torchkge 0.8.0

Knowledge Graph embedding in Python and Pytorch.

TorchKGE

TorchKGE: Knowledge Graph embedding in Python and Pytorch.

• Free software: BSD license

• Documentation: https://torchkge.readthedocs.io.

Features

• Translational models (TransE, TransH, TransR, TransD)

• Semantic Matching models (RESCAL, DistMult)

More models to come.

Credits

This package was created with Cookiecutter and the audreyr/cookiecutter-pypackage project template.

History

0.7.0 (2019-06-01)

• Implemented Mean Reciprocal Rank measure of performance.

• Implemented Logistic Loss.

• Changed implementation of margin loss to use torch methods.

0.6.0 (2019-06-25)

• Implemented DistMult

0.5.0 (2019-06-24)

• Changed implementation of LinkPrediction ranks by moving functions to model methods.

• Implemented RESCAL.

0.4.0 (2019-05-15)

• Fixed a major bug/problem in the Evaluation protocol of LinkPrediction.

0.3.1 (2019-05-10)

• Minor bug fixes in the various normalization functions.

0.3.0 (2019-05-09)

• Fixed CUDA support.

0.2.0 (2019-05-07)

• Added support for filtered performance measures.

0.1.7 (2019-04-03)

• First real release on PyPI.

0.1.0 (2019-04-01)

• First release on PyPI.