Course project

Due dates:

  • Proposal, due 11:59pm February 2
  • Project presentation, in class on March 8
  • Writeup, due 11:59pm March 11

The aim of the course project is to give students an opportunity to pick a research area to get hands-on experience with. Students are encouraged to form groups of up to 3 people.

The project does not need to be original, publishable research (though that is of course a good outcome). We encourage you to pick a project that is aligned with your own research interests and learning goals. The bar is simply that it should be a well-defined project that is related in some way to “data-centric machine learning”, broadly construed.

For example, you may choose to do a detailed analysis of the effect of some variables on the performance of some existing method, or to dive into a publicly available dataset and analyze its composition and how that affects models trained on it. The project need not involve experiments: for example, you could write a perspective paper on privacy or legal considerations, or you could write a theory paper that proves properties about particular methods or presents an alternate proof of existing theorems.

Deliverables

For all project deliverables, only one member should submit on Gradescope on behalf of the entire group. Please list all group members in your submission. The same member should consistently be the one submitting for the group.

Barring exceptional circumstances, all group members will get the same grades for the proposal, presentation, and writeup.

Proposal (5% of total grade, due 11:59pm February 2)

  • Maximum 2 pages.
  • Describe the proposed project as well as any preliminary results.
  • Submit as a typeset PDF on Gradescope.

Presentation (10% of total grade, due in class on March 8; add your slides to Google slides before class)

  • Students will give a 4 min presentation in class.
  • The goal of the presentation is to convey the important high-level ideas and takeaways of your project, rather than all the details.
  • All group members should participate in the presentation.
  • To minimize time spent switching computers, add your slides to the Google slides link in Ed before class.

Writeup (35% of total grade, due 11:59pm March 11)

  • 6-8 pages. This should be structured like a typical research paper. In particular, in addition to setup/methods/results, it should also contain an abstract and introduction; a description of related work; a discussion; and references. You may include an optional appendix. References and any appendices do not count towards the page limit.
  • Please follow the ICLR formatting guidelines and use the appropriate style files.
  • You should also upload any code written for your project. Please upload it to Github etc. and include a link in the writeup. The repository should include all relevant code needed to reproduce the results. It should also come with a README file documenting what commands you ran.
  • At the end of your writeup, include a brief Contributions section that details who contributed what to the project. This is just to ensure everyone contributes meaningfully. Unless in exceptional circumstances, all members will share the same grade. This section does not count towards the page limit.

Compute

Students working with a research lab can use their lab resources, if feasible.

Otherwise, options include:

  • Using Google Colab
  • SSH-ing to unagi.cs.washington.edu, which is administered by CSE. This has two GPUs (RTX 3080ti). You may store materials in the “/local1” folder.

Miscellaneous project policy

Using the same project for CSE599J and another class. While the projects can be related and use a shared codebase, you may not submit an identical project as another class project. If you are working on related projects for two courses, you should first make sure that you follow the guidelines for the CSE599J project. Second, if any part of the project is done for another course, please clearly indicate in the Contributions section of your report which part of the project was done for CSE599J and which part was not. Finally, make sure you check with the instructor for the other class as well.

Using your ongoing research as your CSE599J project. This is allowed. In the Contributions section of your writeup, you should indicate this and describe which parts were done prior to the start of the course vs. which parts were done for the course. You will be evaluated on the parts that were done after the start of the course, i.e., you may not reuse a previously completed project.

Collaborating with people outside this course. This is allowed (e.g., your advisor and labmates might be involved in your ongoing research). In the Contributions section of your writeup, you should indicate this and describe which parts you were responsible for. If you are repurposing text or slides that were written by your collaborators, you should also declare this. You will be evaluated on the parts that you worked on.

Generative AI policy. You may use generative AI tools such as Co-Pilot and ChatGPT to assist you with your work, including for code and writing suggestions. However, you should not use them to substantially complete your report, and you are responsible for all final submissions.

These project guidelines are adapted from Tatsunori Hashimoto’s CS329D course at Stanford.