About me

I am a PhD candidate at the Relational ML Lab, under the supervision of Dr. Rebekka Burkholz, at the CISPA Helmholtz Center for Information Security in Saarland, Germany.

I am interested in the theory of machine learning, with a focus on addressing the challenges of generalization in graph learning. Most recently, I have been looking into the dual role of input graphs as both data and computational models in graph neural networks, and the implications of rewiring them under different criteria.

You can read my CV here.

News

• September 2024: First-author paper accepted at NeurIPS’24: Spectral Graph Pruning Against Over-Squashing and Over-Smoothing. Also accepted at WiML workshop: GNNs Getting ComFy.

• June 2024: Speaker at Helmholtz AI Conference 2024: AI for Science (HAICON’24).