Principal Investigator Bastian Rieck
AIDOS lab
Our world is full of phenomena that occur at multiple scales. Biomedical research, for instance, commonly observes complex systems at different resolutions, ranging from the macroscopic to the microscopic. Zooming in provides us with the 'fine print' (e.g. individual neurons in a brain), while zooming out lets us see the 'big picture' (e.g. locally-connected networks of neurons, or areas in the brain). For many applications, there is not just one specific scale to consider—relevant features might occur on multiple scales and a priori information about their suitability for a specific task is typically lacking.
With noise being an inevitable part of such investigations, we need tools that enable robust multi-scale analyses. Our research agenda is to create, cultivate, and critique such tools based on topological machine learning techniques, with a specific focus on healthcare topics.
Dr. Bastian Rieck
Principal Investigator, aidos lab
Bastian received both his M.Sc. degree in mathematics (graduated with distinction) and his Ph.D. ('summa cum laude') in computer science from Heidelberg University in Germany. He subsequently worked as a (senior) postdoctoral researcher at the Machine Learning and Computational Biology Lab of ETH Zurich in Switzerland. Bastian's research primarily focuses on the development of topological machine learning techniques in the context of healthcare applications. He also has a keen interest in developing techniques that improve our understanding of neural networks.
Factsheet
Dr. Bastian Rieck
Positions and Career
2021 - present
Principal Investigator at Helmholtz Pioneer Campus, Helmholtz Zentrum München, Germany
2020- 2021
Senior assistant at ETH Zurich, Switzerland
2018-2019
Postdoctoral researcher at ETH Zurich, Switzerland
2017
Researcher at Heidelberg University, Germany
2015-2017
Research assistant at Kaiserslautern University, Germany
2011-2015
Research assistant at Heidelberg University, Germany.
Education
2011-2017
Ph.D. in Computer Science at Heidelberg University, Germany
2005-2011
M.Sc.1 in Mathematics at Heidelberg University, Germany
Honors and Awards
2021
Outstanding reviewer (top 10%) for ICML
Outstanding reviewer (among the top 500 reviewers) for ICLR
2020
Top reviewer for ICML 2020
2019
Outstanding reviewer for the ECML PKDD5 2019 Journal Track
Outstanding reviewer (among the top 400 reviewers) for NeurIPS
Outstanding reviewer (top 5%) for ICML
2018
Outstanding reviewer (among the top 200 reviewers) for NeurIPS
Outstanding reviewer (among the top 100 reviewers) for ICML
2017
Award for the best extended abstract at TopoInVis
2011-2014
Research scholarship, Heidelberg Graduate School of Mathematical and Computational Methods for the Sciences (HGS MathComp), Heidelberg University, Germany
PhD Student
Julius von Rohrscheidt
MSc in Mathematics at Ruprecht-Karls Universität Heidelberg
Research Focus: Robust Topological Representation Learning
Master Thesis: Generalised Intersection Homology Theories
Hobbies: Hiking, Travelling, Festivals, Art
Intern
Ferdinand Hölzl (shared with the Urban lab)
BSc.: Physics at Universität Regensburg
BSc. Thesis: “Fabrication and characterization of patterned constrictions in few-layer NbSe2 crystals"
Research Interest: Modelling air pollution through machine learning
Hobbies: Hiking, Music, Reading, Cooking
Selected Publications
Back to the basics with inclusion of clinical domain knowledge — A simple, scalable, and effective model of Alzheimer’s Disease classification.
S. C. Brüningk†, F. Hensel†, L. Lukas, M. Kuijs, C. R. Jutzeler‡, and B. Rieck‡
Proceedings of the 6th Machine Learning for Healthcare Conference. Proceedings of Machine Learning Research, 2021. In press.
Filtration Curves for Graph Representation
O’Bray†, B. Rieck†, and K. Borgwardt
Proceedings of the 27th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD), 2021. doi:10.1145/3447548.3467442. In press.
Early Prediction of Sepsis in the ICU Using Machine Learning: A Systematic Review
M. Moor†, B. Rieck†, M. Horn, C. R. Jutzeler‡, and K. Borgwardt‡
in Medicine 8, 2021. doi: 10.3389/fmed.2021.607952.
A Survey of Topological Machine Learning Methods
F. Hensel, M. Moor, and B. Rieck
Frontiers in Artificial Intelligence 4, 2021. doi: 10.3389/frai.2021.681108.
Stable Topological Signatures for Metric Trees through Graph Approximations
R. Vandaele, B. Rieck, Y. Saeys, and T. De Bie
Pattern Recognition Letters 147, pp. 85–92, 2021. doi: 10.1016/j.patrec.2021.03.035
Uncovering the Topology of Time-Varying fMRI Data using Cubical Persistence
B. Rieck†, T. Yates†, C. Bock, K. Borgwardt, G. Wolf, N. Turk-Browne‡, and S. Krishnaswamy‡
Advances in Neural Information Processing Systems (NeurIPS), Volume 33, pp. 6900–6912, 2020. Accepted as a spotlight presentation at NeurIPS (top 3% of all submissions). arXiv: 2006.07882 [q-bio.NC]
Graph Kernels: State-of-the-Art and Future Challenges
K. Borgwardt, E. Ghisu, F. Llinares-López, L. O’Bray, and B. Rieck
Foundations and Trends® in Machine Learning 13:5–6, pp. 531–712, 2020. doi: 10.1561/2200000076. arXiv: 2011.03854 [cs.LG]
Contact Us
Helmholtz Pioneer Campus
Helmholtz Zentrum München
Deutsches Forschungszentrum für Gesundheit und Umwelt (GmbH)
Ingolstädter Landstr. 1
85764 Neuherberg
Germany