Torben Berndt

Abstract

Many systems in the natural sciences and beyond exhibit complex relational structure that changes over time. Social networks evolve as relationships change, traffic patterns vary throughout the day, and protein–protein interactions shift with cellular conditions. Learning these dynamics from data is a challenging problem. A recent approach in this area, Graph Neural Controlled Differential Equations, extends Neural CDEs from paths on Euclidean domains to paths on graph domains. In this talk, we discuss an extension of this framework that respects the geometry of the underlying set and is equivariant to permutations of the node ordering. We will discuss empirical advantages of this modification, as well as benefits of the formulation as a continuous-time model.

Our speaker

Torben Berndt is a PhD student in the Machine Learning and Artificial Intelligence group at the Heidelberg Institute for Theoretical Studies (HITS). His research focuses on geometric deep learning, with an emphasis on applying mathematical ideas to improve machine learning models for neural dynamical systems and in the physical and natural sciences.

To become a member of the Rough Path Interest Group, register here for free.