ICML Topological Deep Learning Challenge 2024: Beyond the Graph Domain
This addresses the problem of bridging topological deep learning with structured datasets for researchers in machine learning and geometry, though it is incremental as it builds on previous challenge editions.
The paper describes the 2nd ICML Topological Deep Learning Challenge, which focused on developing methods to represent data across different topological domains like hypergraphs and simplicial complexes, receiving 52 submissions.
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.