Guideline & Policy for Project Report

The idea is that this project report should be a manageable amount of work, but that if you want to turn your project into a research paper, everything in the project report will need to be done anyways. If you feel that your project won’t fit into the criteria, please talk to me. There are many ways to make contributions to a field!

Novelty (20%)

Novelty is graded based on a sliding scale and is of course somewhat subjective, but here are a few grading guidelines.

• [~B] A literature review with no new content.
• [~A] A novel combination of existing methods, empirical evidence to support it works well, and explanation of why it works.
• [~A] Applying existing method to a new dataset or problem domain and demonstrate convincing empirical results.
• [~A+] Propose a new problem that is both interesting (or impactful) and challenging (or non-trivial).
• [~A+] Analyzing new properties of existing methods.
• [~A+] Novel methods with evidence-supported motivation - not just making a random tweak for no reason. For full marks, you need to check if the reason you said it should work better is actually the reason why it worked better.
• [~A+] Rigorous theoretical analysis of existing phenomena.

Length (5%)

It should be 6 to 8 pages, not including appendices or bibliography. Don’t be afraid to keep the text short and to the point, and to include large illustrative figures.

Code & Appendix (15%)

You should submit the compressed file (e.g., in zip format) of PDF and code unless you are doing a pure theoretic research project. If that is the case, you should make sure you submit the appendix that include all the proof. You can include as many proofs, extra details, experiments, etc. as you want in the appendices.

Abstract (5%)

It should summarize the main idea of the project and its contributions.

Introduction (5%)

It should clearly state the problem being addressed and why it is important.

Related Work (5%)

It should clearly distinguish what your proposed contribution from previous literature.

Model/Method (20%)

The idea is to make your paper more accessible, especially to readers who are starting by skimming your paper. Here are a few important tips:

• It is very important to include a figure to illustrate the main computation graph of the model. A nice figure would get you some bonus. You must create a new figure, not just use someone else’s, even with attribution!
• Equations are very helpful if you use notations rigorously and concisely.
• Algorithm box is also very useful when your proposed method is hard to parse from pure texts.
• Formal description of the models, loss functions, conjectures, problem domains, theorems, propositions, etc.
• Highlight how your model is different from other approaches via, e.g., using figures or tables.

Experiments (20%)

It should contain one or more from the following list:

• A comparison of your model/method with other baselines on at least one real-world datasets.
• An ablation study on specific design choices.
• An experiment on synthetic datasets demonstrating a property that your model has that a baseline model does not.
• Detailed descriptions of datasets (e.g., how they are collected, key statistics, and properties), evaluation metrics, how you trained your model, and any tricks you used to get it to work.
• Quantitative and or qualitative analysis of experimental results.
• If doing a review, include a table comparing the properties of the different approaches.

Conclusion & Future Work (5%)

It should consist of the main takeaways of your research project. It should also include a discussion on the limitations and potential future directions to improve.