Data Science Seminar

Graph Neural Networks for (Bio-)Medical Applications

The talk will provide a brief introduction to graph neural networks, that is, modern neural networks for graph-structured data. Graph-structured data is ubiquitous in the biomedical domain as it can be used to represent, among others, chemical compounds, proteins, and relationships between various biological concepts. I will address some recent advances, challenges, and applications in the (bio-) medical domain.

Biosketch Dr. Mathias Niepert

Mathias is Research Manager of the Machine Learning group and Chief Research Scientist for AI at NEC Labs Europe in Heidelberg. From 2012-2015 I was a postdoctoral research associate at the Allen School of Computer Science, University of Washington, working primarily with Pedro Domingos. He was also a member of the Data and Web Science Research Group at the University of Mannheim.

Mathias’ research interests include representation learning for graph-structured data, geometric deep learning, probabilistic graphical models, and statistical relational learning. His group's methods are concerned with learning, inducing, and leveraging relational structure with applications in vision, natural language processing, and the (bio-)medical domain.

http://www.matlog.net/ 

to top
powered by webEdition CMS