A Connectionist’s View on Machine Learning

A Connectionist’s View on Machine Learning

Graph structured data is available in abundance to model the world and reason about it. For instance, social networks, chemical molecules, biological networks, and even deep neural networks rely on nodes that exchange information and interact in nonlinear ways.
How can machine learning algorithms make use of such connections?
In this seminar, we will discuss different ways to leverage graph information, either in form of graph neural networks, graph transformers, or as inspiration of sparse neural network architectures. In doing so, we will face typical challenges like their trainability, implicit biases, over-smoothing, over-squashing, etc., and some potential solutions. Not stopping there, we will also use our insights to study contemporary deep learning challenges from a Connectionist's point of view.

---

Organization

In this seminar, students will learn to present, discuss, and summarize papers related to graph neural networks. Specifically, each student will get a single topic assigned to them, consisting of two papers (a lead and follow-up paper). Each student will

• write a short seminar paper on the topic assigned to them, for which the two papers on the topic serve as the starting point;
• prepare a presentation on the topic assigned to them;
• write two short reviews on papers from a different topic, and prepare questions to ask the to the presenter of this paper/topic. The reviews will be shared among the group (in particular with the presenter of the topic).

Important Dates

• Kick-off meeting in the first or second week of the semester (tbd) (to be held online, via zoom).
• The reviews (and questions) must be submitted during the semester.
• The presentations will be organized in a block format during the semester break (dates to be fixed at the kick-off meeting). Participation is mandatory.
• Hand-in of report: tbd, ideally one week after the block course.

Deliverables

• Please note that the submission of all deliverables (within the deadlines) is mandatory to receive a passing grade.
• 2 short reviews (each contributes 15% of your final grade): Write a short review (max 1 page) on one of the papers (not the one that you are presenting) that addresses the following questions:
  1. What is the problem addressed by the paper?
  2. What was done before, and how does the paper improve on previous work?
  3. What are the strengths and the limitations of the techniques in the paper
  4. What part of the paper was difficult to understand?
  5. What are possible improvements or extensions of the techniques in the paper?

  In addition to your review you will have to submit 3 questions that you will ask the presenter of the paper.

• Participation in discussion (10%): Contribute to the discussion during the seminar meeting.

• Presentation (30%): You will prepare and deliver a 20 min presentation (followed by 10 mins question/discussion) of the paper assigned to you. You will have the possibility to get feedback on your slides before the presentation.

• Seminar Paper: (30%) You will write a seminar paper on the topic that you have presented. It must not be longer than 6 pages, not counting references and appendices. Note that appendices are not meant to provide information that is absolutely necessary to understand the paper, but rather to provide auxiliary material. Papers can be shorter, but in general the provided page limit is a good indicator of how long a paper should be.