Relational Intelligence: Geometric Deep Learning and the Rise of Agentic Graphs

Relational Intelligence: Geometric Deep Learning and the Rise of Agentic Graphs

The future of machine learning is relational, where intelligent systems thrive through collaboration, defined by the relationships of agents. In this seminar, we will first study Graph Neural Networks (GNNs) as a special case of agentic networks to gain insights into design principles for effective agent collaboration and expose novel risks that are introduced by the interconnectedness. We’ll discuss the role of agentic diversity, the risks of oversmoothing, and emerging challenges like adversarial attacks and error propagation cascades. In the spirit of the seminar, together, let’s gain insights into how we can build robust, collaborative networks and safeguard them from harm as they evolve.

Organization

In this seminar, students will learn to present, discuss, and summarize papers related to graph neural networks and agentic systems. 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: Monday, Apr 13, at 17:15 (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. Participation is mandatory. Tentative time (to be fixed at the kick-off meeting): Aug 20-21, 2026 in E9 1 (CISPA main building).
• Hand-in of report: tbd, ideally one week after the block course.

Deliverables

• 2 short reviews (each contributes 10% 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 (20%): Contribute to the discussion during the seminar meeting.

• Presentation (40%): 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: (20%) 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.