This work introduces TopoBench, an open-source library designed to standardize benchmarking and accelerate research in topological deep learning (TDL). TopoBench decomposes TDL into a sequence of independent modules for data generation, loading, transforming and processing, as well as model training, optimization and evaluation. This modular organization provides flexibility for modifications and facilitates the adaptation and optimization of various TDL pipelines. A key feature of TopoBench is its support for transformations and lifting across topological domains. Mapping the topology and features of a graph to higher-order topological domains, such as simplicial and cell complexes, enables richer data representations and more fine-grained analyses. The applicability of TopoBench is demonstrated by benchmarking several TDL architectures across diverse tasks and datasets.
@article{arxiv.2406.06642,
title = {TopoBench: A Framework for Benchmarking Topological Deep Learning},
author = {Lev Telyatnikov and Guillermo Bernardez and Marco Montagna and Mustafa Hajij and Martin Carrasco and Pavlo Vasylenko and Mathilde Papillon and Ghada Zamzmi and Michael T. Schaub and Jonas Verhellen and Pavel Snopov and Bertran Miquel-Oliver and Manel Gil-Sorribes and Alexis Molina and Victor Guallar and Theodore Long and Julian Suk and Patryk Rygiel and Alexander Nikitin and Giordan Escalona and Michael Banf and Dominik Filipiak and Max Schattauer and Liliya Imasheva and Alvaro Martinez and Halley Fritze and Marissa Masden and Valentina Sánchez and Manuel Lecha and Andrea Cavallo and Claudio Battiloro and Matt Piekenbrock and Mauricio Tec and George Dasoulas and Nina Miolane and Simone Scardapane and Theodore Papamarkou},
journal= {arXiv preprint arXiv:2406.06642},
year = {2025}
}