ICML 2023 Topological Deep Learning Challenge : Design and Results

TL;DR

This paper details the design and outcomes of the ICML 2023 Topological Deep Learning Challenge, which encouraged development and sharing of topological neural network implementations through open-source packages, attracting 28 submissions.

Contribution

It introduces a new challenge framework for topological deep learning, promoting open-source contributions and providing insights into current research directions.

Findings

28 submissions received during the challenge

Promotion of open-source topological neural network tools

Insights into current topological deep learning methods

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.