TopoBench (TB) is a modular Python library designed to standardize benchmarking and accelerate research in Topological Deep Learning (TDL). In particular, TB allows to train and compare the performances of all sorts of Topological Neural Networks (TNNs) across the different topological domains, where by topological domain we refer to a graph, a simplicial complex, a cellular complex, or a hypergraph. For detailed information, please refer to the TopoBench: A Framework for Benchmarking Topological Deep Learning paper.
TopoBench was launched in 2024 to advance the field of topological data analysis by providing standardized benchmarks and evaluation metrics. Since then, our interdisciplinary team has built powerful new tools that accelerate scientific discovery through topology.
Our name reflects the belief that there is fundamental symmetry in data - between shape and function, between structure and behavior. By harnessing topology's powerful capabilities, we can use it to model complex phenomena and drive breakthrough discoveries.
Key Features
Modular Design
Easily extensible architecture for implementing new topological neural networks and domains.
Benchmarking
Comprehensive suite of benchmarks for evaluating and comparing different approaches.
Community-Driven
Open-source platform welcoming contributions from researchers worldwide.