Towards Variational Generation of Small Graphs

Martin Simonovsky (1, 2, 3) , Nikos Komodakis (1, 2, 3)

1 ENPC - École des Ponts ParisTech
2 LIGM - Laboratoire d'Informatique Gaspard-Monge
3 imagine [Marne-la-Vallée]

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.

Domaines: Apprentissage [cs.LG]; Réseau de neurones [cs.NE]; Vision par ordinateur et reconnaissance de formes [cs.CV]

Martin Simonovsky, Nikos Komodakis. Towards Variational Generation of Small Graphs. ICLR 2018 Workshop track (Sixth International Conference on Learning Representations), Apr 2018, Vancouver, Canada. ⟨hal-01801194⟩