Yan Scholten
Technical University of Munich
Department of Computer Science - I26
Boltzmannstr. 3
85748 Garching b. München
Germany
Room: 00.11.065
E-Mail: scholten [at] in.tum.de
Website: yascho.github.io
Research Interests
- Reliable machine learning
- Conformal prediction
- Machine unlearning
- Machine learning on graphs
Selected Publications
Full list on Google Scholar
- Provably Reliable Conformal Prediction Sets in the Presence of Data Poisoning
- Hierarchical Randomized Smoothing
Yan Scholten, Jan Schuchardt, Aleksandar Bojchevski, Stephan Günnemann
Conference on Neural Information Processing Systems (NeurIPS), 2023
[PDF | Project page | Code] - (Provable) Adversarial Robustness for Group Equivariant Tasks:
Graphs, Point Clouds, Molecules, and More
Jan Schuchardt, Yan Scholten, Stephan Günnemann
Conference on Neural Information Processing Systems (NeurIPS), 2023
[PDF | Project page] - Assessing Robustness via Score-Based Adversarial Image Generation
Marcel Kollovieh, Lukas Gosch, Yan Scholten, Marten Lienen, Stephan Günnemann
[Preprint], 2023 - Randomized Message-Interception Smoothing: Gray-box Certificates for Graph Neural Networks
Yan Scholten, Jan Schuchardt, Simon Geisler, Aleksandar Bojchevski, Stephan Günnemann
Conference on Neural Information Processing Systems (NeurIPS), 2022
[ PDF | Project page | Code ]
Education
- 2019-2022: M.Sc. Informatics - Technical University of Munich (passed with high distinction)
- 2015-2019: B.Sc. Computer Science - Paderborn University (passed with distinction)
Academic Honors and Awards
- 2023: Admission to the Konrad Zuse School of Excellence in Reliable AI
- 2019: Deutschlandstipendium awarded by the Technical University of Munich
- 2018: RISE worldwide scholarship awarded by DAAD
- 2018: Deutschlandstipendium awarded by Studienfonds OWL