iiinova — where your digital self keeps evolving

Reposted by @limbeckkat.bsky.social

Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 11/11/2025

This is an exciting collaboration with @limbeckkat.bsky.social, Lydia Mezrag, and Guy Wolf, supported by @tum.de, @helmholtzmunich.bsky.social, @mila-quebec.bsky.social, @umontreal.ca, and @unifr.bsky.social. 🖖 🧵6/6

071

Reposted by @limbeckkat.bsky.social

Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 11/11/2025

Want to learn more? 🌟Check out our paper, code, blog post, and video!🌟 📜 Paper: arxiv.org/abs/2506.11700 🖥️ Code: github.com/aidos-lab/ma... 📄 Blog: aidos.group/blog/magedge/ 📽️ Video: youtu.be/uQts_HR1uSA 🧵5/6

youtu.be

Geometry-Aware Edge Pooling for Graph Neural Networks

YouTube video by Bastian Grossenbacher-Rieck

151

Reposted by @limbeckkat.bsky.social

Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 11/11/2025

And it just works! Our pooling methods perform well across tasks and… 🏆 …reach top classification and regression performance. 🔥 …retain this robust performance across pooling ratios. ✨ …preserve graph structure and spectral properties 🧵4/n

111

Reposted by @limbeckkat.bsky.social

Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 11/11/2025

But…how? 🔍 We contract the most redundant edges that are least relevant for the graph’s structural diversity as measured by the magnitude or spread of a graph. 🧵3/n

A brief explanation of how we perform pooling.

111

Reposted by @limbeckkat.bsky.social

Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 11/11/2025

Why do we need structure-aware pooling, anyway? 🔮Our methods, MagEdgePool and SpreadEdgePool, faithfully preserve the original graphs’ geometry. Alternative pooling layers destroy graph structure to varying extents. 🧵2/n

We are pretty good at preserving structure in graph datasets!

121

Reposted by @limbeckkat.bsky.social

Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 11/11/2025

Big graph, little compute? In our #NeurIPS2025 paper we propose geometry-aware edge-contraction-based pooling methods for GNNs. Our methods preserve graph structure, make interpretable pooling choices, and ensure robust performance at downstream tasks. 🧵1/n

1134

Reposted by @limbeckkat.bsky.social

Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 07/02/2025

🔥 Friends, I finally collected them all. As of last week, I am finally tenured. 🔥 Thanks to everyone who supported me, in particular my great team (aidos.group), my equally great collaborators, and everyone else who brought their offerings to the fickle fates of academia! #Academia #Tenure

After all these years, finally, I have them all: Tenure, an excellent research group, and the best haircut.

5382

Reposted by @limbeckkat.bsky.social

Emily Simons @emsimons.bsky.social · 19/12/2024

Hi! 👋 Emily Simons here, Fulbright Student Researcher with the AIDOS Lab at #HelmholtzMunich. Happy to be sharing my first contribution to AIDOS in this 🧵. Say hiya to SCOTT, the perfect holiday (software) package🎁for the #curvature and #graph enthusiast in your life. 🧵1/n

172