All publications

Report / 2024

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, Matouš 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 Kovač, Manuel Lecha, Minho Lee, Pierrick Leroy, Theodore Long, German Magai, Alvaro Martinez, Marissa Masden, Sebastian Mežnar, 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, Blaž Škrlj, Nina Miolane

GRaM Workshop · ICML 2024 · Published

Four examples lift graphs to hypergraphs, simplicial complexes and cellular complexes, and a cellular complex to a combinatorial complex.
Lifting maps enrich a graph or cell complex with higher-order structure, illustrating the transformations explored by the challenge. Figure 2 · Bernárdez et al. (2024) · Bernárdez et al. · CC BY 4.0. The paper credits this figure to Hajij et al. (2023).

Beyond pairwise connections

The challenge focuses on topological liftings: transformations that map data into representations such as hypergraphs and cell, simplicial, or combinatorial complexes. Such representations can describe relationships beyond the pairwise edges of a graph.

This report presents the challenge design and summarizes contributions from the participating community. The arXiv record identifies the report with the GRaM workshop at ICML 2024.

Cite this work

@misc{topologicallearningchallenge2024,
  title = {ICML Topological Deep Learning Challenge 2024: Beyond the Graph Domain},
  author = { Guillermo Bernárdez and Lev Telyatnikov and Marco Montagna and Federica Baccini and Mathilde Papillon and Miquel Ferriol-Galmés and Mustafa Hajij and Theodore Papamarkou and Maria Sofia Bucarelli and Olga Zaghen and Johan Mathe and Audun Myers and Scott Mahan and Hansen Lillemark and Sharvaree Vadgama and Erik Bekkers and Tim Doster and Tegan Emerson and Henry Kvinge and Katrina Agate and Nesreen K Ahmed and Pengfei Bai and Michael Banf and Claudio Battiloro and Maxim Beketov and Paul Bogdan and Martin Carrasco and Andrea Cavallo and Yun Young Choi and George Dasoulas and Matouš Elphick and Giordan Escalona and Dominik Filipiak and Halley Fritze and Thomas Gebhart and Manel Gil-Sorribes and Salvish Goomanee and Victor Guallar and Liliya Imasheva and Andrei Irimia and Hongwei Jin and Graham Johnson and Nikos Kanakaris and Boshko Koloski and Veljko Kovač and Manuel Lecha and Minho Lee and Pierrick Leroy and Theodore Long and German Magai and Alvaro Martinez and Marissa Masden and Sebastian Mežnar and Bertran Miquel-Oliver and Alexis Molina and Alexander Nikitin and Marco Nurisso and Matt Piekenbrock and Yu Qin and Patryk Rygiel and Alessandro Salatiello and Max Schattauer and Pavel Snopov and Julian Suk and Valentina Sánchez and Mauricio Tec and Francesco Vaccarino and Jonas Verhellen and Frederic Wantiez and Alexander Weers and Patrik Zajec and Blaž Škrlj and Nina Miolane },
  year = {2024},
  doi = {10.48550/arXiv.2409.05211},
  eprint = {2409.05211},
  archivePrefix = {arXiv},
  url = { https://doi.org/10.48550/arXiv.2409.05211 }
}