TopoX: A Suite of Python Packages for Machine Learning on Topological Domains

TopoX: A Suite of Python Packages for Machine Learning on Topological Domains

17 Feb 2024 | Mustafa Hajij*, Mathilde Papillon*, Florian Frantzen*, Jens Agerberg, Ibrahim ALJabea, Ruben Ballester, Claudio Battiloro, Guillermo Bernárdez, Tolga Birdal, Aiden Brent, Peter Chin, Sergio Escalera, Simone Fiorellino, Odin Hoff Gardaa, Gurusankar Gopalakrishnan, Devendra Govil, Josef Hoppe, Manele Reddy Karri, Jude Khouja, Manuel Lecha, Neal Livesay, Jan Meißner, Soham Mukherjee, Alexander Nikitin, Theodore Papamarkou, Jaro Prilepok, Karthikeyan Natesan Ramamurthy, Paul Rosen, Aldo Guzmán-Sáenz, Alessandro Salatiello, Shreyas N. Samaga, Simone Scardapane, Michael T. Schaub, Luca Scofano, Indro Spinelli, Lev Telyatnikov, Quang Truong, Robin Walters, Maosheng Yang, Olga Zaghen, Ghada Zamzmi, Ali Zia, Nina Miolane
TopoX is a Python software suite for machine learning on topological domains, including hypergraphs, simplicial, cellular, path, and combinatorial complexes. It consists of three packages: TopoNetX for constructing and computing on these domains, TopoEmbedX for embedding topological domains into vector spaces, and TopoModelX for higher-order message passing in neural networks. TopoX provides extensive documentation and is available under MIT license. The suite aims to facilitate research in topological domains by offering foundational code, user-friendly algorithms, and a unified API. It enhances accessibility to topological learning and supports a wide range of topological domains and models. TopoX is designed to be flexible and interoperable, with a focus on simplifying learning and fostering collaboration. It is built on Numpy, Scipy, PyTorch, and PyG, and includes extensive testing and code coverage. TopoX is compared with other packages like NetworkX, HypernetX, and KarateClub, and is noted for its comprehensive functionality and ease of use. The software includes examples and notebooks to help users get started with topological deep learning.TopoX is a Python software suite for machine learning on topological domains, including hypergraphs, simplicial, cellular, path, and combinatorial complexes. It consists of three packages: TopoNetX for constructing and computing on these domains, TopoEmbedX for embedding topological domains into vector spaces, and TopoModelX for higher-order message passing in neural networks. TopoX provides extensive documentation and is available under MIT license. The suite aims to facilitate research in topological domains by offering foundational code, user-friendly algorithms, and a unified API. It enhances accessibility to topological learning and supports a wide range of topological domains and models. TopoX is designed to be flexible and interoperable, with a focus on simplifying learning and fostering collaboration. It is built on Numpy, Scipy, PyTorch, and PyG, and includes extensive testing and code coverage. TopoX is compared with other packages like NetworkX, HypernetX, and KarateClub, and is noted for its comprehensive functionality and ease of use. The software includes examples and notebooks to help users get started with topological deep learning.
Reach us at info@study.space
Understanding TopoX%3A A Suite of Python Packages for Machine Learning on Topological Domains