Skip to content

Latest commit

 

History

History
20 lines (11 loc) · 856 Bytes

README.md

File metadata and controls

20 lines (11 loc) · 856 Bytes

Poincaré Embeddings for Learning Hierarchical Representations

This is the NumPy and PyTorch implementation. Link to paper

The difference of results between implementations is due to the different sampling methods.

Results:

NumPy implementation

https://github.com/qiangsiwei/poincare_embedding/blob/master/data/mammal_numpy.png

PyTorch implementation

https://github.com/qiangsiwei/poincare_embedding/blob/master/data/mammal_torch.png

TensorFlow implementation

https://github.com/qiangsiwei/poincare_embedding/blob/master/data/mammal_tensor.png