I am Postdoc at Georg-August University Göttingen in the lab of Alexander Ecker. There I am working on using graph learning methods on 3D scans of neurons. The key question, we are trying to answer is how much the 3D morphology of a (mouse brain) neuron tells us about its function and vice versa. I am further interested in basic research about graph learning both from a theoretical and practical perspective.
Before coming to Göttingen I worked as a postdoc at Aarhus University, Denmark on the generalization performance of boosting methods with Kasper Green Larsen. During my PhD in Aachen under the supervision of Martin Grohe, I mainly worked on the algorithmic complexity of learning of logical formulas over graphs. Furthermore, I have been working with practical graph learning in various smaller projects.
ritzert@informatik.uni-goettingen.de
Neural Data Science
Georg-August University Göttingen
Göttingen, Germany
Research
I am generally interested in graph machine learning, both from theory and practice. My recent research focuses on the application of graph learning methods for neurons. In addition, I am working on general graph learning techniques with a special focus on explainability and long-range interactions.
I am further interested in complexity, learning theory, graphs, and lately clustering.Teaching
I am currently giving a lecture on graph learning at Georg-August University Göttingen. Furthermore I am involved in the AI for everyone BIP of the european enlight initiative. Open thesis projects can be found at eckerlab.org together with the projects of my colleages at the group.
Selected Publications
For a full list of my papers, please visit my google scholar page.
Peer-reviewed (selection)- Weisfeiler and leman go neural: Higher-order graph neural networks, AAAI 2019 C. Morris, M. Ritzert, M. Fey, WL. Hamilton, JE. Lenssen, G. Rattan, M. Grohe
- Optimal weak to strong learning, NeurIPS 2022 K. Green Larsen, M. Ritzert
- AdaBoost is not an Optimal Weak to Strong Learner, ICML 2023 M. Møller Høgsgaard, K. Green Larsen, M. Ritzert
- Graph neural networks for maximum constraint satisfaction, Frontiers in AI 2021 J. Toenshoff, M. Ritzert, H. Wolf, M. Grohe
- Learning first-order definable concepts over structures of small degree, LICS 2017 M. Grohe, M. Ritzert
- Where Did the Gap Go? Reassessing the Long-Range Graph Benchmark. J. Tönshoff, M. Ritzert, E. Rosenbluth, M. Grohe
Short CV
- since 2022 PostDoc, Computer Science, Georg-August University Göttingen, Germany
- 2021-2022 PostDoc, Computer Science, Aarhus University, Denmark
- 2016-2021 PhD, Informatik, RWTH Aachen University, Germany
- 2014-2016 Master of Science, Informatik, RWTH Aachen University, Germany
- 2011-2014 Bachelor of Science, Informatik, RWTH Aachen University, Germany