Course:CPSC532:StaRAI
Computer Science 532: Probabilistic graphical models, knowledge graphs and statistical-relational AI
This is the wiki for our course. We will (try to) build a collaborative research space. For a previous offering see: 2017 pages.
Presentations
Please add your name to one of the following papers. Two presenters per paper, please.
- Jan 20 - Maulik Parmar: "Probabilistic Machine learning and Artificial Intelligence"(Link to Gaussian Processess [1], Link to Paper:[2])
- Jan 27 - Melika Farahani
- Feb 3 - Amin Mohamadi, Andrew Evans
- Feb 10 - Lucca Siaudzionis, Obada Alhumsi
- Feb 24: Lucca Siaudzionis, Maulik Parmar
- Mar 5: Melika Farahani, Obada Alhumsi
- Mar 10: Amin Mohamadi
- Mar 26: Amin Mohamadi
- Mar 31: Lucca Siaudzionis, Melika Farahani
- April 9: Obada Alhumsi, Maulik Parmar
February Assignment/Project
Deadline: February 12. In groups of 1 or 2 you will write a background page on this wiki, that will then be peer reviewed by the rest of the class. You are writing for your peers that have the background assumed for the course. Explain clearly the main ideas using appropriate examples. Please follow the Page Template. Here are some topics; see David if you have other ideas:
- Exact Inference
- Variational Inference
- Inference through Sampling
- Knowledge Graphs
- Causality and Missing Data
- Graph Neural Networks
Peer review
- Deadline: discussions ending February 21 - so others have have time to revise. Please provide feedback to the each other pages in their discussion tab. Think about these questions.
- February 23: evaluation of all pages emailed to David. This should include -- for every page including your own -- a grade out of 20 that one would expect in a graduate course, and a 1 paragraph summary of the rationale for your grade.
March Assignment/Project
Deadline: March 16. Choose 2 papers (with disjoint sets of authors) relevant to the course that reference each other. Please choose a paper by March 5 and email David with your proposal (so that he can help you). The main task is to explain the incremental contribution of the second paper. What did it bring that was new? What did they actually do? How did they justify that it was a contribution (e.g., theorems, experimentation, real-world application). Explain the background needed to understand the contribution. You are writing for your peers that have the background assumed for the course. Explain clearly the main ideas using appropriate examples. Please follow the Page Template.
- R-GCN: GCN's for Relational Data
- Query2Box and Faithful Embeddings for Knowledge Base Queries.
- Table detection in documents.
- Convolutional 2D Knowledge Graph Embeddings
- Blackbox Variational Inference
- Learning Bayesian Networks
April Assignment/Project
Your third and final assignment is to create a hypothesis related to the course and test it. Your result should describe the hypothesis and whether it works. The reader should be able to understand the background, what the the hypothesis is, whether the hypothesis is true, and the evidence you used to come to this conclusion. Your hypothesis can be theoretical or practical.
Rules
- Do not plagiarize; give references to all sources. Put quotes in quotes.
- Give links, but make sure that the pages are readable (with sentences) without following the links.
- Each page can have multiple authors (so it can be a group project).
- You need to add your page to the table of contents in a position that makes sense. Fell free to edit and change the structure of the table of content to give it a coherent structure.
- You will need to give a presentation of at most 6 minutes + 2 minutes for questions for each person (so if you have a group of 3, for example, you need a coherent presentation of 18 minutes where everyone participates); do not go over!
- Please choose a topic that is different from other courses that you have done (or else you need to negotiate with the instructors to make sure you are not counting the same work multiple times).
- You should refer to wiki pages and to other research papers as appropriate.
Key Dates
- March 29 - last day to choose pages
- April 21 - First Draft ready for critiquing. Please critique very other page (there should only be 3 other pages).
Write your comments in the discussion tab of the page. Please give constructive feedback --- give the sort of feedback you would like to receive --- and answer the questions on the evaluation page. Please feel free to respond to them there too, and actually have a discussion. The critiques are not meant to be anonymous; you are meant to be helping each other.
- Sometime in April 23 - 10:00am
- April 23 - Critiques due
- April 27 - Final pages ready for peer marking
- April 29 - Peer marking completed. This is a hard deadline as I need to have marks in by April 30.