ICML 拓扑深度学习挑战赛 2024：超越图域
机器学习
2024-09-10 v1 人工智能
摘要
本文描述了第 2 届 ICML 拓扑深度学习挑战赛，该挑战赛在 ICML 2024 ELLIS 几何基础表示学习与生成建模（GRaM）研讨会中举办。该挑战赛聚焦于在不同离散拓扑域中表示数据的问题，旨在弥合拓扑深度学习（TDL）与其他类型结构化数据集（例如点云、图）之间的差距。具体而言，参赛者被要求设计并实现拓扑提升，即不同数据结构与拓扑域之间的映射——如超图，或单纯复形/胞腔复形/组合复形。该挑战赛收到了 52 份满足所有要求的提交。本文介绍了挑战赛的主要范围，并总结了主要结果与发现。
引用
@article{arxiv.2409.05211,
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},
journal= {arXiv preprint arXiv:2409.05211},
year = {2024}
}
备注
Proceedings of the Geometry-grounded Representation Learning and Generative Modeling Workshop (GRaM) at ICML 2024