QR kód

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...

Celý popis

Uloženo v:
Hlavní autoři: Truong Son Hy, Risi Kondor
Médium: Artigo
Jazyk:Inglês
Vydáno: IOP Publishing 2023-01-01
Edice:Machine Learning: Science and Technology
Témata:
graph neural networks
graph variational autoencoders
hierarchical generative models
molecule generation
supervised and unsupervised molecular representation learning
On-line přístup:https://doi.org/10.1088/2632-2153/acc0d8
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Podobné jednotky