LEE Wee Sun

Professor
Head, Department Of Computer Science


  • Ph.D. (Australian National University, Canberra, Australia, 1996)
  • B.Eng. (Computer Systems Engineering, University of Queensland, Brisbane, Australia, 1992)

LEE Wee Sun is a professor in the Department of Computer Science, National University of Singapore. He obtained his B.Eng from the University of Queensland in 1992 and his Ph.D. from the Australian National University in 1996. He has been a research fellow at the Australian Defence Force Academy, a fellow of the Singapore-MIT Alliance, and a visiting scientist at MIT. His research interests include machine learning, planning under uncertainty, and approximate inference. His works have won the Test of Time Award at Robotics: Science and Systems (RSS) 2021, the RoboCup Best Paper Award at International Conference on Intelligent Robots and Systems (IROS) 2015, the Google Best Student Paper Award at Uncertainty in AI (UAI) 2014 (as faculty co-author), as well as several competitions and challenges. He has been an area chair for machine learning and AI conferences such as the Neural Information Processing Systems (NeurIPS), the International Conference on Machine Learning (ICML), the AAAI Conference on Artificial Intelligence (AAAI), and the International Joint Conference on Artificial Intelligence (IJCAI). He was a program, conference and journal track co-chair for the Asian Conference on Machine Learning (ACML), and he is currently the chair of the steering committee of ACML.

RESEARCH AREAS

Artificial Intelligence
  • Decision Making & Planning
  • Machine Learning

RESEARCH INTERESTS

  • Machine Learning

  • Planning Under Uncertainty

  • Approximate Inference

RESEARCH PROJECTS

Algorithmic Inductive Bias

Effective deep learning methods are usually structured, e.g. convolutional neural networks. How do we design a structure for a target task? We study the use of task related algorithms. The process, called neuralizing the algorithm, unrolls the execution of the algorithm into a computation graph and replaces some graph elements with learnable approximators, capturing important information flow.


Learning to reason and plan with visual and linguistic inputs

Different subfields of AI, e.g. vision, language, reasoning, learning has been studied separately in depth. However, like the blind men and the elephant, can we truly understand the subject that way? We seek to exploit recent progress, particularly in deep learning, to effectively combine these methods within a single learning architecture. Image credit: Golden Treasury Readers: Primer.


RESEARCH GROUPS

TEACHING INNOVATIONS

SELECTED PUBLICATIONS

  • Mohammed Haroon Dupty, Yanfei Dong, and Wee Sun Lee. PF-GNN: Differentiable particle filtering based approximation of universal graph representations. In International Conference on Learning Representations (ICLR), 2021.
  • Zhen Zhang, Fan Wu, and Wee Sun Lee. Factor graph neural network. Neural Information Processing Systems NeurIPS 2020.
  • Xiao Ma, Peter Karkus, David Hsu, and Wee Sun Lee. Particle filter recurrent neural networks. AAAI Conference on Artificial Intelligence AAAI2020.
  • Peter Karkus, Xiao Ma, David Hsu, Leslie Pack Kaelbling, Wee Sun Lee, and Tomás Lozano-Pérez. Differentiable algorithm networks for composable robot learning. Robotics: Science and Systems 2019.
  • Andrew Wrigley, Wee Sun Lee,Nan Ye.Tensor Belief Propagation. International Conference on Machine Learning ICML 2017.
  • Zhan Wei Lim,David Hsu, and Wee Sun Lee. Shortest Path under Uncertainty: Exploration versus Exploitation. Uncertainty in AI UAI 2017.
  • Nguyen Viet Cuong,Wee Sun Lee, Nan Ye. Near-optimal Adaptive Pool-based Active Learning withGeneral Loss. Uncertainty in AI UAI2014.
  • Haoyu Bai, David Hsu, Wee Sun Lee. Integrated Perception and Planning in Continuous Space: A POMDP Approach. International Journal of Robotics Research, 2014.
  • Nguyen Viet Cuong, Nan Ye, Wee Sun Lee, Hai Leong Chieu. Conditional Random Field with High-order Dependencies for Sequence Labeling and Segmentation. Journal of Machine Learning Research, 2014
  • Adhiraj Somani, Nan Ye, David Hsu, and Wee Sun Lee. DESPOT: Online POMDP Planning with Regularization. Neural Information Processing Systems NIPS 2013.
  • Hanna Kurniawati, David Hsu, and Wee Sun Lee. SARSOP: Efficient point-based pomdp planning by approximating optimally reachable belief spaces. Robotics: Science and Systems, 2008.
  • Bing Liu, Wee Sun Lee, Philip S. Yu, and Xiaoli Li. Partially supervised classification of text documents.International Conference on Machine Learning ICML 2002.
  • Robert Schapire,Yoav Freund, Peter Bartlett, Wee Sun Lee. Boosting the Margin: A New Explanation for the Effectiveness of Voting Methods. The Annals of Statistics, 1998

AWARDS & HONOURS

  • Test of Time Award, Robotics: Science and Systems (RSS) 2021

  • RoboCup Best Paper Award, International Conference on Intelligent Robots and Systems (IROS) 2015

  • First place, Humanitarian Robotics and Automation Technology Challenge (HRATC) 2015

  • First place, POMDP track, ICAPS International Probabilistic Planning Competition (IPPC) in 2011 and again in 2014

  • Google Best Student Paper Award, Uncertainty in AI (UAI) 2014 (as faculty co-author)

  • First place for English lexical sample task and second place in the English coarse-grained all word task, word sense disambiguation evaluation in Semeval-1 2007

  • J.G. Crawford Prize, Australian National University, 1996

MODULES TAUGHT