Structures are pervasive in science and engineering. Some structures are conveniently observable, e.g., 3D point clouds, molecules, phylogenetic trees, social networks, whereas some are latent or hard to be measured, e.g., parse trees for languages/images, causal graphs, and latent interactions among actors in multi-agent systems. Advanced deep learning techniques have emerged recently to effectively process data in the above scenarios.
This course will teach cutting-edge deep learning models and methods with structures from probabilistic and geometric perspectives. In particular, for observable structures, we will introduce popular models, e.g., Transformers, Graph Neural Networks, with an emphasis on motivating applications, design principles, practical and or theoretical limitations, and future directions. For latent structures, we will introduce motivating applications, latent variable models (e.g., variational auto-encoders), and inference methods (e.g., amortization and search), and learning methods (e.g., REINFORCE and relaxation).
The instructor will present the lectures every week except that students will present their projects in the last two weeks.
Students should ask all course-related questions on Piazza. We will use Canvas to handle submission and evaluation of all reports and project related files.
|TAs||Jiahe Liu, Yuanpei Gao|
|Section 1||1:30pm to 3:00pm, Monday|
|Section 2||1:30pm to 3:00pm, Wednesday|
|Location||Room 103, Chemical and Biological Engineering Building|
|Office Hour||3:30pm to 4:30pm, Tuesday, KAIS 3047 (Ohm)|
Grades will be based on:
Students can work on projects individually, or in groups of up to four (group should be formed as early as possible). Students are strongly encouraged to form groups via, e.g., discussing on Piazza. However, a larger group would be expected to do more than a smaller one or individuals. All students in a group will receive the same grade. Students are allowed to undertake a research project that is related to their thesis or other external projects, but the work done for this course must represent substantial additional work and cannot be submitted for grades in another course.
The grade will depend on the quality of research ideas, how well you present them in the report, how clearly you position your work relative to prior literature, how illuminating and or convincing your experiments are, and well-supported your conclusions are. Full marks will require a novel contribution.
Each group of students will write a short (>=2 pages) research project proposal, which ideally will be structured similarly to a standard paper. You don’t have to do exactly what your proposal claims - the point of the proposal is mainly to have a plan for yourself and to allow me to give you feedback. Students will do a short presentation (roughly 5 minutes for individual, 10 to 15 minutes for a larger group) for their projects towards the end of the course. At the end of the class, every group needs to submit a project report (6~8 pages).
All reports (i.e., paper reading report, proposal, peer-review report, and final project report) must be written in NeurIPS conference format and must be submitted as PDF
Late work will be automatically subject to a 20% penalty and can be submitted up to 3 days after the deadline
UBC values academic integrity. Therefore, all students must understand the meaning and consequences of cheating, plagiarism and other academic offences under the Code of Student Conduct and Discipline.
It is the responsibility of each student to understand the policy for each course work, ask questions to the instructor if it is not clear, and carefully acknowledge all sources (papers, code, books, websites, individual communications) using appropriate referencing style when submitting work.
This is a tentative schedule, which will likely change as the course goes on.
|#||Dates||Lecture Topic||Lecture Slides||Suggested Readings|
|1||Sep. 11||Introduction to Deep Learning||slides||Chapter 13, 14 of PML1 book & DL book|
|Geometric Deep Learning: Invariance, Equivariance, and Deep Learning Models for Sets & Sequences||slides||DeepSets & Transformers & PreNorm & VisionTransformers & SwinTransformers & Chapter 15 of PML1 book|
|Geometric Deep Learning: Graph Neural Networks: Message Passing Models||slides||Part II of GRL book & Chapter 23 of PML book & Chapter 4 of GNN book & GNNs & GGNNs & GAT & Graphormer & GPS|
|Geometric Deep Learning: Graph Neural Networks: Graph Convolution Models||slides||Part II of GRL book & Chapter 23 of PML book & Chapter 4 of GNN book & GCNs & ChebyNet & LanczosNet|
|Geometric Deep Learning: Group Equivariant Deep Learning
|Probabilistic Deep Learning: Auto-Regressive Models||slides||Chapter 11 of GNN book & DGMG & GraphRNN & GRAN|
|Probabilistic Deep Learning: Large Language Models (LLMs)||slides||Stanford CS 324|
|Probabilistic Deep Learning: VAEs and GANs
||slides||VAE & VGAE & GraphVAE & JunctionTreeVAEs & MolGANs|
|Probabilistic Deep Learning: Energy-based Models (EBMs)||slides||RBMs & CD & NVIL & Wake-Sleep & Oops I Took A Gradient|
|Probabilistic Deep Learning: Diffusion Models||slides||Score-based Models & ScoreSDE & DDPM|
I am very open to auditing guests if you are a member of the UBC community (registered student, staff, and/or faculty). I would appreciate that you first email me. If the in-person class is too full and running out of space, I would ask that you please allow registered students to attend.
While there is no required textbook, I recommend the following closely relevant ones for further reading:
In particular, for diffusion models, I recommend the following textbook on the relevant background mathematical materials:
I also recommend students who are self-motivated to take a look at similar courses taught at other universities: