I am ELLIS Doctoral Student @ AIDOS supervised by Prof. Bastian Rieck and co-supervised by Prof. Søren Hauberg.

My research focuses on geometrical and topological methods in machine learning, with a particular interest in theoretically motivated approaches that leverage differential geometry and algebraic topology.

Past work

I started my journey in applications of topological deep learning when working with Dr. Telyatnikov and Dr. Bernardez from REAL AI. We have a preprint out on efficient ways to perform higher-order message passing. Check it out here .

Current work & Thesis

For my M.Sc. thesis I was supervised by Prof. Erik Bekkers from AMLab and Prof. Bastian Rieck. I explored an alternative metric that fully characterizes attributed graphs, it’s relationship to homomorphism counts and how it is complete on expectation.

My takeaway

My thesis topic revolves around the limitations in the current expressivity meassures used to quantify the expressive power of GNNs. I believe that we are being too “square” when looking at graphs and we should step out of the box since this expressivity has some practical limitaitons.

Current work

I am working with an awesome set of researchers I met at LOGML 2025 on bounding the generalization error of GNNs using Rademacher Complexity based on different coloring functions.