Timezone: »
Message passing algorithms are distributed algorithms that operate on graphs, where each node uses only information present locally at the node and incident edges, and send information only to its neighbouring nodes. They are often highly effective in machine learning and are relatively easy to parallelise. Examples include approximate inference algorithms on probabilistic graphical models, the value iteration algorithm for Markov decision process, graph neural networks and attention networks.
This tutorial presents commonly used approximate inference algorithms for probabilistic graphical models and the value iteration algorithm for Markov decision process, focusing on understanding the objectives that the algorithms are optimising for. We then consider more flexible but less interpretable message passing algorithms including graph neural networks and attention networks. We discuss how these more flexible networks can simulate the more interpretable algorithms, providing some understanding of the inductive biases of these networks through algorithmic alignment and allowing the understanding to be used for network design.
Mon 5:00 p.m. - 5:40 p.m.
|
Part 1: Message Passing Overview and Probabilistic Graphical Models
(
Talk
)
SlidesLive Video » |
Wee Sun Lee 🔗 |
Mon 5:40 p.m. - 5:50 p.m.
|
Q&A
|
🔗 |
Mon 5:50 p.m. - 6:00 p.m.
|
Break
|
🔗 |
Mon 6:00 p.m. - 6:16 p.m.
|
Part 2: Markov Decision Process
(
talk
)
SlidesLive Video » |
Wee Sun Lee 🔗 |
Mon 6:16 p.m. - 6:25 p.m.
|
Q&A
|
🔗 |
Mon 6:25 p.m. - 6:30 p.m.
|
Break
|
🔗 |
Mon 6:30 p.m. - 7:20 p.m.
|
Part 3: Graph Neural Networks and Attention Networks
(
Talk
)
SlidesLive Video » |
Wee Sun Lee 🔗 |
Mon 7:20 p.m. - 7:25 p.m.
|
Break
|
🔗 |
Mon 7:35 p.m. - 8:50 p.m.
|
Overall tutorial Q&A and discussion: 45 minutes or until discussion ends
(
Q&A Overview
)
|
🔗 |
Mon 8:30 p.m. - 9:00 p.m.
|
Part 4: Appendix: Proofs and Derivations
(
Recorded video, not to be played live but to be viewed offline b
)
SlidesLive Video » |
Wee Sun Lee 🔗 |
Author Information
Wee Sun Lee (National University of Singapore)
Wee Sun Lee 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, 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 co-chair of the steering committee of ACML.
More from the Same Authors
-
2022 : Efficient Offline Policy Optimization with a Learned Model »
Zichen Liu · Siyi Li · Wee Sun Lee · Shuicheng Yan · Zhongwen Xu -
2023 Poster: Large Language Models as Commonsense Knowledge for Large-Scale Task Planning »
Zirui Zhao · Wee Sun Lee · David Hsu -
2021 : Part 4: Appendix: Proofs and Derivations »
Wee Sun Lee -
2021 : Part 3: Graph Neural Networks and Attention Networks »
Wee Sun Lee -
2021 : Part 2: Markov Decision Process »
Wee Sun Lee -
2021 : Part 1: Message Passing Overview and Probabilistic Graphical Models »
Wee Sun Lee -
2020 Poster: Factor Graph Neural Networks »
Zhen Zhang · Fan Wu · Wee Sun Lee -
2017 Poster: QMDP-Net: Deep Learning for Planning under Partial Observability »
Peter Karkus · David Hsu · Wee Sun Lee -
2015 Poster: Adaptive Stochastic Optimization: From Sets to Paths »
Zhan Wei Lim · David Hsu · Wee Sun Lee -
2013 Poster: DESPOT: Online POMDP Planning with Regularization »
Adhiraj Somani · Nan Ye · David Hsu · Wee Sun Lee -
2013 Poster: Learning with Invariance via Linear Functionals on Reproducing Kernel Hilbert Space »
Xinhua Zhang · Wee Sun Lee · Yee Whye Teh -
2013 Spotlight: Learning with Invariance via Linear Functionals on Reproducing Kernel Hilbert Space »
Xinhua Zhang · Wee Sun Lee · Yee Whye Teh -
2013 Poster: Active Learning for Probabilistic Hypotheses Using the Maximum Gibbs Error Criterion »
Nguyen Viet Cuong · Wee Sun Lee · Nan Ye · Kian Ming Adam Chai · Hai Leong Chieu -
2011 Poster: Monte Carlo Value Iteration with Macro-Actions »
Zhan Wei Lim · David Hsu · Wee Sun Lee -
2010 Session: Oral Session 2 »
Wee Sun Lee -
2009 Poster: Conditional Random Fields with High-Order Features for Sequence Labeling »
Nan Ye · Wee Sun Lee · Hai Leong Chieu · Dan Wu -
2007 Poster: Cooled and Relaxed Survey Propagation for MRFs »
Hai Leong Chieu · Wee Sun Lee · Yee Whye Teh -
2007 Spotlight: Cooled and Relaxed Survey Propagation for MRFs »
Hai Leong Chieu · Wee Sun Lee · Yee Whye Teh -
2007 Spotlight: What makes some POMDP problems easy to approximate? »
David Hsu · Wee Sun Lee · Nan Rong -
2007 Poster: What makes some POMDP problems easy to approximate? »
David Hsu · Wee Sun Lee · Nan Rong -
2006 Poster: Hyperparameter Learning for Graph Based Semi-supervised Learning Algorithms »
Xinhua Zhang · Wee Sun Lee