Skip to content
A simple Tensorflow implementation of https://arxiv.org/abs/1906.04985
Python
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
.idea
data
vkge
.DS_Store
.gitignore
LICENSE
README.md
main_LFM.py
main_LIM.py
requirements.txt
setup.cfg
setup.py

README.md

Neural-Variational-Knowledge-Graphs

Overview

This library contains a Tensorflow implementation of the Laten Fact Model and Latent Information model for Gaussian and Von-Mises Fisher latent priors, using the re-parametrisation trick to learn the distributional parameters. The VMF re-parametrisation trick is as presented in [1](http://arxiv.org/abs/1804.00891). Check out the authors of VMF blogpost (https://nicola-decao.github.io/s-vae). The Gaussian re-parametrisation trick is a Tensorflow probability function.


From paper

Dependencies

Installation

To install, run

$ python setup.py install

Structure


CONTRIBUTERS:

  • Alexander Cowen-Rivers (GitHub)

Supervisors:


Instructions

For:


Training Models

Train variational knowledge graph model, on nations dataset with normal prior using DistMult scoring function :

python main_LIM.py  --no_batches 10 --epsilon 1e-07 --embedding_size 50 --dataset nations --alt_prior False --lr 0.001 --score_func DistMult --negsamples 5 --projection False --distribution normal --file_name /User --s_o False

Usage

  1. Clone or download this repository.
  2. Prepare your data, or use any of the six included KG datasets.

Usage

Please cite [1] and [2] in your work when using this library in your experiments.

Feedback

For questions and comments, feel free to contact ACR(mailto:mc_rivers@icloud.com).

License

MIT

Citation

[1] Davidson, T. R., Falorsi, L., De Cao, N., Kipf, T.,
and Tomczak, J. M. (2018). Hyperspherical Variational
Auto-Encoders. arXiv preprint arXiv:1804.00891.

BibTeX format:

@article{s-vae18,
  title={Hyperspherical Variational Auto-Encoders},
  author={Davidson, Tim R. and
          Falorsi, Luca and
          De Cao, Nicola and
          Kipf, Thomas and
          Tomczak, Jakub M.},
  journal={arXiv preprint arXiv:1804.00891},
  year={2018}
}
You can’t perform that action at this time.