← All researchPublication · Topological deep learning

Curvature-guided Graph-to-Hypergraph Structural Lifting Alleviates Over-Squashing in Graph Learning

Michael BanfMichael Banf
10 to 12 June 2026 · IOCMA 2026, 2nd International Online Conference on Mathematics and Applications (MDPI) · poster

The lifting method, presented to the applied mathematics community.

The research

Graphs squeeze information through bottlenecks. We use curvature to find a network's backbones and lift them to hyperedges, so distant parts of a graph can talk.

What it changes in practice

A company's knowledge graph has bottlenecks too. Curvature tells us where answers get squashed before they reach the person who needs them.

More in Topological deep learning

Contact

For projects, partnerships, press and open roles.

Goethestr. 68, 80336 Munich · +49 89 12137977 · contact@perelyn.com
Contact

Request a conversation. We’ll be in touch.

For projects, partnerships, press and open roles.

Topic
* Required
You are in good company:
Deutsche BahnE.ONHenkelLiebherrMarc O'PoloMunich ReREWEZEISSRocheOn