SGVAE: Sequential Graph Variational Autoencoder
Machine Learning
2019-12-18 v1 Machine Learning
Abstract
Generative models of graphs are well-known, but many existing models are limited in scalability and expressivity. We present a novel sequential graphical variational autoencoder operating directly on graphical representations of data. In our model, the encoding and decoding of a graph as is framed as a sequential deconstruction and construction process, respectively, enabling the the learning of a latent space. Experiments on a cycle dataset show promise, but highlight the need for a relaxation of the distribution over node permutations.
Cite
@article{arxiv.1912.07800,
title = {SGVAE: Sequential Graph Variational Autoencoder},
author = {Bowen Jing and Ethan A. Chi and Jillian Tang},
journal= {arXiv preprint arXiv:1912.07800},
year = {2019}
}