Lev Telyatnikov @levtelyatnikov.bsky.social · 25/08/2025We can’t wait to see what the community builds with TopoBench! Star our repo, read the paper, and bring reproducibility to your TDL research. Contributions and feedback are welcome! #OpenSource #Python #AcademicTwitter 064
Lev Telyatnikov @levtelyatnikov.bsky.social · 25/08/2025This was a massive team effort! Developed & led by @levtelyatnikov.bsky.social , @gbg141.bsky.social , Theodore Papamarkou. With major contributions from @Marco Montagna, Mustafa Hajij, Ghada Zamzmi, Michael T. Schaub, @ninamiolane.bsky.social , & @sscardapane.bsky.social , and many others! 164
Lev Telyatnikov @levtelyatnikov.bsky.social · 25/08/2025For a deep dive into our framework for reproducible benchmarking, our methodology, and key findings, check out the full paper. Paper: arxiv.org/abs/246.06642 #MachineLearning #GNN #DataSciencearxiv.org 153
Lev Telyatnikov @levtelyatnikov.bsky.social · 25/08/2025At its core, TopoBench is a framework for robust and fair evaluation in TDL. We’re empowering researchers and practitioners to compare models with confidence and push the field forward, together. 142
Lev Telyatnikov @levtelyatnikov.bsky.social · 25/08/2025Curious about topological liftings? TopoBench lets you experiment with them on your own data! We’ve included 20+ liftings from last year’s TDL Challenge @TAGinDS, @PyT_Team_. Explore them all in our Wiki: github.com/geometric-in... #TDAgithub.comStructural LiftingsTopoBench is a Python library designed to standardize benchmarking and accelerate research in Topological Deep Learning - geometric-intelligence/TopoBench 143
Lev Telyatnikov @levtelyatnikov.bsky.social · 25/08/2025Struggling with reproducible benchmarks in TDL? We’ve got you covered. 12+ models tested on 22+ diverse, cross-domain datasets. Tutorials to get you started with topology & higher-order homophily Webpage/Docs: geometric-intelligence.github.io/TopoBench/geometric-intelligence.github.ioTopoBenchTopoBench: A comprehensive benchmarking framework for Topological Deep Learning models and datasets. 133
Lev Telyatnikov @levtelyatnikov.bsky.social · 25/08/2025Delighted to announce TopoBench has been accepted to DMLR! It’s a modular library for Topological Deep Learning, built to provide reproducible, cross-domain benchmarks and accelerate research. GitHub: github.com/geometric-in... #AI #DeepLearninggithub.comGitHub - geometric-intelligence/TopoBench: TopoBench is a Python library designed to standardize benchmarking and accelerate research in Topological Deep LearningTopoBench is a Python library designed to standardize benchmarking and accelerate research in Topological Deep Learning - geometric-intelligence/TopoBench 1134
Reposted by Lev TelyatnikovMartin Carrasco @martin.topology.rocks · 26/05/2025TDL actually works at scale! And we believe 𝐇𝐎𝐏𝐒𝐄 lays the foundation for broad applications of TDL ✨ 📭 Reach out for collaborations Special thanks to @levtelyatnikov.bsky.social and @gbg1441 and the team @ninamiolane.bsky.social and @Coerulatus :) (6/6) 075
Reposted by Lev TelyatnikovNina Miolane @ninamiolane.bsky.social · 27/05/2025At last Topological Neural Networks are fast🚀 HOPSE builds an encoder for combinatorial complexes, enabling topological deep learning (TDL) w/o the usual computational cost. A major step forward for TDL! @martinca.bsky.social @gbg141.bsky.social @marcomonga.bsky.social @levtelyatnikov.bsky.social 074
Reposted by Lev TelyatnikovGeometric Intelligence Lab @geometric-intel.bsky.social · 27/05/2025🚨 New preprint from the lab! Discover fast topological neural networks, that leverage higher order structures without the usual computational burden! By @martinca.bsky.social @gbg141.bsky.social @marcomonga.bsky.social @levtelyatnikov.bsky.social @ninamiolane.bsky.social 022
Lev Telyatnikov @levtelyatnikov.bsky.social · 26/05/2025Absolutely proud of this work! Huge thanks to @gbg141.bsky.social @ninamiolane.bsky.social @marcomonga.bsky.social — and of course @martinca.bsky.social, who drove the project, learned on the fly, and kept the enthusiasm high at every turn! 185
