Reproduce “Topological Deep Learning Challenge 2026: Bridging the Gap” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Guillermo Bernárdez, Lev Telyatnikov, Mathilde Papillon, Marco Montagna, Louisa Cornelis, Louis Van Langendonck, Antonio Purificato, Bruno Neri and 63 more
The authors compare submitted graph neural networks (GNNs) and topological neural networks (TNNs) in a shared pipeline across two tasks on synthetic graphs with varied structural properties. They analyze 34 GNN and 31 TNN submissions. TNNs have lower mean error on triangle counting, while community-detection accuracy is close; these descriptive results do not isolate topology or establish general model-family advantages.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.