TUESDAY, DECEMBER 7
Keynote Session 1
9:00 - 9:35
Prof. Deniz Gündüz, Imperial College London.
Distributed Learning and Inference over Wireless Channels
Abstract:
Edge devices collect massive amounts of data, opening up new potentials for machine learning applications. Machine learning at the edge can benefit from exploiting both data and processing power distributed across many wireless devices, but this brings about many new challenges including the low latency requirements of learning applications, privacy concerns preventing data sharing, and the impact of noise and interference on the convergence of the learning process. Overcoming these challenges while meeting the requirements of the machine learning tasks calls for a new paradigm of semantic-oriented communication network design tailored for learning applications. In this talk, I will present recent results on efficient distributed inference and training over wireless networks taking into account channel impairments and power and bandwidth limitations of wireless devices, as well as the semantics of the underlying learning tasks. This will involve bringing together novel communication and coding techniques with distributed learning and inference algorithms.
Technical Session 1
9:35 - 10:20
- Relay-Assisted Over-the-Air Federated Learning
Zehong Lin, Hang Liu and Ying Jun (Angela) Zhang (The Chinese University of Hong Kong, Hong Kong)
- Secure Federated Learning Based on Coded Distributed Computing
Shaoliang Zhu, Alia Asheralieva and Md Monjurul Karim (Southern University of Science and Technology, China); Dusit Niyato (Nanyang Technological University, Singapore); Arif Khuhawar (Southern University of Science and Technology, China)
- User-Centric Federated Learning
Mohamad Mestoukirdi (EURECOM, France); Matteo Zecchin (Eurecom, France); David Gesbert (Eurecom Institute, France); Qianrui Li (Mitsubishi Electric R&D Centre Europe, France); Nicolas Gresset (Mitsubishi Electric Research Centre Europe, France)
Keynote Session 2
10:20 - 10:55
Prof. Kaibin Huang, The University of Hong Kong.
6G Intelligent Edge: Shannon Meets Turing
Abstract:
The popularity of mobile devices and densification of wireless networks result in the availability of enormous data and computational resources distributed at the network edge. To leverage the data and resources, machine-learning is deployed at the network edge to train AI models by exploiting the distributed mobile data while preserving their privacy. While computing speeds are advancing rapidly, the communication latency is becoming the bottleneck of fast edge learning. Attempts to overcome the bottleneck have led to the emergence of a new paradigm in wireless communication, “communication efficient edge learning”, which departs from the classic principle of “rate-maximization” and focuses on “fast intelligence acquisition”. In this talk, I will overview new design challenges in the area and highlight some recent advancements in different directions including resource allocation, gradient quantization, feature transmission, wireless data labelling, active data acquisition, and over-the-air computation.
Technical Session 2
11:00 - 12:00
- Joint Annotator Clustering and Power Control for Energy-Efficient Wireless Crowd Labelling
Xiaoyang Li (Southern University of Science and Technology, China); Guangxu Zhu (Shenzhen Research Institute of Big Data, China); Kaifeng Han (China Academy of Information and Communications Technology, China); Yi Gong (Southern University of Science and Technology, Shenzhen, China); Kaibin Huang (The University of Hong Kong, Hong Kong)
- AI-powered Infrastructures for Intelligence and Automation in Beyond-5G System
Leonardo Militano (ZHAW School of Engineering, Switzerland); Anastasios Zafeiropoulos (Institute of Communication and Computer Systems/National Technical University of Athens, Greece); Eleni Fotopoulou (Institute of Communication and Computer Systems / National Technical University of Athens, Greece); Roberto Bruschi (CNIT, Italy); Chiara Lombardo (University of Genoa & CNIT- Research Unit of the University of Genoa, Italy); Andy Edmonds (Terraview GmbH, Switzerland); Symeon Papavassiliou (Institute of Communication and Computer Systems/National Technical University of Athens, Greece)
- The Emergence of Wireless MAC Protocols with Multi-Agent Reinforcement Learning
Mateus Pontes Mota (Nokia Bell Labs & INSA Lyon, France); Alvaro Valcarce (Nokia Bell Labs, France); Jean-Marie Gorce (INSA-Lyon & CITI, Inria, France); Jakob Hoydis (Nvidia, France)
- Distributed Signal Strength Prediction using Satellite Map empowered by Deep Vision Transformer
Haiyao Yu and Zhanwei Hou (University of Sydney, Australia); Yifan Gu (The University of Sydney, Australia); Peng Cheng (La Trobe University & The University of Sydney, Australia); Wanli Ouyang, Yonghui Li and Branka Vucetic (University of Sydney, Australia)
