Toward 6G in 2030: Edge-AI Co-Design

Lei Jiao
Date and time: 
Thu, Oct 20 2022 - 12:00pm
Location: 
220 Deschutes
Speaker(s):
Lei Jiao
University of Oregon
Host/Committee: 
  • Reza Rejaie

Driven by the 6G vision of “connected intelligence” or “intelligent Internet of intelligent things,” Edge AI embeds model training and inference at the network edge and is becoming a key and indispensable enabling technology to revolutionize the integration of sensing, communication, computation, and intelligence for the next decade. In this talk, first, I will present an overview of my research centered on 5G/6G, including scenarios, problems, methodologies, outputs, and impacts. Next, I will exhibit some of my Edge AI research sponsored by two recent NSF grants. Specifically, we design novel online algorithms to continuously operate federated learning over distributed cloud-edge networks, managing data transference, resource provisioning, and the federated learning process across wireless carriers based only on the predicted inputs about the dynamic system environments, and also conduct a first-of-its-kind study of realizing online transfer learning in edge networks, addressing crucial challenges of online model training, uncertain network contexts, time-coupled model placements, and the balance between resource consumption and model accuracy. Last, I will briefly introduce my ongoing efforts and lay out my vision for future directions.

Biography: 

Lei Jiao is an assistant professor in the Department of Computer Science at the University of Oregon. He is interested in the mathematics of optimization, control, learning, and economics applied to computer and telecommunication systems, networks, and services, spanning edge/cloud computing, artificial intelligence, security, energy, and multimedia. He has published 55 papers, which have attracted 4300+ citations (according to Google Scholar), mainly in top and prestigious journals and conferences such as IEEE Journal on Selected Areas in Communications, IEEE/ACM Transactions on Networking, IEEE Transactions on Parallel and Distributed Systems, IEEE Transactions on Mobile Computing, INFOCOM, MOBIHOC, ICDCS, SECON, ICNP, and IPDPS. His research has been funded by the National Science Foundation, including via a CAREER award. He also received the Ripple Faculty Fellowship, the Best Paper Awards of IEEE LANMAN 2013 and IEEE CNS 2019, and the Alcatel-Lucent Bell Labs UK and Ireland Recognition Award. He has been on the technical program committees of many conferences, including INFOCOM, MOBIHOC, ICDCS, WWW, and IWQoS, and served as the program chairs of multiple symposiums or workshops with INFOCOM and ICDCS. Previously, he worked as a member of technical staff at Nokia Bell Labs in Dublin, Ireland and as a researcher at IBM Research in Beijing, China. He received the PhD degree in computer science from the University of Göttingen, Germany.

Tags: