ICML 2023 Topological Deep Learning Challenge: Design and Results

Mathilde Papillon*, Mustafa Hajij, Audun Myers, Florian Frantzen, Ghada Zamzmi, Helen Jenne, Johan Mathe, Josef Hoppe, Maosheng Yang, More Authors

*Corresponding author for this work

Research output: Contribution to journalConference articleScientificpeer-review

8 Downloads (Pure)

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.

Original languageEnglish
Pages (from-to)3-8
Number of pages6
JournalProceedings of Machine Learning Research
Volume221
Publication statusPublished - 2023
Event2nd Annual Workshop on Topology, Algebra, and Geometry in Machine Learning, TAG-ML 2023, held at the International Conference on Machine Learning, ICML 2023 - Honolulu, United States
Duration: 28 Jul 2023 → …

Funding

The authors would like the thank the organizers of the ICML 2023 Topology, Algebra and Geometry in Machine Learning Workshop for their valuable support in the organization of the challenge.

Fingerprint

Dive into the research topics of 'ICML 2023 Topological Deep Learning Challenge: Design and Results'. Together they form a unique fingerprint.

Cite this