GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders

By Martin Simonovsky, Nikos Komodakis. 2018

1,007 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Generative Models, Graph Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Generative Models

In Graph Learning

Citations in the corpus

Object-Centric Learning with Slot Attention (2020, background): “Set representations are commonly used in tasks across many data modalities ranging from point cloud prediction [29, 30], classifying multiple objects in an image [31], or generation of molecules with desired properties [32, 33].”
Score-based Generative Modeling in Latent Space (2021, methodology): “LSGM would allow to model graph data more naturally using encoders and decoders tailored to graphs [43, 44, 45, 46].”
Multiset-Equivariant Set Prediction with Approximate Implicit Differentiation (2021, background): “Since sets are closely related to graphs, there are also natural extensions to molecule generation (Simonovsky & Komodakis, 2018) and scene graph prediction (Krishna et al., 2017; Xu et al., 2017).”
E(n) Equivariant Graph Neural Networks (2021, background): “A Graph Autoencoder can learn unsupervised representations of graphs in a continuous latent space (Kipf & Welling, 2016b; Simonovsky & Komodakis, 2018).”
Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation (2018, background): “Note that both scores are calculated from empirical prediction models whose parameters are estimated from related datasets [41, 1], and these scores are widely used in previous molecule generation papers [9, 22, 4, 39, 27].”
Learning Multimodal Graph-to-Graph Translation for Molecular Optimization (2018, background): “Recently proposed graph decoders (Simonovsky & Komodakis, 2018; Li et al., 2018b; Jin et al., 2018; You et al., 2018b; Liu et al., 2018) focus on learning generative models of graphs.”
GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models (2018, methodology): “For example, Simonovsky & Komodakis 2018 propose a VAE-based approach, while Li et al. 2018 propose a framework based upon graph neural networks.”
A Comprehensive Survey on Graph Neural Networks (2019, background): “Graph Variational Autoencoder (GraphVAE) [67] models the existence of nodes and edges as independent random variables.”
Permutation Invariant Graph Generation via Score-Based Generative Modeling (2020, methodology): “Examples include GraphVAE (Simonovsky and Komodakis, 2018), Graphite (Grover et al., 2018), and junction tree variational autoencoders (Jin et al., 2018).”
GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation (2020, methodology): “JT-VAE has been shown to outperform other previous VAE-based models (Kusner et al., 2017; G´omez-Bombarelli et al., 2018; Simonovsky & Komodakis, 2018).”
MolGAN: An implicit generative model for small molecular graphs (2018, methodology): “The number of samples differs from the previous experiment to be in line with the setting in Simonovsky & Komodakis (2018).”
Deep Set Prediction Networks (2019, methodology): “This has been used for predicting point clouds [1; 5], bounding boxes [15; 2], and graphs (sets of nodes and edges) [3; 17].”
GraphQA: protein model quality assessment using graph convolutional networks (2020, background): “…2018a), drug-drug interaction (Zitnik et al., 2018), drug-target interaction (Gao et al., 2018) molecular optimization (Jin et al., 2019), and generation of proteins, molecules and drugs (Ingraham et al., 2019a; You et al., 2018; Liu et al., 2018; Li et al., 2018b; Simonovsky & Komodakis, 2018).”
Does Unsupervised Architecture Representation Learning Help Neural Architecture Search? (2020, methodology): “While [40, 41] use graph VAE for the generative problems, we focus on mapping the finite discrete neural architectures into the continuous latent space regularized by KL-divergence such that each architecture is encoded into a unique area in the latent space.”
Efficient Graph Generation with Graph Recurrent Attention Networks (2019, methodology): “We implement a GraphVAE model where the encoder is a 3 -layer GCN and decoder is a MLP with 2 hidden layers.”