All publications

Journal article / 2025

TopoBench: A Framework for Benchmarking Topological Deep Learning

Lev Telyatnikov*, Guillermo Bernárdez*, Marco Montagna, Mustafa Hajij, Martin Carrasco, Pavlo Vasylenko, Mathilde Papillon, Ghada Zamzmi, Michael T. Schaub, Jonas Verhellen, Pavel Snopov, Bertran Miquel-Oliver, Manel Gil-Sorribes, Alexis Molina, Victor Guallar, Theodore Long, Julian Suk, Patryk Rygiel, Alexander V. Nikitin, Giordan Escalona, Michael Banf, Dominik Filipiak, Liliya Imasheva, Max Schattauer, Alvaro L. Martinez, Halley Fritze, Marissa Masden, Valentina Sánchez, Manuel Lecha, Andrea Cavallo, Claudio Battiloro, Matthew Piekenbrock, Mauricio Tec, George Dasoulas, Nina Miolane, Simone Scardapane, Theodore Papamarkou

* Equal contribution

Journal of Data-centric Machine Learning Research · Published

TopoBench workflow with connected data-loading, preprocessing, topology-lifting, neural-network, training and logging modules.
TopoBench separates data preparation, model components, training and experiment communication into interchangeable modules. Figure 1 · Telyatnikov, Bernárdez et al. (2025) · Telyatnikov, Bernárdez et al. · CC BY 4.0. Original arXiv v3 figure, also Figure 1 in the published paper.

A shared framework for topological learning

TopoBench organizes experiments into interchangeable components for data loading, topological transformations, models, and evaluation. This makes it possible to compare approaches across representations such as graphs, hypergraphs, and cell or simplicial complexes.

The project provides implementations, documentation, and reproducibility instructions for researchers building and benchmarking topological learning methods.

Cite this work

@article{topobench2025,
  title = {TopoBench: A Framework for Benchmarking Topological Deep Learning},
  author = { Lev Telyatnikov and Guillermo Bernárdez and Marco Montagna and Mustafa Hajij and Martin Carrasco and Pavlo Vasylenko and Mathilde Papillon and Ghada Zamzmi and Michael T. Schaub and Jonas Verhellen and Pavel Snopov and Bertran Miquel-Oliver and Manel Gil-Sorribes and Alexis Molina and Victor Guallar and Theodore Long and Julian Suk and Patryk Rygiel and Alexander V. Nikitin and Giordan Escalona and Michael Banf and Dominik Filipiak and Liliya Imasheva and Max Schattauer and Alvaro L. Martinez and Halley Fritze and Marissa Masden and Valentina Sánchez and Manuel Lecha and Andrea Cavallo and Claudio Battiloro and Matthew Piekenbrock and Mauricio Tec and George Dasoulas and Nina Miolane and Simone Scardapane and Theodore Papamarkou },
  year = {2025},
  journal = {Journal of Data-centric Machine Learning Research},
  volume = {2},
  number = {20},
  pages = {1--39},
  url = { https://data.mlr.press/volumes/02.html }
}