HypLL: The Hyperbolic Learning Library

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 easy-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. The compressed archive is available at: https://doi.org/10.21942/uva.23385506.v4

[1]  Mina Ghadimi Atigh,et al.  Hyperbolic Deep Learning in Computer Vision: A Survey , 2023, International Journal of Computer Vision.

[2]  N. Sebe,et al.  Hyperbolic Vision Transformers: Combining Improvements in Metric Learning , 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Mina Ghadimi Atigh,et al.  Hyperbolic Image Segmentation , 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Irwin King,et al.  Hyperbolic Graph Neural Networks: A Review of Methods and Applications , 2022, ArXiv.

[5]  Shu Wu,et al.  Fully Hyperbolic Graph Convolution Network for Recommendation , 2021, CIKM.

[6]  S. Axen,et al.  Manifolds.jl: An Extensible Julia Framework for Data Analysis on Manifolds , 2021, ACM Trans. Math. Softw..

[7]  Guoying Zhao,et al.  Hyperbolic Deep Neural Networks: A Survey , 2021, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Christopher De Sa,et al.  Differentiating through the Fréchet Mean , 2020, ICML.

[9]  Rasul Karimov,et al.  Geoopt: Riemannian Optimization in PyTorch , 2020, ArXiv.

[10]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[11]  Octavian-Eugen Ganea,et al.  Constant Curvature Graph Convolutional Networks , 2019, ICML.

[12]  Douwe Kiela,et al.  Hyperbolic Graph Neural Networks , 2019, NeurIPS.

[13]  Valentin Khrulkov,et al.  Hyperbolic Image Embeddings , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Jan Eric Lenssen,et al.  Fast Graph Representation Learning with PyTorch Geometric , 2019, ArXiv.

[15]  Gary Bécigneul,et al.  Poincaré GloVe: Hyperbolic Word Embeddings , 2018, ICLR.

[16]  Gary Bécigneul,et al.  Riemannian Adaptive Optimization Methods , 2018, ICLR.

[17]  Thomas Hofmann,et al.  Hyperbolic Neural Networks , 2018, NeurIPS.

[18]  Xavier Pennec,et al.  geomstats: a Python Package for Riemannian Geometry in Machine Learning , 2018, ArXiv.

[19]  Thomas Hofmann,et al.  Hyperbolic Entailment Cones for Learning Hierarchical Embeddings , 2018, ICML.

[20]  Douwe Kiela,et al.  Poincaré Embeddings for Learning Hierarchical Representations , 2017, NIPS.

[21]  Pierre Vandergheynst,et al.  Geometric Deep Learning: Going beyond Euclidean data , 2016, IEEE Signal Process. Mag..

[22]  Zheng Zhang,et al.  MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems , 2015, ArXiv.

[23]  Abraham Albert Ungar,et al.  A Gyrovector Space Approach to Hyperbolic Geometry , 2009, A Gyrovector Space Approach to Hyperbolic Geometry.

[24]  Carole D. Hafner,et al.  The State of the Art in Ontology Design: A Survey and Comparative Review , 1997, AI Mag..