The speaker, Dr. Jun Jang, is an associate professor at the Hong Kong University of Science and Technology with research interests in wireless communication, networking, mobile edge computing, edge AI, and cooperative AI. He has received numerous awards and is a distinguished lecturer and editor for several journals.

The talk focused on task-oriented communication for edge AI, emphasizing integrating AI and communication technologies to improve network edge applications. Examples included autonomous driving cars and lightweight network designs that allow devices to access external computing power, balance communication and computation, and perform edge co-inference more efficiently.

A key concept discussed was the use of task-oriented communication to reduce communication overhead by focusing on transmitting essential features and inference results, drawing on the analogy of how humans process and store information. This approach is contrasted with traditional data-oriented communication that emphasizes preserving all details, including irrelevant ones.

The presentation covered various technical aspects and challenges of implementing task-oriented communication, including the need for adaptive rate control, network slicing, and the potential of using large language models for task planning and execution at the edge. The approach aims to shift from data-oriented to task-oriented communication to optimize network resources and improve the efficiency of AI applications at the network edge.



Bio:

Jun Zhang received his Ph.D. degree in Electrical and Computer Engineering from the University of Texas at Austin. He is an IEEE Fellow and an IEEE ComSoc Distinguished Lecturer. He is an Associate Professor in the Department of Electronic and Computer Engineering at the Hong Kong University of Science and Technology. His research interests include wireless communications and networking, mobile edge computing and edge AI, and cooperative AI. Dr. Zhang co-authored the book Fundamentals of LTE (Prentice-Hall, 2010). He is a co-recipient of several best paper awards, including the 2021 Best Survey Paper Award of IEEE Communications Society, the 2019 IEEE Communications Society & Information Theory Society Joint Paper Award, and the 2016 Marconi Prize Paper Award in Wireless Communications. He also received the 2016 IEEE ComSoc Asia-Pacific Best Young Researcher Award. He is an Editor of IEEE Transactions on Communications and IEEE Transactions on Machine Learning in Communications and Networking, and was an editor of IEEE Transactions on Wireless Communications (2015-2020).

Link to archive for slides: https://oregon.chapters.comsoc.org/ar...

#edgeai #5g