ICLR 2021 Challenge for Computational Geometry & Topology: Design and Results

2021/08/22 by Nina Miolane, Miolane, Nina, Matteo Caorsi +66
Biochemistry, Genetics and Molecular Biology · Computer Science · Mathematics · #Cell Image Analysis Techniques #Computational Geometry (cs.CG) #Differential Geometry (math.DG) #FOS: Computer and information sciences #FOS: Mathematics #General Topology (math.GN) #Topological and Geometric Data Analysis #cs.CG #math.DG #math.GN

paper · pdf · doi:10.48550/arxiv.2108.09810

openalex publication_date 2021/08/22 · arxiv created 2021/08/25 · arxiv updated 2021/08/27 · openalex created_date 2021/08/30 · openalex updated_date 2026/07/28

Abstract

This paper presents the computational challenge on differential geometry and topology that happened within the ICLR 2021 workshop "Geometric and Topological Representation Learning". The competition asked participants to provide creative contributions to the fields of computational geometry and topology through the open-source repositories Geomstats and Giotto-TDA. The challenge attracted 16 teams in its two month duration. This paper describes the design of the challenge and summarizes its main findings.

Citations

• Shape Manifolds, Procrustean Metrics, and Complex Projective Spaces
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Fast Graph Representation Learning with PyTorch Geometric
• A Topology Layer for Machine Learning
• Predicting Neural Network Accuracy from Weights
• An Empirical Bayes Approach to Shrinkage Estimation on the Manifold of Symmetric Positive-Definite Matrices

Related

• ICML Topological Deep Learning Challenge 2024: Beyond the Graph Domain
• Emerging Challenges in Computational Topology
• Collection of abstracts of the Workshop on Triangulations in Geometry and Topology at CG Week 2014 in Kyoto
• A Topology Scavenger Hunt to Introduce Topological Data Analysis
• 04351 Summary – Spatial Representation: Discrete vs. Continuous Computational Models