Graph Deconvolutional Generation
arXiv:2002.07087
Abstract
Graph generation is an extremely important task, as graphs are found throughout different areas of science and engineering. In this work, we focus on the modern equivalent of the Erdos-Renyi random graph model: the graph variational autoencoder (GVAE). This model assumes edges and nodes are independent in order to generate entire graphs at a time using a multi-layer perceptron decoder. As a result of these assumptions, GVAE has difficulty matching the training distribution and relies on an expensive graph matching procedure. We improve this class of models by building a message passing neural network into GVAE's encoder and decoder. We demonstrate our model on the specific task of generating small organic molecules
References in corpus (12)
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- Semi-Supervised Classification with Graph Convolutional Networks
- Convolutional Networks on Graphs for Learning Molecular Fingerprints
- MolGAN: An implicit generative model for small molecular graphs
- Learning Deep Generative Models of Graphs
- Gated Graph Sequence Neural Networks
- Constrained Graph Variational Autoencoders for Molecule Design
- Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation
- Syntax-Directed Variational Autoencoder for Structured Data
- Order Matters: Sequence to sequence for sets
- Efficient Graph Generation with Graph Recurrent Attention Networks
- Graphite: Iterative Generative Modeling of Graphs