Virtual Talk with Sandra Kiefer


Graph Neural Networks (GNNs) are a machine learning architecture to learn functions on graphs. For example, since problem instances for combinatorial optimisation tasks are often modelled as graphs, GNNs have recently received much attention as a natural framework for finding good heuristics in neural optimisation approaches.
The question which functions can actually be learnt by message-passing GNNs and which ones exceed their power has been studied extensively. In this talk, I will consider it from a graph-theoretical perspective. I will survey the Weisfeiler—Leman algorithm as a combinatorial procedure to analyse and compare graph structure, and I will discuss some results concerning the power of the algorithm on natural graph classes. The findings directly translate into insights about the power of GNNs and of their extensions to higher-dimensional neural networks.



Sandra Kiefer is a Glasstone Research Fellow in Computer Science at the University of Oxford and a Junior Research Fellow with Jesus College in Oxford. Her main research interests are algorithmic and structural graph theory as well as logic in computer science. In an application, she explores the reconstruction of biochemical networks by means of combinatorial algorithms and machine learning.
For her dissertation on combinatorial and logical approaches to graph comparison, Sandra received the Ackermann Award 2021. After her Ph.D. studies at RWTH Aachen University, she was a postdoctoral researcher at RWTH Aachen University and at the University of Warsaw, as well as a research group leader at Max Planck Institute for Software Systems in Saarbrücken.


Zoom Registration

Please register with to receive the Zoom login.

Back to the event overview