Hyperbolic Learning Library (HypLL)

HypLL requires Python 3.10+ and PyTorch 1.11+. It is highly recommended to install PyTorch following the official instructions at https://pytorch.org/get-started/locally/ before installing HypLL.

To install HypLL, first set up and activate a Python virtual environment, then use pip to install the package from PyPI.

# 1. Create a virtual environment
python -m venv .env

# 2. Activate the environment
# On Linux/macOS:
source .env/bin/activate
# On Windows:
.env\Scripts\activate

# 3. Install HypLL
pip install hypll

If the standard make html command is unavailable, you can explicitly invoke the Sphinx build module using the following command:

SPHINXBUILD="python3 -m sphinx.cmd.build" make html

The Hyperbolic Learning Library (HypLL) is an extension of PyTorch for deep learning in hyperbolic space.

Prerequisites

• Python: 3.10 or higher
• PyTorch: 1.11 or higher

It is highly recommended to have a working PyTorch installation before installing HypLL.

Setup Steps

1. Create a Python virtual environment:

   python -m venv .env

2. Activate the environment:
   • Linux/macOS: source .env/bin/activate
   • Windows: .env\Scripts\activate
3. Install HypLL via pip:

   pip install hypll

If you use HypLL in your research, please cite the project using the following BibTeX entry:

@article{spengler2023hypll,
  title={HypLL: The Hyperbolic Learning Library},
  author={van Spengler, Max and Wirth, Philipp and Mettes, Pascal},
  journal={arXiv preprint arXiv:2306.06154},
  year={2023}
}