Johannes Gasteiger, né Klicpera

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

Room: 00.11.053

Phone: +49 (0)89 / 289-17265
Fax: +49 (0)89 / 289-17276
E-Mail: j.gasteiger [at] in.tum.de

GitHub: gasteigerjo
Twitter: @gasteigerjo

Research Focus

• Machine learning for graphs and molecules
• Graph neural networks

Selected Publications

Google Scholar

• Johannes Gasteiger, Florian Becker, Stephan Günnemann
  GemNet: Universal Directional Graph Neural Networks for Molecules
  Conference on Neural Information Processing Systems (NeurIPS), 2021
  [Paper | Code | Project page]
• Johannes Gasteiger, Chandan Yeshwanth, Stephan Günnemann
  Directional Message Passing on Molecular Graphs via Synthetic Coordinates
  Conference on Neural Information Processing Systems (NeurIPS), 2021
  [Paper | Code | Project page]
• Johannes Gasteiger, Marten Lienen, Stephan Günnemann
  Scalable Optimal Transport in High Dimensions for Graph Distances, Embedding Alignment, and More
  International Conference on Machine Learning (ICML), 2021
  [Paper | LCN code | GTN code | Project page]
• Aleksandar Bojchevski*, Johannes Gasteiger*, Bryan Perozzi, Amol Kapoor, Martin Blais, Benedek Rozemberczki, Michal Lukasik, Stephan Günnemann
  Scaling Graph Neural Networks with Approximate PageRank
  SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2020. Oral.
  [Paper | Code | Colab | Project page]
• Johannes Gasteiger, Janek Groß, Stephan Günnemann
  Directional Message Passing for Molecular Graphs
  International Conference on Learning Representations (ICLR), 2020. Spotlight.
  [Paper | Code | Project page]
• Johannes Gasteiger, Stefan Weißenberger, Stephan Günnemann
  Diffusion Improves Graph Learning
  Conference on Neural Information Processing Systems (NeurIPS), 2019
  [Paper | Blog | Code | Project page]
• Johannes Gasteiger, Aleksandar Bojchevski, Stephan Günnemann
  Predict then Propagate: Graph Neural Networks meet Personalized PageRank
  International Conference on Learning Representations (ICLR), 2019
  [Paper | Code | Project page]

*Equal contribution

Research Background

• 2018: Master's thesis: From Graph Convolutional Networks to Weighted Embedding Propagation
• 2016 - 2017: Master's thesis, University of Cambridge: Measuring the Energy Landscapes of Large Granular Systems
• 2015: Bachelor's thesis: Fault Parameterization and Rough Fault Earthquake Simulations in SeisSol
• 2014: Bachelor's thesis: Simulation of electrically pumped GaAs nanowire lasers

Education

• 2015 - 2018: M.Sc. Informatics, Technical University of Munich, passed with high distinction
• 2014 - 2018: M.Sc. Physics (Condensed Matter Physics), Technical University of Munich, passed with high distinction
• 2012 - 2015: B.Sc. Informatics, Technical University of Munich, passed with high distinction
• 2011 - 2014: B.Sc. Physics (Applied and Engineering Physics), Technical University of Munich, passed with high distinction

Academic Honors and Awards

• Scholarship awarded by the German Academic Scholarship Foundation (Studienstiftung des deutschen Volkes)
• Promoted by the best.in.tum program of the Informatics department, Technical University of Munich
• Scholarship awarded by the Max Weber-Program of the State of Bavaria