Dr. Nguyen H. Tran
Title: Federated Machine Learning for Intelligent Edge Networks
Bio:
Nguyen H. Tran (S’10-M’11-SM’18) received BS and Ph.D degrees, from HCMC University of Technology and Kyung Hee University, in electrical and computer engineering, in 2005 and 2011, respectively. He was an Assistant Professor with the Department of Computer Science and Engineering, Kyung Hee University, from 2012 to 2017. Since 2018, he has been with the School of Computer Science, The University of Sydney, where he is currently a Senior Lecturer. His research interests include distributed computing, machine learning, and networking. He received the best KHU thesis award in engineering in 2011 and several best paper awards, including IEEE ICC 2016 and ACM MSWiM 2019. He received the Korea NRF Funding for Basic Science and Research 2016-2023 and ARC Discovery Project 2020-2023. He was an Editor of IEEE Transactions on Green Communications and Networking from 2016 to 2020, and an Associate Editor of IEEE Journal of Selected Areas in Communications 2020 in the area of distributed machine learning/Federated Learning.
Abstract:
Watch Dr. Nguyen H. Tran’s keynote invitation
Emerging Internet of Things (IoT) applications such as augmented reality, autonomous driving, surveillance, and industry 4.0 generate significant amounts of data. The effective deployment of such applications is thus reliant on the use of advanced machine learning techniques so as to properly exploit the generated data. However, traditional machine learning schemes use centralized training data at a data center which requires data transfer from a massive number of distributed IoT devices to a third-party location which raises serious privacy concerns and can be inefficient in its use of communication resources. Relating to these privacy and communication concerns, this talk will introduce the state-of-the-art techniques of distributed and edge-assisted learning algorithms in federated learning (FL) that will play a critical role in the next generation of intelligent edge computing network.