Looking for PhDs
I am offering a full PhD positions. If you are interested, please send me an email.
- I am invited to give a lecture on Efficient Federated Learning at the REAML Summer School 2022.
- My colleagues Osman Mian, David Kaltenpoth and I published the paper “Regret-based Federated Causal Discovery” at the 2022 ACM SIGKDD workshop on Causal Discovery.
- My colleagues Henning Petzka, Linara Adilova, Cristian Sminchisescu, Mario Boley and I published the paper “Relative Flatness and Generalization” at NeurIPS 2021 (A*, top 7%).
- I received the NeurIPS 2021 outstanding reviewer award.
- My colleagues Xiaoxiao Li, Meirui Jiang, Xiaofei Zhang, Qi Dou, and I published the paper “FedBN: Federated Learning on Non-IID Features via Local Batch Normalization” at ICLR 2021 (A*, top 7%).
- I received a 2021 ICLR reviewer award.
- I was invited as keynote speaker at the Workshop on Data-Centric Dependability and Security (DCDS) where I gave a presentation on Secure and Trustworthy Federated Learning.
- I am co-chair of the Workshop on Parallel, Distributed, and Federated Learning (PDFL’21) at ECMLPKDD 2021 (A, top 18%). We had two fantastic keynotes by Bharat Rao on “Opportunities and Challenges for Federated Learning in Healthcare” and by Blaise Agüera y Arcas on “Social AI and Distributed Ethics“.
- I am honored to be invited to serve as an editorial board member for the Springer journal Machine Learning.
- Our paper “Resource-Constrained On-Device Learning by Dynamic Averaging” won the Best Paper Award at the PDFL’20 workshop. Congratulations to Lukas, and our co-authors.
- My colleagues Pascal Welke, Florian Seiffarth, Stefan Wrobel and I published the paper “hoPS: Probabilistic Subtree Mining for Small and Large Graphs” in SIGKDD 2020 (A*, top 4%).
- I received the NeurIPS 2019 and ICML 2019 best reviewers award.
I am interested in the theoretically sound application of machine learning to distributed data sources which entails four major challenges: The computational complexity of processing very large datasets, the often prohibitive communication required to centralize this data, the privacy-issues of sharing highly sensitive data, and the trustworthiness of the resulting model. My goal is to develop trustworthy machine learning methods. This means that ideally the learning method can be efficiently executed or parallelized and the resulting model is trustworthy in the sense that its performance can be guaranteed, it is robust against adversarial behavior, and its training preserves the privacy of sensitive data. I worked on in-situ methods that process data locally, thus using local processing power, reducing communication, and maintaining data privacy. I developed machine learning, online learning and online optimization algorithms for distributed and decentralized learning, both from batch data and data streams. As learning methods, I used (generalized) linear models, kernel methods, and deep learning. To ensure their trustworthiness, I analyzed them from a learning theory perspective to provide strong guarantees on their behavior and performance. I applied these approaches with partners in the industry on healthcare applications, but also on cybersecurity, material science, and autonomous driving.
Applying machine learning in healthcare poses novel and interesting challenges. Data privacy is paramount, applications require high confidence in model quality, and practitioners demand explainable and comprehensible models. In my research group on Trustworthy Machine Learning I tackle these challenges, investigating novel approaches to privacy-preserving federated learning, the theoretical foundations of deep learning, and the collaborative training of explainable models.
Curriculum Vitae – Highlights
I am leader of the research group Trustworthy Machine Learning at the Institut für KI in der Medizin (IKIM), located at the Ruhr-University Bochum. In 2021 I was a postdoctoral researcher at the CISPA Helmholtz Center for Information Security in the Exploratory Data Analysis group of Jilles Vreeken. From 2019 to 2021 I was a postdoctoral research fellow at Monash University, where I am still an affiliated researcher. From 2011 to 2019 I was a data scientist at Fraunhofer IAIS, where I lead Fraunhofer’s part in the EU project DiSIEM, managing a small research team. Moreover, I was a project-specific consultant and researcher, e.g., for Volkswagen, DHL, and Hussel, and I designed and gave industrial trainings. Since 2014 I was simultaneously a doctoral researcher at the University of Bonn, teaching graduate labs and seminars, and supervising Master’s and Bachelor’s theses. Before that, I worked for 10 years as a software developer.