ICML Topological Deep Learning Challenge 2024: Beyond the Graph Domain

Guillermo Bernárdez, Lev Telyatnikov, Marco Montagna, Federica Baccini, Mathilde Papillon, Miquel Ferriol-Galmés, Mustafa Hajij, Theodore Papamarkou, Maria Sofia Bucarelli, Olga Zaghen, Johan Mathe, Audun Myers, Scott Mahan, Hansen Lillemark, Sharvaree Vadgama, Erik Bekkers, Tim Doster, Tegan Emerson, Henry Kvinge, Katrina Agate, Nesreen K Ahmed, Pengfei Bai, Michael Banf, Claudio Battiloro, Maxim Beketov, Paul Bogdan, Martin Carrasco, Andrea Cavallo, Yun Young Choi, George Dasoulas, Matous̆ Elphick, Giordan Escalona, Dominik Filipiak, Halley Fritze, Thomas Gebhart, Manel Gil-Sorribes, Salvish Goomanee, Victor Guallar, Liliya Imasheva, Andrei Irimia, Hongwei Jin, Graham Johnson, Nikos Kanakaris, Boshko Koloski, Veljko Kovac̆, Manuel Lecha, Minho Lee, Pierrick Leroy, Theodore Long, German Magai, Alvaro Martinez, Marissa Masden, Sebastian Mez̆nar, Bertran Miquel-Oliver, Alexis Molina, Alexander Nikitin, Marco Nurisso, Matt Piekenbrock, Yu Qin, Patryk Rygiel, Alessandro Salatiello, Max Schattauer, Pavel Snopov, Julian Suk, Valentina Sánchez, Mauricio Tec, Francesco Vaccarino, Jonas Verhellen, Frederic Wantiez, Alexander Weers, Patrik Zajec, Blaz̆ S̆krlj, Nina Miolane
Proceedings of the Geometry-grounded Representation Learning and Generative Modeling Workshop (GRaM), PMLR 251:420-428, 2024.

Abstract

This paper describes the 2nd edition of the ICML Topological Deep Learning Challenge that was hosted within the ICML 2024 ELLIS Workshop on Geometry-grounded Representation Learning and Generative Modeling (GRaM). The challenge focused on the problem of representing data in different discrete topological domains in order to bridge the gap between Topological Deep Learning (TDL) and other types of structured datasets (e.g. point clouds, graphs). Specifically, participants were asked to design and implement topological liftings, i.e. mappings between different data structures and topological domains –like hypergraphs, or simplicial/cell/combinatorial complexes. The challenge received 52 submissions satisfying all the requirements. This paper introduces the main scope of the challenge, and summarizes the main results and findings.

Cite this Paper

BibTeX
@InProceedings{pmlr-v251-bernardez24a, title = {ICML Topological Deep Learning Challenge 2024: Beyond the Graph Domain}, author = {Bern\'ardez, Guillermo and Telyatnikov, Lev and Montagna, Marco and Baccini, Federica and Papillon, Mathilde and Ferriol-Galm\'es, Miquel and Hajij, Mustafa and Papamarkou, Theodore and Bucarelli, Maria Sofia and Zaghen, Olga and Mathe, Johan and Myers, Audun and Mahan, Scott and Lillemark, Hansen and Vadgama, Sharvaree and Bekkers, Erik and Doster, Tim and Emerson, Tegan and Kvinge, Henry and Agate, Katrina and Ahmed, Nesreen K and Bai, Pengfei and Banf, Michael and Battiloro, Claudio and Beketov, Maxim and Bogdan, Paul and Carrasco, Martin and Cavallo, Andrea and Choi, Yun Young and Dasoulas, George and Elphick, Matou\u{s} and Escalona, Giordan and Filipiak, Dominik and Fritze, Halley and Gebhart, Thomas and Gil-Sorribes, Manel and Goomanee, Salvish and Guallar, Victor and Imasheva, Liliya and Irimia, Andrei and Jin, Hongwei and Johnson, Graham and Kanakaris, Nikos and Koloski, Boshko and Kova\u{c}, Veljko and Lecha, Manuel and Lee, Minho and Leroy, Pierrick and Long, Theodore and Magai, German and Martinez, Alvaro and Masden, Marissa and Me\u{z}nar, Sebastian and Miquel-Oliver, Bertran and Molina, Alexis and Nikitin, Alexander and Nurisso, Marco and Piekenbrock, Matt and Qin, Yu and Rygiel, Patryk and Salatiello, Alessandro and Schattauer, Max and Snopov, Pavel and Suk, Julian and S\'anchez, Valentina and Tec, Mauricio and Vaccarino, Francesco and Verhellen, Jonas and Wantiez, Frederic and Weers, Alexander and Zajec, Patrik and \u{S}krlj, Bla\u{z} and Miolane, Nina}, booktitle = {Proceedings of the Geometry-grounded Representation Learning and Generative Modeling Workshop (GRaM)}, pages = {420--428}, year = {2024}, editor = {Vadgama, Sharvaree and Bekkers, Erik and Pouplin, Alison and Kaba, Sekou-Oumar and Walters, Robin and Lawrence, Hannah and Emerson, Tegan and Kvinge, Henry and Tomczak, Jakub and Jegelka, Stephanie}, volume = {251}, series = {Proceedings of Machine Learning Research}, month = {29 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v251/main/assets/bernardez24a/bernardez24a.pdf}, url = {https://proceedings.mlr.press/v251/bernardez24a.html}, abstract = {This paper describes the 2nd edition of the ICML Topological Deep Learning Challenge that was hosted within the ICML 2024 ELLIS Workshop on Geometry-grounded Representation Learning and Generative Modeling (GRaM). The challenge focused on the problem of representing data in different discrete topological domains in order to bridge the gap between Topological Deep Learning (TDL) and other types of structured datasets (e.g. point clouds, graphs). Specifically, participants were asked to design and implement topological liftings, i.e. mappings between different data structures and topological domains –like hypergraphs, or simplicial/cell/combinatorial complexes. The challenge received 52 submissions satisfying all the requirements. This paper introduces the main scope of the challenge, and summarizes the main results and findings.} }
Endnote
%0 Conference Paper %T ICML Topological Deep Learning Challenge 2024: Beyond the Graph Domain %A Guillermo Bernárdez %A Lev Telyatnikov %A Marco Montagna %A Federica Baccini %A Mathilde Papillon %A Miquel Ferriol-Galmés %A Mustafa Hajij %A Theodore Papamarkou %A Maria Sofia Bucarelli %A Olga Zaghen %A Johan Mathe %A Audun Myers %A Scott Mahan %A Hansen Lillemark %A Sharvaree Vadgama %A Erik Bekkers %A Tim Doster %A Tegan Emerson %A Henry Kvinge %A Katrina Agate %A Nesreen K Ahmed %A Pengfei Bai %A Michael Banf %A Claudio Battiloro %A Maxim Beketov %A Paul Bogdan %A Martin Carrasco %A Andrea Cavallo %A Yun Young Choi %A George Dasoulas %A Matous̆ Elphick %A Giordan Escalona %A Dominik Filipiak %A Halley Fritze %A Thomas Gebhart %A Manel Gil-Sorribes %A Salvish Goomanee %A Victor Guallar %A Liliya Imasheva %A Andrei Irimia %A Hongwei Jin %A Graham Johnson %A Nikos Kanakaris %A Boshko Koloski %A Veljko Kovac̆ %A Manuel Lecha %A Minho Lee %A Pierrick Leroy %A Theodore Long %A German Magai %A Alvaro Martinez %A Marissa Masden %A Sebastian Mez̆nar %A Bertran Miquel-Oliver %A Alexis Molina %A Alexander Nikitin %A Marco Nurisso %A Matt Piekenbrock %A Yu Qin %A Patryk Rygiel %A Alessandro Salatiello %A Max Schattauer %A Pavel Snopov %A Julian Suk %A Valentina Sánchez %A Mauricio Tec %A Francesco Vaccarino %A Jonas Verhellen %A Frederic Wantiez %A Alexander Weers %A Patrik Zajec %A Blaz̆ S̆krlj %A Nina Miolane %B Proceedings of the Geometry-grounded Representation Learning and Generative Modeling Workshop (GRaM) %C Proceedings of Machine Learning Research %D 2024 %E Sharvaree Vadgama %E Erik Bekkers %E Alison Pouplin %E Sekou-Oumar Kaba %E Robin Walters %E Hannah Lawrence %E Tegan Emerson %E Henry Kvinge %E Jakub Tomczak %E Stephanie Jegelka %F pmlr-v251-bernardez24a %I PMLR %P 420--428 %U https://proceedings.mlr.press/v251/bernardez24a.html %V 251 %X This paper describes the 2nd edition of the ICML Topological Deep Learning Challenge that was hosted within the ICML 2024 ELLIS Workshop on Geometry-grounded Representation Learning and Generative Modeling (GRaM). The challenge focused on the problem of representing data in different discrete topological domains in order to bridge the gap between Topological Deep Learning (TDL) and other types of structured datasets (e.g. point clouds, graphs). Specifically, participants were asked to design and implement topological liftings, i.e. mappings between different data structures and topological domains –like hypergraphs, or simplicial/cell/combinatorial complexes. The challenge received 52 submissions satisfying all the requirements. This paper introduces the main scope of the challenge, and summarizes the main results and findings.
APA
Bernárdez, G., Telyatnikov, L., Montagna, M., Baccini, F., Papillon, M., Ferriol-Galmés, M., Hajij, M., Papamarkou, T., Bucarelli, M.S., Zaghen, O., Mathe, J., Myers, A., Mahan, S., Lillemark, H., Vadgama, S., Bekkers, E., Doster, T., Emerson, T., Kvinge, H., Agate, K., Ahmed, N.K., Bai, P., Banf, M., Battiloro, C., Beketov, M., Bogdan, P., Carrasco, M., Cavallo, A., Choi, Y.Y., Dasoulas, G., Elphick, M., Escalona, G., Filipiak, D., Fritze, H., Gebhart, T., Gil-Sorribes, M., Goomanee, S., Guallar, V., Imasheva, L., Irimia, A., Jin, H., Johnson, G., Kanakaris, N., Koloski, B., Kovac̆, V., Lecha, M., Lee, M., Leroy, P., Long, T., Magai, G., Martinez, A., Masden, M., Mez̆nar, S., Miquel-Oliver, B., Molina, A., Nikitin, A., Nurisso, M., Piekenbrock, M., Qin, Y., Rygiel, P., Salatiello, A., Schattauer, M., Snopov, P., Suk, J., Sánchez, V., Tec, M., Vaccarino, F., Verhellen, J., Wantiez, F., Weers, A., Zajec, P., S̆krlj, B. & Miolane, N.. (2024). ICML Topological Deep Learning Challenge 2024: Beyond the Graph Domain. Proceedings of the Geometry-grounded Representation Learning and Generative Modeling Workshop (GRaM), in Proceedings of Machine Learning Research 251:420-428 Available from https://proceedings.mlr.press/v251/bernardez24a.html.

Related Material