挑战跨拓扑结构数据表示，推动拓扑深度学习发展
ICML Topological Deep Learning Challenge 2024: Beyond the Graph Domain
- 设计拓扑提升映射，实现不同数据结构间转换
- 52份合格提交，验证多种拓扑结构转换可行性
- 适合拓扑学习、图神经网络研究者参考
本文介绍在ICML 2024 ELLIS几何基础表征学习与生成建模研讨会（GRaM）中举办的第二届ICML拓扑深度学习挑战赛。挑战聚焦于如何在不同离散拓扑域中表示数据，以弥合拓扑深度学习（TDL）与其他结构化数据集（如点云、图）之间的差距。参赛者需设计并实现拓扑提升，即在不同数据结构与拓扑域（如超图、单纯复形/胞腔/组合复形）间的映射。挑战共收到52份满足全部要求的提交。本文介绍挑战的核心目标，并总结主要成果与发现。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。