Poincaré Embeddings for Learning Hierarchical Representations

PyTorch implementation of Poincaré Embeddings for Learning Hierarchical Representations

Example: Embedding WordNet Mammals

To embed the transitive closure of the WordNet mammals subtree, first generate the data via

cd wordnet
make

This will generate the transitive closure of the full noun hierarchy as well as of the mammals subtree of WordNet.

To embed the mammals subtree in the reconstruction setting (i.e., without missing data), go to the root directory of the project and run

NTHREADS=2 ./example.sh

This shell script includes the appropriate parameter settings for the mammals subtree and saves the trained model as mammals.pth.

The embeddings are trained via multithreaded async SGD. In the example above, the number of threads is set to a conservative setting (NHTREADS=2) which should run well even on smaller machines. On machines with many cores, increase NTHREADS for faster convergence.

Installation

Simply clone this repository via

git clone https://github.com/facebookresearch/poincare-embeddings.git
cd poincare-embeddings

Dependencies

• Python 3 with NumPy
• PyTorch
• Scikit-Learn
• NLTK (to generate the WordNet data)

References

If you find this code useful for your research, please cite the following paper in your publication:

@incollection{nickel2017poincare,
  title = {Poincar\'{e} Embeddings for Learning Hierarchical Representations},
  author = {Nickel, Maximilian and Kiela, Douwe},
  booktitle = {Advances in Neural Information Processing Systems 30},
  editor = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
  pages = {6341--6350},
  year = {2017},
  publisher = {Curran Associates, Inc.},
  url = {http://papers.nips.cc/paper/7213-poincare-embeddings-for-learning-hierarchical-representations.pdf}
}

License

This code is licensed under CC-BY-NC 4.0.