Study of Deep Generative Models for Inorganic Chemical Compositions
arXiv:1910.11499
Abstract
Generative models based on generative adversarial networks (GANs) and variational autoencoders (VAEs) have been widely studied in the fields of image generation, speech generation, and drug discovery, but, only a few studies have focused on the generation of inorganic materials. Such studies use the crystal structures of materials, but material researchers rarely store this information. Thus, we generate chemical compositions without using crystal information. We use a conditional VAE (CondVAE) and a conditional GAN (CondGAN) and show that CondGAN using the bag-of-atom representation with physical descriptors generates better compositions than other generative models. Also, we evaluate the effectiveness of the Metropolis-Hastings-based atomic valency modification and the extrapolation performance, which is important to material discovery.
arXiv comment10 pages
References in corpus (17)
- Conditional Generative Adversarial Nets
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
- SchNet - a deep learning architecture for molecules and materials
- Conditional Image Synthesis With Auxiliary Classifier GANs
- Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
- Semi-Supervised Learning with Deep Generative Models
- NIPS 2016 Tutorial: Generative Adversarial Networks
- Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models
- MolGAN: An implicit generative model for small molecular graphs
- Representation of compounds for machine-learning prediction of physical properties
- Generative Models for Automatic Chemical Design
- Learning Latent Subspaces in Variational Autoencoders
- A Two-Step Graph Convolutional Decoder for Molecule Generation
- DEFactor: Differentiable Edge Factorization-based Probabilistic Graph Generation
- Data-Driven Approach to Encoding and Decoding 3-D Crystal Structures
- Preventing Posterior Collapse with delta-VAEs