New paper accepted at NeurIPS 2025!
The Flood Complex: Large-Scale Persistent Homology on Millions of Points

📜 Paper: arxiv.org/abs/2509.22432
💻 Speed up your TDA pipeline now: pypi.org/project/floo...

Amazing collab with Florian Graf, @martinuray.bsky.social, Stefan Huber and @rkwitt.bsky.social!

Graph Neural Networks Can (Often) Count Substructures Message passing graph neural networks (GNNs) are known to have limited expressive power in their ability to distinguish some non-isomorphic graphs. Because of this, it is well known that they are...

New paper accepted at ICLR 2025 (Spotlight)!
Graph Neural Networks Can (Often) Count Substructures

📜Paper: openreview.net/forum?id=sZQRUrvLn4

Joint work with Till Schulz and @mlsb-borgwardt.bsky.social
#ICLR2025

Join our new reading group GLOW on the foundations of graph learning. Everybody is welcome! 🌟

Next meeting: Nov 20th! 👀

Speakers: Paolo Pellizzoni and Maya Bechler-Speicher

sites.google.com/view/graph-l...