Stephan Günnemann is a Professor at the Department of Computer Science, Technical University of Munich (TUM) and Executive Director of the Munich Data Science Institute. His main research focuses on reliable machine learning for graphs and temporal data. Stephan is particularly interested in graph neural networks and their application for, e.g., molecular modelling. His works on subspace clustering on graphs as well as adversarial robustness of graph neural networks have received the best research paper awards at ECML-PKDD and KDD. Stephan acquired his doctoral degree at RWTH Aachen University, Germany in the field of computerscience. From 2012 to 2015 he was an associate of Carnegie MellonUniversity, USA. Stephan has received a Google Faculty Research Award, is a Junior-Fellow of the German Computer Science Society, and recipient of the Heinz-Maier-Leibnitz Medal, the highest scientific award of TUM.
AG 1, AG 2, AG 3, INET, AG 4, AG 5, D6, SWS, RG1, MMCI
Graph neural networks (GNNs) have achieved impressive results in various graph learning tasks and they have found their way into many application domains. One of the most impactful applications is their use for molecular systems. In my talk, I will present some of the underlying challenges when using GNNs for such science domains, I will showcase recent GNN solutions covering surrogate models and ab-initio principles, and I will conclude with a discussion of benchmarking practices.