Multiresolution equivariant graph variational autoencoder

In this paper, we propose Multiresolution Equivariant Graph Variational Autoencoders (MGVAE), the first hierarchical generative model to learn and generate graphs in a multiresolution and equivariant manner. At each resolution level, MGVAE employs higher order message passing to encode the graph whi...

Full description

Saved in:
Bibliographic Details
Published in:Machine learning: science and technology Vol. 4; no. 1; pp. 15031 - 15054
Main Authors: Hy, Truong Son, Kondor, Risi
Format: Journal Article
Language:English
Published: Bristol IOP Publishing 01.03.2023
Subjects:
Coarsening
graph neural networks
graph variational autoencoders
Graphs
hierarchical generative models
Image processing
Learning
Message passing
Molecular properties
molecule generation
Permutations
supervised and unsupervised molecular representation learning
ISSN:2632-2153, 2632-2153
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we propose Multiresolution Equivariant Graph Variational Autoencoders (MGVAE), the first hierarchical generative model to learn and generate graphs in a multiresolution and equivariant manner. At each resolution level, MGVAE employs higher order message passing to encode the graph while learning to partition it into mutually exclusive clusters and coarsening into a lower resolution that eventually creates a hierarchy of latent distributions. MGVAE then constructs a hierarchical generative model to variationally decode into a hierarchy of coarsened graphs. Importantly, our proposed framework is end-to-end permutation equivariant with respect to node ordering. MGVAE achieves competitive results with several generative tasks including general graph generation, molecular generation, unsupervised molecular representation learning to predict molecular properties, link prediction on citation graphs, and graph-based image generation. Our implementation is available at https://github.com/HyTruongSon/MGVAE .
Bibliography:MLST-100828.R1
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2632-2153
2632-2153
DOI:10.1088/2632-2153/acc0d8