LGSep 26, 2023

ICML 2023 Topological Deep Learning Challenge : Design and Results

arXiv:2309.15188v45 citationsh-index: 70Has Code
Originality Synthesis-oriented
AI Analysis

This is an incremental effort to promote open-source tools and community engagement in topological deep learning, primarily for researchers in that niche field.

The paper describes a computational challenge on topological deep learning hosted at ICML 2023, where participants submitted open-source implementations of topological neural networks, resulting in 28 qualifying submissions over two months.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes