Awesome Open Source
Awesome Open Source

NEW

A much faster version (in PyTorch) is available here: https://github.com/baharefatemi/SimplE

Summary

This software can be used to reproduce the results in our "SimplE Embedding for Link Prediction in Knowledge Graphs" paper. It can be also used to learn SimplE models for other datasets. The software can be also used as a framework to implement new tensor factorization models (implementations for TransE and ComplEx are included as two examples).

Dependencies

  • Python version 2.7
  • Numpy version 1.13.1
  • Tensorflow version 1.1.0

Usage

To run a model M on a dataset D, do the following steps:

  • cd to the directory where main.py is
  • Run python main.py -m M -d D

Examples (commands start after $):

$ python main.py -m SimplE_ignr -d wn18
$ python main.py -m SimplE_avg -d fb15k
$ python main.py -m ComplEx -d wn18

Running a model M on a dataset D will save the embeddings in a folder with the following address:

$ <Current Directory>/M_weights/D/

As an example, running the SimplE_ignr model on wn18 will save the embeddings in the following folder:

$ <Current Directory>/SimplE_ignr_weights/wn18/

Learned Embeddings for SimplE

The best embeddings learned for SimplE_ignr and SimplE_avg on wn18 and fb15k can be downloaded from this link and this link respectively.

To use these embeddings, place them in the same folder as main.py, load the embeddings and use them.

Publication

Refer to the following publication for details of the models and experiments.

Cite SimplE

If you use this package for published work, please cite one (or both) of the following:

@inproceedigs{kazemi2018simple,
  title={SimplE Embedding for Link Prediction in Knowledge Graphs},
  author={Kazemi, Seyed Mehran and Poole, David},
  booktitle={Advances in Neural Information Processing Systems},
  year={2018}
}

@phdthesis{Kazemi_2018, 
  series={Electronic Theses and Dissertations (ETDs) 2008+}, 
  title={Representing and learning relations and properties under uncertainty}, 
  url={https://open.library.ubc.ca/collections/ubctheses/24/items/1.0375812}, 
  DOI={http://dx.doi.org/10.14288/1.0375812}, 
  school={University of British Columbia}, 
  author={Kazemi, Seyed Mehran}, 
  year={2018}, 
  collection={Electronic Theses and Dissertations (ETDs) 2008+}
}

Contact

Seyed Mehran Kazemi

Computer Science Department

The University of British Columbia

201-2366 Main Mall, Vancouver, BC, Canada (V6T 1Z4)

http://www.cs.ubc.ca/~smkazemi/

[email protected]

License

Licensed under the GNU General Public License Version 3.0. https://www.gnu.org/licenses/gpl-3.0.en.html

Copyright (C) 2018 Seyed Mehran Kazemi


Get A Weekly Email With Trending Projects For These Topics
No Spam. Unsubscribe easily at any time.
python (54,621
tensorflow (2,161
knowledge-graph (126
knowledge-base (40
knowledgebase (30
link-prediction (18