GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders

Martin Simonovsky, Nikos Komodakis

Abstract: Deep learning on graphs has become a popular research topic with many applications. However, past work has concentrated on learning graph embedding tasks only, which is in contrast with advances in generative models for images and text. Is it possible to transfer this progress to the domain of graphs? We propose to sidestep hurdles associated with linearization of such discrete structures by having a decoder output a probabilistic fully-connected graph of a predefined maximum size directly at once. Our method is formulated as a variational autoencoder. We evaluate on the challenging task of conditional molecule generation.

TL;DR: We demonstate an autoencoder for graphs.

Keywords: graph, generative model, autoencoder

Data: [ZINC](https://paperswithcode.com/dataset/zinc)

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:1802.03480/code)