Topological Deep Learning Challenge 2025: Expanding the Data Landscape

Guillermo Bernárdez, Lev Telyatnikov, Mathilde Papillon, Marco Montagna, Raffael Theiler, Louisa Cornelis, Johan Mathe, Miquel Ferriol, Pavlo Vasylenko, Jan-Willem Van Looy, Lucia Testa, Bruno Neri, Donatella Genovese, Melanie Weber, Amaury Wei, Alessio Devoto, Alexander Weers, Robert Jankowski, Loris Cino, David Leko, Michael Banf, Jonas Müller, Thomas Grapentin, Taejin Paik, Abhijeet Dutta, Hugo Walter, Thomas Vaitses Fontanari, Ali Ghasemi, Dario Loi, Haitz Sáez de Ocáriz Borde, Gabriela Aguilar-Argüello, Giovanni B. da Rosa, Théo Saulus, Eric Rubiel Dolores-Cuenca, Leonardo Di Nino, Pierrick Leroy, Mario Edoardo Pandolfo, Andrea Cavallo, Yu Qin, Pavel Snopov, Amirreza Akbari, Ixchel Meza-Chávez, Louis Van Langendonck, Jared Able, Maria Yuffa Meshcheryakova, Henry Tsay, Luka Benić, Dominik Filipiak, Patrick Liu, Huidong Liang, Alexsandro Santos da Rosa Jr., Tiziana Cattai, Henrique M. Borges, Enrico Grimaldi, Manuel Lecha, Claudio Battiloro, Xuan-Chen Liu, Raj Deshpande, Graham Johnson, Igor Morgunov, Hugo Micheron, Rémi Devaux, Antoine Jardin, Tegan Emerson, Olga Fink, Nina Miolane
Proceedings of the 1st Conference on Topology, Algebra, and Geometry in Data Science(TAG-DS 2025), PMLR 321:4-14, 2026.

Abstract

This paper describes the 2025 edition of the Topological Deep Learning Challenge: Expanding the Data Landscape, hosted at the first Topology, Algebra, and Geometry in Data Science (TAG-DS) Conference. This year’s challenge aimed to address the data bottleneck in the field by systematically expanding the ecosystem of Topological Deep Learning (TDL). Powered by TopoBench, the challenge was organized into two primary missions: enriching the data landscape with diverse datasets, and advancing core data infrastructure. In particular, participants were invited to contribute to the open-source platform by implementing new dataset loaders, designing new benchmark tasks, or engineering robust, scalable data pipelines. The initiative successfully yielded 44 qualifying submissions. This paper outlines the scope of the competition and summarizes the key results and findings, highlighting the new resources now available to the TDL community.

Cite this Paper

BibTeX
@InProceedings{pmlr-v321-bernardez26a, title = {Topological Deep Learning Challenge 2025: Expanding the Data Landscape}, author = {Bern\'ardez, Guillermo and Telyatnikov, Lev and Papillon, Mathilde and Montagna, Marco and Theiler, Raffael and Cornelis, Louisa and Mathe, Johan and Ferriol, Miquel and Vasylenko, Pavlo and Van Looy, Jan-Willem and Testa, Lucia and Neri, Bruno and Genovese, Donatella and Weber, Melanie and Wei, Amaury and Devoto, Alessio and Weers, Alexander and Jankowski, Robert and Cino, Loris and Leko, David and Banf, Michael and M\"{u}ller, Jonas and Grapentin, Thomas and Paik, Taejin and Dutta, Abhijeet and Walter, Hugo and Fontanari, Thomas Vaitses and Ghasemi, Ali and Loi, Dario and S\'aez de Oc\'ariz Borde, Haitz and Aguilar-Arg\"uello, Gabriela and da Rosa, Giovanni B. and Saulus, Th\'eo and Dolores-Cuenca, Eric Rubiel and Di Nino, Leonardo and Leroy, Pierrick and Pandolfo, Mario Edoardo and Cavallo, Andrea and Qin, Yu and Snopov, Pavel and Akbari, Amirreza and Meza-Ch\'avez, Ixchel and Van Langendonck, Louis and Able, Jared and Meshcheryakova, Maria Yuffa and Tsay, Henry and Beni\'c, Luka and Filipiak, Dominik and Liu, Patrick and Liang, Huidong and Santos da Rosa Jr., Alexsandro and Cattai, Tiziana and Borges, Henrique M. and Grimaldi, Enrico and Lecha, Manuel and Battiloro, Claudio and Liu, Xuan-Chen and Deshpande, Raj and Johnson, Graham and Morgunov, Igor and Micheron, Hugo and Devaux, R\'emi and Jardin, Antoine and Emerson, Tegan and Fink, Olga and Miolane, Nina}, booktitle = {Proceedings of the 1st Conference on Topology, Algebra, and Geometry in Data Science(TAG-DS 2025)}, pages = {4--14}, year = {2026}, editor = {Bernardez Gil, Guillermo and Black, Mitchell and Cloninger, Alexander and Doster, Timothy and Emerson, Tegan and Garcı́a-Rodondo, Ińes and Holtz, Chester and Kotak, Mit and Kvinge, Henry and Mishne, Gal and Papillon, Mathilde and Pouplin, Alison and Rainey, Katie and Rieck, Bastian and Telyatnikov, Lev and Yeats, Eric and Wang, Qingsong and Wang, Yusu and Wayland, Jeremy}, volume = {321}, series = {Proceedings of Machine Learning Research}, month = {01--02 Dec}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v321/main/assets/bernardez26a/bernardez26a.pdf}, url = {https://proceedings.mlr.press/v321/bernardez26a.html}, abstract = {This paper describes the 2025 edition of the Topological Deep Learning Challenge: Expanding the Data Landscape, hosted at the first Topology, Algebra, and Geometry in Data Science (TAG-DS) Conference. This year’s challenge aimed to address the data bottleneck in the field by systematically expanding the ecosystem of Topological Deep Learning (TDL). Powered by TopoBench, the challenge was organized into two primary missions: enriching the data landscape with diverse datasets, and advancing core data infrastructure. In particular, participants were invited to contribute to the open-source platform by implementing new dataset loaders, designing new benchmark tasks, or engineering robust, scalable data pipelines. The initiative successfully yielded 44 qualifying submissions. This paper outlines the scope of the competition and summarizes the key results and findings, highlighting the new resources now available to the TDL community.} }
Endnote
%0 Conference Paper %T Topological Deep Learning Challenge 2025: Expanding the Data Landscape %A Guillermo Bernárdez %A Lev Telyatnikov %A Mathilde Papillon %A Marco Montagna %A Raffael Theiler %A Louisa Cornelis %A Johan Mathe %A Miquel Ferriol %A Pavlo Vasylenko %A Jan-Willem Van Looy %A Lucia Testa %A Bruno Neri %A Donatella Genovese %A Melanie Weber %A Amaury Wei %A Alessio Devoto %A Alexander Weers %A Robert Jankowski %A Loris Cino %A David Leko %A Michael Banf %A Jonas Müller %A Thomas Grapentin %A Taejin Paik %A Abhijeet Dutta %A Hugo Walter %A Thomas Vaitses Fontanari %A Ali Ghasemi %A Dario Loi %A Haitz Sáez de Ocáriz Borde %A Gabriela Aguilar-Argüello %A Giovanni B. da Rosa %A Théo Saulus %A Eric Rubiel Dolores-Cuenca %A Leonardo Di Nino %A Pierrick Leroy %A Mario Edoardo Pandolfo %A Andrea Cavallo %A Yu Qin %A Pavel Snopov %A Amirreza Akbari %A Ixchel Meza-Chávez %A Louis Van Langendonck %A Jared Able %A Maria Yuffa Meshcheryakova %A Henry Tsay %A Luka Benić %A Dominik Filipiak %A Patrick Liu %A Huidong Liang %A Alexsandro Santos da Rosa Jr. %A Tiziana Cattai %A Henrique M. Borges %A Enrico Grimaldi %A Manuel Lecha %A Claudio Battiloro %A Xuan-Chen Liu %A Raj Deshpande %A Graham Johnson %A Igor Morgunov %A Hugo Micheron %A Rémi Devaux %A Antoine Jardin %A Tegan Emerson %A Olga Fink %A Nina Miolane %B Proceedings of the 1st Conference on Topology, Algebra, and Geometry in Data Science(TAG-DS 2025) %C Proceedings of Machine Learning Research %D 2026 %E Guillermo Bernardez Gil %E Mitchell Black %E Alexander Cloninger %E Timothy Doster %E Tegan Emerson %E Ińes Garcı́a-Rodondo %E Chester Holtz %E Mit Kotak %E Henry Kvinge %E Gal Mishne %E Mathilde Papillon %E Alison Pouplin %E Katie Rainey %E Bastian Rieck %E Lev Telyatnikov %E Eric Yeats %E Qingsong Wang %E Yusu Wang %E Jeremy Wayland %F pmlr-v321-bernardez26a %I PMLR %P 4--14 %U https://proceedings.mlr.press/v321/bernardez26a.html %V 321 %X This paper describes the 2025 edition of the Topological Deep Learning Challenge: Expanding the Data Landscape, hosted at the first Topology, Algebra, and Geometry in Data Science (TAG-DS) Conference. This year’s challenge aimed to address the data bottleneck in the field by systematically expanding the ecosystem of Topological Deep Learning (TDL). Powered by TopoBench, the challenge was organized into two primary missions: enriching the data landscape with diverse datasets, and advancing core data infrastructure. In particular, participants were invited to contribute to the open-source platform by implementing new dataset loaders, designing new benchmark tasks, or engineering robust, scalable data pipelines. The initiative successfully yielded 44 qualifying submissions. This paper outlines the scope of the competition and summarizes the key results and findings, highlighting the new resources now available to the TDL community.
APA
Bernárdez, G., Telyatnikov, L., Papillon, M., Montagna, M., Theiler, R., Cornelis, L., Mathe, J., Ferriol, M., Vasylenko, P., Van Looy, J., Testa, L., Neri, B., Genovese, D., Weber, M., Wei, A., Devoto, A., Weers, A., Jankowski, R., Cino, L., Leko, D., Banf, M., Müller, J., Grapentin, T., Paik, T., Dutta, A., Walter, H., Fontanari, T.V., Ghasemi, A., Loi, D., Sáez de Ocáriz Borde, H., Aguilar-Argüello, G., da Rosa, G.B., Saulus, T., Dolores-Cuenca, E.R., Di Nino, L., Leroy, P., Pandolfo, M.E., Cavallo, A., Qin, Y., Snopov, P., Akbari, A., Meza-Chávez, I., Van Langendonck, L., Able, J., Meshcheryakova, M.Y., Tsay, H., Benić, L., Filipiak, D., Liu, P., Liang, H., Santos da Rosa Jr., A., Cattai, T., Borges, H.M., Grimaldi, E., Lecha, M., Battiloro, C., Liu, X., Deshpande, R., Johnson, G., Morgunov, I., Micheron, H., Devaux, R., Jardin, A., Emerson, T., Fink, O. & Miolane, N.. (2026). Topological Deep Learning Challenge 2025: Expanding the Data Landscape. Proceedings of the 1st Conference on Topology, Algebra, and Geometry in Data Science(TAG-DS 2025), in Proceedings of Machine Learning Research 321:4-14 Available from https://proceedings.mlr.press/v321/bernardez26a.html.

Related Material