Assessing Deep Generative Models in Chemical Composition Space

06 July 2022, Version 1
This content is a preprint and has not undergone peer review at the time of posting.


The computational discovery of novel materials has been one of the main motivations behind research in theoretical chemistry for several decades. Despite much effort, this is far from a solved problem, however. Among other reasons, this is due to the enormous space of possible structures and compositions that could potentially be of interest. In the case of inorganic materials, this is exacerbated by the combinatorics of the periodic table, since even a single crystal structure can in principle display millions of compositions. Consequently, there is a need for tools that enable a more guided exploration of the materials design space. Here, generative machine learning (ML) models have recently emerged as a promising technology. In this work, we assess the performance of a range of deep generative models based on Reinforcement Learning (RL), Variational Autoencoders (VAE) and Generative Adversarial Networks (GAN) for the prototypical case of designing Elpasolite compositions with low formation energies. By relying on the fully enumerated space of 2~million main group Elpasolites, the precision, coverage and diversity of the generated materials is rigorously assessed. Additionally, a hyperparameter selection scheme for generative models in chemical composition space is developed.


generative model
materials discovery
variational autoencoder
reinforcement learning


Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.