Scope
The sixth-generation of wireless networks (6G) transforms the way we interact with technology and promises ultra-fast data transmission, enhanced reliability, and comprehensive connectivity. However, this advancement in network capabilities introduces complex challenges, particularly regarding the role of artificial intelligence (AI) in managing, optimizing, and securing these networks. To streamline the implementation of 6G networks, Generative AI (GenAI) and Large Language Models (LLMs) are viewed as critical technologies to transition from being AI-native to becoming intrinsic automation-native, integrating AI deeply into every aspect of network operations. Following the technical report of the European Commission on "Ethics guidelines for trustworthy AI", AI solutions should pursue trustworthiness. This aligns with the principles that emphasize transparency, fairness, and accountability of AI solutions in 6G Networks. In this context, for AI/GenAI automation to be effectively integrated into 6G commercial networks, it is essential to build substantial trust and clarity in the often opaque "black box" nature of AI. By revealing the impact of different inputs on the outputs, AI developers and 6G researchers can identify and rectify biases, inaccuracies, or unforeseen behaviors in AI models. In this intent, eXplainable AI (XAI) techniques and measurements become crucial. They help clarify the reasoning behind AI's predictions and decisions, which are instrumental in enhancing the comprehension of causality within AI models. The concept of explainability in AI is crucial for 6G to enable the trust and reliability required by critical infrastructures and services. They can be applied in different forms within 6G networks, specifically as Ante-hoc, In-hoc, and Post-hoc explanations.
This workshop aims to bring researchers and scientists together to discuss the opportunities and challenges in the research, design, and engineering of trustworthy and transparent AI/GenAI, especially to enable trust between stakeholders through a deeper understanding of the complexities involved in integrating trustworthy AI/GenAI within 6G networks.
Topics of Interest
We seek original completed and unpublished work not currently under review by any other journal/ magazine/conference. This event will focus on, but will not be limited to, the following subjects of interest:
- AI/ML-driven 6G Networks
- Explainable AI/GenAI for 6G
- AI/GenAI for 6G Network Slicing
- AI/GenAI for 6G Non-Terrestrial Networks
- AI/GenAI for Wireless Sensing in 6G
- AI/GenAI for 6G O-RAN
- AI/GenAI for energy efficiency in 6G
- AI/GenAI for security and privacy in 6G
- AI/GenAI for scalable and massive 6G
- AI/GenAI for low latency applications
- GenAI-enhanced semantic communications
- AI/GenAI-based protocol learning
- AI/GenAI for users’ behavior analysis and inference
- GenAI for mobility management and network control
- AI/GenAI-based resource management
- AI/GenAI and Blockchain for 6G
- AI/GenAI integration in 6G PoCs
Keynotes
Prof. Walid Saad, Virginia Tech, USA
Prof. Houbing Herbert Song, University of Maryland, Baltimore County, USA
Important Dates
Paper Submission Deadline: 5 April 2024 30 April 2024 (FIRM)
Paper Acceptance Notification: 14 May 2024
Camera Ready: 1 June 2024
Submission Link
https://edas.info/newPaper.php?c=31484&track=123460
Chairs
Farhad Rezazadeh, CTTC, Spain (Contact: farhad.rh[at]ieee[dot]org)
Hatim Chergui, i2CAT Foundation, Spain
Nguyen Van Huynh, University of Liverpool, United Kingdom
Yongxin Liu, Embry-Riddle Aeronautical University, United States
Toktam Mahmoodi, King's College London, United Kingdom
Dusit Niyato, Nanyang Technological University, Singapore
