_version_ 1866915462367936512
author Telyatnikov, Lev
Bernardez, Guillermo
Montagna, Marco
Hajij, Mustafa
Carrasco, Martin
Vasylenko, Pavlo
Papillon, Mathilde
Zamzmi, Ghada
Schaub, Michael T.
Verhellen, Jonas
Snopov, Pavel
Miquel-Oliver, Bertran
Gil-Sorribes, Manel
Molina, Alexis
Guallar, Victor
Long, Theodore
Suk, Julian
Rygiel, Patryk
Nikitin, Alexander
Escalona, Giordan
Banf, Michael
Filipiak, Dominik
Schattauer, Max
Imasheva, Liliya
Martinez, Alvaro
Fritze, Halley
Masden, Marissa
Sánchez, Valentina
Lecha, Manuel
Cavallo, Andrea
Battiloro, Claudio
Piekenbrock, Matt
Tec, Mauricio
Dasoulas, George
Miolane, Nina
Scardapane, Simone
Papamarkou, Theodore
author_facet Telyatnikov, Lev
Bernardez, Guillermo
Montagna, Marco
Hajij, Mustafa
Carrasco, Martin
Vasylenko, Pavlo
Papillon, Mathilde
Zamzmi, Ghada
Schaub, Michael T.
Verhellen, Jonas
Snopov, Pavel
Miquel-Oliver, Bertran
Gil-Sorribes, Manel
Molina, Alexis
Guallar, Victor
Long, Theodore
Suk, Julian
Rygiel, Patryk
Nikitin, Alexander
Escalona, Giordan
Banf, Michael
Filipiak, Dominik
Schattauer, Max
Imasheva, Liliya
Martinez, Alvaro
Fritze, Halley
Masden, Marissa
Sánchez, Valentina
Lecha, Manuel
Cavallo, Andrea
Battiloro, Claudio
Piekenbrock, Matt
Tec, Mauricio
Dasoulas, George
Miolane, Nina
Scardapane, Simone
Papamarkou, Theodore
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_06642
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TopoBench: A Framework for Benchmarking Topological Deep Learning
Telyatnikov, Lev
Bernardez, Guillermo
Montagna, Marco
Hajij, Mustafa
Carrasco, Martin
Vasylenko, Pavlo
Papillon, Mathilde
Zamzmi, Ghada
Schaub, Michael T.
Verhellen, Jonas
Snopov, Pavel
Miquel-Oliver, Bertran
Gil-Sorribes, Manel
Molina, Alexis
Guallar, Victor
Long, Theodore
Suk, Julian
Rygiel, Patryk
Nikitin, Alexander
Escalona, Giordan
Banf, Michael
Filipiak, Dominik
Schattauer, Max
Imasheva, Liliya
Martinez, Alvaro
Fritze, Halley
Masden, Marissa
Sánchez, Valentina
Lecha, Manuel
Cavallo, Andrea
Battiloro, Claudio
Piekenbrock, Matt
Tec, Mauricio
Dasoulas, George
Miolane, Nina
Scardapane, Simone
Papamarkou, Theodore
Machine Learning
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.
title TopoBench: A Framework for Benchmarking Topological Deep Learning
topic Machine Learning
url https://arxiv.org/abs/2406.06642