`

Timezone: »

 
Tutorial
Message Passing In Machine Learning
Wee Sun Lee

Mon Dec 06 05:00 PM -- 09:00 PM (PST) @ None

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. - 5:50 p.m.
Part 1: Message Passing Overview and Probabilistic Graphical Models (Talk)
Wee Sun Lee
Mon 5:50 p.m. - 6:00 p.m.
Q&A
Mon 6:00 p.m. - 6:05 p.m.
Break
Mon 6:05 p.m. - 6:30 p.m.
Part 2: Markov Decision Process (talk)
Wee Sun Lee
Mon 6:30 p.m. - 6:35 p.m.
Q&A
Mon 6:35 p.m. - 6:40 p.m.
Break
Mon 6:40 p.m. - 7:40 p.m.
Part 3: Graph Neural Networks and Attention Networks (Talk)
Wee Sun Lee
Mon 7:40 p.m. - 7:45 p.m.
Break
Mon 7:45 p.m. - 8:30 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)
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, approximate inference and planning under uncertainty. 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