GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders

02/09/2018
by   Martin Simonovsky, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/14/2018

Designing Random Graph Models Using Variational Autoencoders With Applications to Chemical Design

Deep generative models have been praised for their ability to learn smoo...
research
05/19/2023

RGCVAE: Relational Graph Conditioned Variational Autoencoder for Molecule Design

Identifying molecules that exhibit some pre-specified properties is a di...
research
12/17/2019

SGVAE: Sequential Graph Variational Autoencoder

Generative models of graphs are well-known, but many existing models are...
research
09/07/2018

Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoders

Deep generative models have achieved remarkable success in various data ...
research
09/28/2018

Graph Generation via Scattering

Generative networks have made it possible to generate meaningful signals...
research
02/14/2020

Graph Deconvolutional Generation

Graph generation is an extremely important task, as graphs are found thr...
research
01/27/2022

GraphTune: A Learning-based Graph Generative Model with Tunable Structural Features

Generative models for graphs have been actively studied for decades, and...

Please sign up or login with your details

Forgot password? Click here to reset