ICML 2023 Topological Deep Learning Challenge: Design and Results

Mathilde Papillon, Mustafa Hajij, Audun Myers, Helen Jenne, Johan Mathe, Theodore Papamarkou, Aldo Guzmán-Sáenz, Neal Livesay, Tamal Dey, Abraham Rabinowitz, Aiden Brent, Alessandro Salatiello, Alexander Nikitin, Ali Zia, Claudio Battiloro, Dmitrii Gavrilev, German Magai, Gleb Bazhenov, Guillermo Bernardez, Indro Spinelli, Jens Agerberg, Kalyan Nadimpalli, Lev Telyatninkov, Luca Scofano, Lucia Testa, Manuel Lecha, Maosheng Yang, Mohammed Hassanin, Odin Hoff Gardaa, Olga Zaghen, Paul Hausner, Paul Snopoff, Rubén Ballester, Sadrodin Barikbin, Sergio Escalera, Simone Fiorellino, Henry Kvinge, Karthikeyan Natesan Ramamurthy, Paul Rosen, Robin Walters, Shreyas N. Samaga, Soham Mukherjee, Sophia Sanborn, Tegan Emerson, Timothy Doster, Tolga Birdal, Abdelwahed Khamis, Simone Scardapane, Suraj Singh, Tatiana Malygina, Yixiao Yue, Nina Miolane
Proceedings of 2nd Annual Workshop on Topology, Algebra, and Geometry in Machine Learning (TAG-ML), PMLR 221:3-8, 2023.

Abstract

This paper presents the computational challenge on topological deep learning that was hosted within the ICML 2023 Workshop on Topology and Geometry in Machine Learning. The competition asked participants to provide open-source implementations of topological neural networks from the literature by contributing to the python packages TopoNetX (data processing) and TopoModelX (deep learning). The challenge attracted twenty-eight qualifying submissions in its two month duration. This paper describes the design of the challenge and summarizes its main findings.

Cite this Paper

BibTeX
@InProceedings{pmlr-v221-papillon23a, title = {ICML 2023 Topological Deep Learning Challenge: Design and Results}, author = {Papillon, Mathilde and Hajij, Mustafa and Myers, Audun and and Jenne, Helen and Mathe, Johan and Papamarkou, Theodore and Guzm\'{a}n-S\'{a}enz, Aldo and Livesay, Neal and Dey, Tamal and Rabinowitz, Abraham and Brent, Aiden and Salatiello, Alessandro and Nikitin, Alexander and Zia, Ali and Battiloro, Claudio and Gavrilev, Dmitrii and Magai, German and Bazhenov, Gleb and Bernardez, Guillermo and Spinelli, Indro and Agerberg, Jens and Nadimpalli, Kalyan and Telyatninkov, Lev and Scofano, Luca and Testa, Lucia and Lecha, Manuel and Yang, Maosheng and Hassanin, Mohammed and Gardaa, Odin Hoff and Zaghen, Olga and Hausner, Paul and Snopoff, Paul and Ballester, Rub\'{e}n and Barikbin, Sadrodin and Escalera, Sergio and Fiorellino, Simone and Kvinge, Henry and Ramamurthy, Karthikeyan Natesan and Rosen, Paul and Walters, Robin and Samaga, Shreyas N. and Mukherjee, Soham and Sanborn, Sophia and Emerson, Tegan and Doster, Timothy and Birdal, Tolga and Khamis, Abdelwahed and Scardapane, Simone and Singh, Suraj and Malygina, Tatiana and Yue, Yixiao and Miolane, Nina}, booktitle = {Proceedings of 2nd Annual Workshop on Topology, Algebra, and Geometry in Machine Learning (TAG-ML)}, pages = {3--8}, year = {2023}, editor = {Doster, Timothy and Emerson, Tegan and Kvinge, Henry and Miolane, Nina and Papillon, Mathilde and Rieck, Bastian and Sanborn, Sophia}, volume = {221}, series = {Proceedings of Machine Learning Research}, month = {28 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v221/papillon23a/papillon23a.pdf}, url = {https://proceedings.mlr.press/v221/papillon23a.html}, abstract = {This paper presents the computational challenge on topological deep learning that was hosted within the ICML 2023 Workshop on Topology and Geometry in Machine Learning. The competition asked participants to provide open-source implementations of topological neural networks from the literature by contributing to the python packages TopoNetX (data processing) and TopoModelX (deep learning). The challenge attracted twenty-eight qualifying submissions in its two month duration. This paper describes the design of the challenge and summarizes its main findings.} }
Endnote
%0 Conference Paper %T ICML 2023 Topological Deep Learning Challenge: Design and Results %A Mathilde Papillon %A Mustafa Hajij %A Audun Myers %A Helen Jenne %A Johan Mathe %A Theodore Papamarkou %A Aldo Guzmán-Sáenz %A Neal Livesay %A Tamal Dey %A Abraham Rabinowitz %A Aiden Brent %A Alessandro Salatiello %A Alexander Nikitin %A Ali Zia %A Claudio Battiloro %A Dmitrii Gavrilev %A German Magai %A Gleb Bazhenov %A Guillermo Bernardez %A Indro Spinelli %A Jens Agerberg %A Kalyan Nadimpalli %A Lev Telyatninkov %A Luca Scofano %A Lucia Testa %A Manuel Lecha %A Maosheng Yang %A Mohammed Hassanin %A Odin Hoff Gardaa %A Olga Zaghen %A Paul Hausner %A Paul Snopoff %A Rubén Ballester %A Sadrodin Barikbin %A Sergio Escalera %A Simone Fiorellino %A Henry Kvinge %A Karthikeyan Natesan Ramamurthy %A Paul Rosen %A Robin Walters %A Shreyas N. Samaga %A Soham Mukherjee %A Sophia Sanborn %A Tegan Emerson %A Timothy Doster %A Tolga Birdal %A Abdelwahed Khamis %A Simone Scardapane %A Suraj Singh %A Tatiana Malygina %A Yixiao Yue %A Nina Miolane %B Proceedings of 2nd Annual Workshop on Topology, Algebra, and Geometry in Machine Learning (TAG-ML) %C Proceedings of Machine Learning Research %D 2023 %E Timothy Doster %E Tegan Emerson %E Henry Kvinge %E Nina Miolane %E Mathilde Papillon %E Bastian Rieck %E Sophia Sanborn %F pmlr-v221-papillon23a %I PMLR %P 3--8 %U https://proceedings.mlr.press/v221/papillon23a.html %V 221 %X This paper presents the computational challenge on topological deep learning that was hosted within the ICML 2023 Workshop on Topology and Geometry in Machine Learning. The competition asked participants to provide open-source implementations of topological neural networks from the literature by contributing to the python packages TopoNetX (data processing) and TopoModelX (deep learning). The challenge attracted twenty-eight qualifying submissions in its two month duration. This paper describes the design of the challenge and summarizes its main findings.
APA
Papillon, M., Hajij, M., Myers, A., Jenne, H., Mathe, J., Papamarkou, T., Guzmán-Sáenz, A., Livesay, N., Dey, T., Rabinowitz, A., Brent, A., Salatiello, A., Nikitin, A., Zia, A., Battiloro, C., Gavrilev, D., Magai, G., Bazhenov, G., Bernardez, G., Spinelli, I., Agerberg, J., Nadimpalli, K., Telyatninkov, L., Scofano, L., Testa, L., Lecha, M., Yang, M., Hassanin, M., Gardaa, O.H., Zaghen, O., Hausner, P., Snopoff, P., Ballester, R., Barikbin, S., Escalera, S., Fiorellino, S., Kvinge, H., Ramamurthy, K.N., Rosen, P., Walters, R., Samaga, S.N., Mukherjee, S., Sanborn, S., Emerson, T., Doster, T., Birdal, T., Khamis, A., Scardapane, S., Singh, S., Malygina, T., Yue, Y. & Miolane, N.. (2023). ICML 2023 Topological Deep Learning Challenge: Design and Results. Proceedings of 2nd Annual Workshop on Topology, Algebra, and Geometry in Machine Learning (TAG-ML), in Proceedings of Machine Learning Research 221:3-8 Available from https://proceedings.mlr.press/v221/papillon23a.html.

Related Material