Hands-on Graph Neural Networks

Hands-on Graph Neural Networks

Graphs have long proven to be a powerful data representation across a wide range of applications. Prominent examples include social and transportation networks, as well as small molecules and proteins. Recently, graph neural networks (GNNs) have emerged as a powerful tool for extending the success of deep learning to the graph domain.

In this seminar we aim to cover both the foundations of GNNs as well as more advanced topics such as their limitations and expressiveness, relation to transformers, extensions to geometric graphs, graph generative models and some applications in molecular machine learning.

During the seminar, participants will create talktorials, i.e., self-contained IPython notebooks that explain (teach) a select topic both from a theoretic point of view and in terms of a practical demonstration part. The mandatory part of the seminar will conclude with final talks where participants present their topics to fellow students.

 

Registration

Please use the SIC seminar assignment system to apply for the seminar. If you are a Bioinformatics student, you can also apply via mail.

If you are accpeted and registered for the seminar please do not forget to also register for the seminar in the LSF in time!

 

Kickoff

The kickoff meeting will take place on Monday October 21st, 3:30pm.

 

Topics

The list of topics is preliminary and should not be considered final until October 21st.