Machine Learning for Edge Computing with Resource Constraints
02 Apr, 2019 (Tue)
3:00 pm
Room 603, Chow Yei Ching Building

Add to your calendar: iCal, Google Calendar
HKU Campus Map


Prof. K.K. Leung
EEE and Computing Departments
Imperial College, London


Prof. K.K. Leung

Emerging technologies including Internet of Things (IoT), social networking and crowd sourcing generate large amounts of data at the network edge. Machine-learning models can be built from the collected data, to enable detection, classification and prediction of future events. Due to bandwidth, storage and privacy concerns, it is often impractical to send all the data to a centralized location for processing.

In this work, we consider the problem of learning model parameters from data distributed across multiple edge nodes, without sending raw data to a centralized place. Our focus is on a generic class of federated machine-learning models that are trained using gradient-descent based approaches. We analyze the convergence bound of distributed gradient descent, based on which we propose a control algorithm that determines the best trade-off between local update and global parameter aggregation to minimize the loss function for a given resource budget. The performance of the proposed algorithm is evaluated via extensive experiments with real data sets.

If time permits, the speaker will also present a brief overview of current work by his team on reinforcement learning for resource allocation.


Biography of the speaker:

Kin K. Leung received his B.S. degree from the Chinese University of Hong Kong in 1980, and his M.S. and Ph.D. degrees from University of California, Los Angeles, in 1982 and 1985, respectively. He joined AT&T Bell Labs in New Jersey in 1986 and worked at its successor companies, AT&T Labs and Bell Labs of Lucent Technologies, until 2004. Since then, he has been the Tanaka Chair Professor in the Electrical and Electronic Engineering (EEE), and Computing Departments at Imperial College in London. He serves as the Head of Communications and Signal Processing Group in the EEE Department at Imperial. His research focuses on networking, protocols, optimization and modeling issues of wireless broadband, sensor and ad-hoc networks. He also works on multi-antenna systems and cross-layer optimization of these networks.

He received the Distinguished Member of Technical Staff Award from AT&T Bell Labs in 1994, and was a co-recipient of the 1997 Lanchester Prize Honorable Mention Award. He was elected as an IEEE Fellow in 2001. He received the Royal Society Wolfson Research Merits Award from 2004 to 2009 and became a member of Academia Europaea in 2012. Along with his co-authors, he also received a number of best paper awards at major conferences, including the IEEE PIMRC 2012 and ICDCS 2013. He serves as a member (2009-11) and the chairman (2012-15) of the IEEE Fellow Evaluation Committee for Communications Society. He was a guest editor for the IEEE JSAC, IEEE Wireless Communications and the MONET journal, and as an editor for the JSAC: Wireless Series, IEEE Transactions on Wireless Communications and IEEE Transactions on Communications. Currently, he is an editor for the ACM Computing Survey and International Journal on Sensor Networks.


Dr. K.B. Huang

Most seminars are open to the general public, free of charge, unless otherwise stated. Registration is not required. Arrangement for car parking facilities on campus please contact us for details.

For enquiries, please contact:
Department of Electrical and Electronic Engineering,
Room 601, Chow Yei Ching Building,
Pokfulam Road, Hong Kong
Tel: (852) 2859 7093