Towards Variational Generation of Small Graphs

Martin Simonovsky, Nikos Komodakis

Abstract: In this paper we propose a generative model for graphs formulated as a variational autoencoder. We sidestep hurdles associated with linearization of graphs by having the decoder output a probabilistic fully-connected graph of a predefined maximum size directly at once. We evaluate on the challenging task of molecule generation.

TL;DR: We present an autoencoder for graphs.

Keywords: graph, generative model, autoencoder