HypLL: The Hyperbolic Learning Library
This provides a tool for researchers and practitioners in machine learning, multimedia, and computer vision to explore hyperbolic deep learning, but it is incremental as it packages existing methods into a library.
The authors tackled the lack of an accessible open-source library for building hyperbolic deep learning modules, and they presented HypLL, a library built on PyTorch designed for ease-of-use to unify progress in this field.
Deep learning in hyperbolic space is quickly gaining traction in the fields of machine learning, multimedia, and computer vision. Deep networks commonly operate in Euclidean space, implicitly assuming that data lies on regular grids. Recent advances have shown that hyperbolic geometry provides a viable alternative foundation for deep learning, especially when data is hierarchical in nature and when working with few embedding dimensions. Currently however, no accessible open-source library exists to build hyperbolic network modules akin to well-known deep learning libraries. We present HypLL, the Hyperbolic Learning Library to bring the progress on hyperbolic deep learning together. HypLL is built on top of PyTorch, with an emphasis in its design for ease-of-use, in order to attract a broad audience towards this new and open-ended research direction. The code is available at: https://github.com/maxvanspengler/hyperbolic_learning_library.