Hands-on Graph Neural Networks

Passing & Grade

To pass the seminar, you have to attend the final talks and:

• write a tutorial notebook for your topic;
• review one other tutorial;
• update your tutorial notebook based on the reviews you received;
• give a short presentation about your topic;
• participate in discussions of other presentations;

… with a passing grade. The final grade is based on your presentation (35%), tutorial notebook (50%), and reviews (15%). You will fail the whole seminar if you receive a failing grade in any of the three parts. If we are undecided, we will also consider the discussion participation.

Tutorial Notebooks

Your first ask is to create a self-consistent tutorial within a Jupyter Notebook that elucidates the key concepts of the selected topic through code examples. The scope of this project may vary depending on the complexity of the topic and references. A complete re-implementation may be achievable or it may be more appropriate to concentrate on a small toy problem focusing on a single concept. The Notebook should be well-structured, containing text and figures that clarify the concepts, as well as well-documented code. Please use the first two weeks after you were assigned a topic, to familiarize yourself with your topics core reference and develop a concept how and what content you want to cover in your tutorial notebook. You will have the opportunity to disuss this concept and receive feedback from your supervisor.

Formalities:

• The tutorial notebook should run on Google Colab and utilize Pytorch.
• We will invite each student to explain their code in an individual meeting. You should be able to explain the code in detail and justify design choices.
• You can download external data (weights, training data) from within your notebook.
• Plagiarism will get you expelled from the seminar and potentially exmatriculated. However, you can discuss solutions with your fellow students and take inspiration from open-source implementations.
• You can also copy&paste small code snippets if they are clearly indicated.
• Comment your code extensively and assign proper names to your functions, variables, and classes.
• Ensure to set seeds to make your code deterministic, and remember to save the final weights for reproducibility.
• Include the URL of the original publications, your name, and any external resources you use.
• The notebooks might be published/
• The deadline for submissions is 23:59 local time.

Reviews

We will assign one tutorial notebook to each student to review. The primary objective of this review is to offer suggestions for enhancements and to identify any potential mistakes or ambiguities, whether they be technical, conceptual, or grammatical in nature. Each review should be approximately one to two pages in length and must be sent to the author and your supervisor via Mail.

Presentation

Identify the key ideas and concepts and give a self-consistent presentation explaining these concepts to your fellow students.

The presentation should be 15 to 20 minutes long.

Here are some suggestions for a good presentation (we will use this as a basis for grading the presentations):

• The goal is to tell a (self-consistent and entertaining) story - not to convince us that you understand the paper.
• Put time and effort into creating visualizations and preparing (running) examples.
• Prioritize concreteness, simplicity, and clarity.
• Focus on intuition, high-level understanding, and contextualization, not on technical details.
• Don’t overcrowd your slides. Try to avoid full sentences and be cautious with bullet points.
• Explore and include supplementary material where it seems useful (literature, youtube, GitHub, medium articles, OpenReview, etc.).
• Use equations only when necessary; use color-coded equations to improve their readability (example).
• Be critical of the authors’ claims, don’t fall for overselling.
• Use slide numbers.
• Submit your slides as .pdf to your supervisor at least one week before your talk.