GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders

Martin Simonovsky 1, 2, 3 Nikos Komodakis 1, 2, 3
3 IMAGINE [Marne-la-Vallée]
LIGM - Laboratoire d'Informatique Gaspard-Monge, ENPC - École des Ponts ParisTech
Abstract : Deep learning on graphs has become a popular research topic with many applications. However, past work has concentrated on learning graph embedding tasks, 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 molecule generation.
Complete list of metadatas

Cited literature [24 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01990381
Contributor : Simonovsky Martin <>
Submitted on : Wednesday, January 23, 2019 - 9:35:24 AM
Last modification on : Tuesday, March 19, 2019 - 11:43:24 PM

File

icann_paper_long.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01990381, version 1

Collections

Citation

Martin Simonovsky, Nikos Komodakis. GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders. 27th International Conference on Artificial Neural Networks (ICANN), Oct 2018, Rhodes, Greece. ⟨hal-01990381⟩

Share

Metrics

Record views

42

Files downloads

157