- This is Pytorch implementation Variational Graph Auto Encoder by Thomas N. Kipf & Max Welling.
- VGAE is tool which helps in to find the hidden links within graph network. As an Encoder it uses Graph Convolution Network and at the Deocoder side it uses simple inner product decoder followed by the sigmoid activation function. More information is available in the presentation.
- https://towardsdatascience.com/intuitively-understanding-variational-autoencoders-1bfe67eb5daf
- https://towardsdatascience.com/tutorial-on-variational-graph-auto-encoders-da9333281129
- https://towardsdatascience.com/how-to-do-deep-learning-on-graphs-with-graph-convolutional-networks-7d2250723780
- https://www.countbayesie.com/blog/2017/5/9/kullback-leibler-divergence-explained
@article{kipf2016variational,
title={Variational Graph Auto-Encoders},
author={Kipf, Thomas N and Welling, Max},
journal={NIPS Workshop on Bayesian Deep Learning},
year={2016}
}
Disclaimer: Original implementation in Tensorflow as well as data is availabel here. https://github.com/tkipf/gae/tree/master/gae