Simon Geisler

Technical University of Munich
Department of Informatics - I26
Boltzmannstr. 3
85748 Garching b. München
Germany

Room: 00.11.055
Phone: +49 (0)89 / 289-17277
Fax: +49 (0)89 / 289-17257
E-Mail: simon.geisler [at] in [dot] tum [dot] de

Research Focus

• Robust Deep Learning
• Uncertainty Estimation in Deep Learning
• Machine Learning for Graphs and Sequences

Selected Publications

• Transformers Meet Directed Graphs
  Simon Geisler, Yujia Li, Daniel Mankowitz, Ali Taylan Cemgil, Stephan Günnemann, and Cosmin Paduraru
  International Conference on Machine Learning (ICML), 2023
• Are Defenses for Graph Neural Networks Robust?
  Simon Geisler*, Felix Mujkanovic*, Stephan Günnemann, and Aleksandar Bojchevski
  Neural Information Processing Systems (NeurIPS) 2022
• Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustness
  Simon Geisler*, Johanna Sommer*, Jan Schuchardt, Aleksandar Bojchevski, and Stephan Günnemann
  International Conference on Learning Representations (ICLR), 2022
• Robustness of Graph Neural Networks at Scale
  Simon Geisler, Tobias Schmidt, Hakan Şirin, Daniel Zügner, Aleksandar Bojchevski, and Stephan Günnemann
  Neural Information Processing Systems (NeurIPS), 2021
• Reliable Graph Neural Networks via Robust Aggregation
  Simon Geisler, Daniel Zügner, Stephan Günnemann
  Neural Information Processing Systems (NeurIPS), 2020

* equal contribution

Academic & Professional Experience

Jun-Oct 2022: Research Intern, Google DeepMind, London, UK

2015-2020: Data Scientist, Robert Bosch GmbH, Autonomous Driving and Connected Services, Abstatt, Germany

Jun-Aug 2019: Deep Learning Intern, Bosch Center for Artificial Intelligence (BCAI), Sunnyvale, USA

2016-2019: M.Sc. Data Science, Albstadt-Sigmaringen University in cooperation with University of Mannheim, Germany

Academic Honors and Awards

2014-2016: Gifted student scholarship, Konrad-Adenauer-Foundation

2015: Scholarship, Fulbright