios and devices, are impractical. Consequently, online learning-based solutions are more suitable for future 6G networks due to their ability to make decisions and adapt to the ever-changing wireless communication environment. This adaptability can be achieved through online-based algorithms such as statistical learning theory, online convex optimization, multi-armed bandits, game theory, and online prediction techniques, which address various 6G challenges. This cost-effective and rapidly converging learning methodology is encouraging researchers and practitioners to apply and evaluate its performance in diverse future wireless communication systems, including millimeter-wave/terahertz communications, device-to-device communications, non-orthogonal multiple access systems, physical layer security, unmanned aerial vehicle communications, cognitive radio systems, reconfigurable intelligent systems, and wireless power transfer.
Online learning-based solutions for V2V, V2I, and V2X scenarios.
Self-learning enhanced underwater communications.
Self-learning aided satellite communications.
Online learning empowered optical communications.
Online learning-based solutions for RIS-aided wireless communication networks.
Online-based wireless resource allocation and mobility management in 6G networks.
Online aided energy harvesting, power control, and wireless power transfer channel estimation and prediction solutions.
Self-learning-based multi-access and modulation (NOMA, OTFS, SCMA, etc.).
Online learning solutions for 6G ultra-high reliability and low-latency communications (URLLC).
Online learning-based solutions for Interference avoidance, management, and cancellation techniques in 6G networks.
Self-learning aided new communications and network technologies in 6G, such as visible light communication (VLC), optical networks, and aerial access networks.
Online learning solutions for efficient computation offloading technologies in 6G networks.
Online learning-based solutions for wireless spectrum sensing, localization, and signal processing in 6G networks.
Communication-efficient online learning techniques (such as transfer, federated, online un/supervised, reinforcement, and meta-learning).
Online enhanced security and privacy issues in 6G communication networks.
The "Innovative Online Learning Algorithms for 6G Wireless Networks" session will offer compelling and interactive keynotes to ignite intellectual discourse, foster collaboration, and drive innovation. Through captivating keynote speeches, thematic presentations, a thought-provoking panel discussion, a visually engaging poster session, and dedicated networking opportunities, participants will actively share knowledge, explore cutting-edge research, tackle challenges, and forge connections with fellow researchers and industry experts. This immersive format will empower attendees to collectively shape the future of AI in the 6G era, unlocking new possibilities and paving the way for groundbreaking advancements at the intersection of 6G technology and novel AI techniques. The Session will be held on the 17th of December 2024 13-14.30 PM Cairo time Zone
Keynote 1: Online Learning Algorithm-Based Optimization of Smart UAV Wireless Networks presented by Khanh Tran Gia Institute of Science Tokyo, Japan
Keynote 2: Machine learning -Aided Downlink Resource Management for UAV-NOMA Systems by Ahmad Gendiaby Ahmad Gendia Kyushu University, Japan
Keynote 3: Unlocking the Power of AI in Wireless Communication: Harnessing Real-World Data for Next-Gen Solutions by Ahmed Nasser KAUST, KSA
Sherief Hashima (Computational Learning Theory Team, RIKEN-AIP, Japan; Sherief.hashima@riken.jp)
Kohei Hatano (Informatics Dept, Kyushu University, Japan; Hatano@inf.kyushu-u.ac.jp)
Hamada Rizk (Information Networking Dept, Osaka University, Japan; Hamada.m.rizk@gmail.com)
Eiji Takimoto (Informatics Dept, Kyushu University, Japan; eiji@inf.kyushu-u.ac.jp)
Mostafa M. Fouda (Department of Electrical and Computer Engineering, Idaho State University, ID, USA; mfouda@ieee.org)
This special session is supported by JSPS KAKENHI Grant Number JP22H03649.