Scientific Report on TUM-IAS Fellowship
The Focus Group Data Mining and Analytics studies principles for robust and trustworthy machine learning. Specifically, we are interested in learning principles for non-independent data such as graphs and temporal data. As the number of machine learning models deployed in the real world grows, questions regarding their robustness become increasingly important. Are the models’ predictions reliable or do they change if the underlying data gets slightly perturbed? In particular, for safety-critical and scientific use cases, it is essential to assess the models’ vulnerability to worst-case perturbations – ensuring that we can trust the machine learning model even in the worst case. full report …
Short CV
Stephan Günnemann acquired his doctoral degree in 2012 at RWTH Aachen University in the field of computer science. From 2012 to 2015 he was an associate of Carnegie Mellon University, USA; initially as a postdoctoral fellow and later as a senior researcher. Prof. Günnemann has been a visiting researcher at Simon Fraser University, Canada, and a research scientist at the Research & Technology Center of Siemens AG. In 2015, Prof. Günnemann set up an Emmy Noether research group at TUM Department of Informatics. He has been a professor at TUM since 2016.
Selected Awards
- 2020, Google Faculty Research Award in Machine Learning
- 2018, ACM SIGKDD Best Research Paper Award
- 2017, Junior-Fellow of the German Computer Science Society
- 2017, Microsoft Azure Research Award
- 2015, Member of the Emmy Noether Program of the German Research Foundation (DFG)
- 2013, Recipient of a German Academic Exchange Service (DAAD) Research Fellowship
- 2013, Dissertation Award of the German Computer Science Society
- 2013, Borchers Badge for Doctoral Dissertation, RWTH Aachen University
- 2012, Recipient of a German Academic Exchange Service (DAAD) Research Fellowship
- 2011, Best Paper Award at the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases
Research Interest
Stephan Günnemann conducts research in the area of machine learning and data analytics. His main research focuses on how to make machine learning techniques reliable, thus, enabling their safe and robust use in various application domains. Prof. Günnemann is particularly interested in studying machine learning methods targeting complex data domains such as graphs/networks and temporal data.
Selected Publications
- Bojchevski A, Klicpera J, Günnemann S: "Efficient Robustness Certificates for Discrete Data: Sparsity-Aware Randomized Smoothing for Graphs, Images and More". International Conference on Machine Learning. 2020.
- Klicpera J, Weißenberger S, Günnemann S: "Diffusion improves graph learning". Advances in Neural Information Processing Systems. 2019; 13354-13366.
- Bojchevski A, Günnemann S: "Certifiable Robustness to Graph Perturbations". Advances in Neural Information Processing Systems. 2019; 8319-8330.
- Zügner D, Akbarnejad A, Günnemann S: "Adversarial Attacks on Neural Networks for Graph Data". ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2018: 2847-2856.
- Bojchevski A, Shchur O, Zügner D, Günnemann S: "NetGAN: Generating Graphs via Random Walks". International Conference on Machine Learning. 2018; 609-618.
Publications as TUM-IAS-Fellow
