Research

I am generally interested in the intersection of data management and machine learning. This includes questions such as how to make machine learning scalable, decentralized, and private – ideally at the same time – or how to build data infrastructures that benefit the common good.

My PhD research focuses on designing and implementing cross-silo federated learning systems. The goal of my work is to enable different organizations or individuals to jointly execute federated computations across multiple data silos. More concretely, I work on systems that support the end-to-end process from the initial discovery of interested parties to a final evaluation of the result. For that, I use techniques from data management, data discovery, data integration, algorithmic privacy, and machine learning. Beyond my core PhD research, I have also been exploring other topics in the field of data management in collaboration with colleagues or as part of advising theses.

I am always looking for great students and collaborators. If you are interested in writing a BSc/MSc thesis with me or working as a Research Assistant at DIMA, send me an email explaining your interest and attach an up-to-date CV.