06.11.2026
Best Thesis Award for Sohir Maskey
Recognition for Research on the Theoretical Foundations of Graph Neural Networks
Former MCML Junior Member Sohir Maskey received the Theoretical Foundations of Deep Learning Best Thesis Award of the DFG Priority Programme 2298. The award recognizes his PhD thesis “Theoretical Foundations of Graph Neural Networks: From Expressivity to Generalization,” completed at LMU Munich in the MATH4AI research group of MCML PI Gitta Kutyniok.
His research addressed fundamental questions about graph neural networks: what makes these networks expressive, and when does greater expressivity actually lead to better generalization? Among his theoretical contributions is the NeurIPS 2024 paper “Weisfeiler and Leman Go Loopy: A New Hierarchy for Graph Representational Learning,” for which he was invited to give an oral presentation. During his PhD, MCML supported his participation in international conferences. After completing his PhD, Sohir Maskey joined Aleph Alpha.
Congratulations on this recognition!
Related
09.11.2026
Outstanding Paper Award at EMNLP 2026 for Work on Accent Bias in Audio Language Models
A paper co-authored by MCML PI Valentin Hofmann on accent bias in audio language models won an Outstanding Paper Award at EMNLP 2026.
02.11.2026
Gitta Kutyniok Elected Member of acatech
MCML PI Gitta Kutyniok has been elected a member of acatech, the German National Academy of Science and Engineering.
