Knowledge Graph embedding in Python and Pytorch.
Project description
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.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for torchkge-0.8.0-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | f78e362930e19eec1f00080a6620757445045457552ce32e131a3acbcb3b7507 |
|
MD5 | 7df6264bcd944c7b6a9b64c746f17c26 |
|
BLAKE2b-256 | f528b36c99d2d6e2a888ad54970606f9252af22388769afe404e55140dc166f4 |