TopoBench: A Framework for Benchmarking Topological Deep Learning
This provides a framework for researchers in topological deep learning to accelerate research through standardized benchmarking, though it is incremental as it builds on existing TDL concepts.
The authors tackled the lack of standardized benchmarking in topological deep learning by introducing TopoBench, an open-source library that modularizes TDL pipelines and supports transformations across topological domains, demonstrating its applicability through benchmarking of TDL architectures on diverse tasks and datasets.
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.