torchkge-team/ torchkge

(v0.16.22) 25 days ago

Python

Need help with torchkge?

Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

torchkge-team

157 Stars

17 Forks

Other

725 Commits

1 Opened issues

Description

TorchKGE: Knowledge Graph embedding in Python and PyTorch.

Services available

Need anything else?

Contributors list

Readme

========

TorchKGE

Name: torchkge
Brand: torchkge
SKU: //torchkge-team/torchkge
Rating: 2.1425 (157 reviews)

.. image:: https://graphs.telecom-paristech.fr/images/logotorchKGEsmall.png :align: right :width: 100px :alt: logo torchkge

.. image:: https://img.shields.io/pypi/v/torchkge.svg :target: https://pypi.python.org/pypi/torchkge

.. image:: https://travis-ci.com/torchkge-team/torchkge.svg?branch=master :target: https://travis-ci.com/torchkge-team/torchkge

.. image:: https://readthedocs.org/projects/torchkge/badge/?version=latest :target: https://torchkge.readthedocs.io/en/latest/?badge=latest :alt: Documentation Status

.. image:: https://pyup.io/repos/github/torchkge-team/torchkge/shield.svg :target: https://pyup.io/repos/github/torchkge-team/torchkge/ :alt: Updates

TorchKGE: Knowledge Graph embedding in Python and Pytorch.

TorchKGE is a Python module for knowledge graph (KG) embedding relying solely on Pytorch. This package provides researchers and engineers with a clean and efficient API to design and test new models. It features a KG data structure, simple model interfaces and modules for negative sampling and model evaluation. Its main strength is a highly efficient evaluation module for the link prediction task, a central application of KG embedding. It has been

observed

_ to be up to five times faster than

AmpliGraph

_ and twenty-four times faster than

OpenKE

_. Various KG embedding models are also already implemented. Special attention has been paid to code efficiency and simplicity, documentation and API consistency. It is distributed using PyPI under BSD license.

Citations

If you find this code useful in your research, please consider citing our

paper

_ (presented at

IWKG-KDD

_ 2020):

.. code-block::

@inproceedings{arm2020torchkge,
    title={TorchKGE: Knowledge Graph Embedding in Python and PyTorch},
    author={Armand Boschin},
    year={2020},
    month={Aug},
    booktitle={International Workshop on Knowledge Graph: Mining Knowledge Graph for Deep Insights},
}

Free software: BSD license
Documentation: https://torchkge.readthedocs.io.