Con-CDVAE: A method for the conditional generation of crystal structures

TL;DR

Con-CDVAE is a novel generative model that enables targeted creation of crystal structures based on desired properties, advancing materials discovery with validated physical plausibility.

Contribution

We extend CDVAE with new components, a two-step training process, and three generation strategies for improved conditional crystal generation.

Findings

Effective generation of crystals with specified properties.

Model performance validated through extensive testing.

Generated crystals show physical credibility via DFT calculations.

Abstract

In recent years, progress has been made in generating new crystalline materials using generative machine learning models, though gaps remain in efficiently generating crystals based on target properties. This paper proposes the Con-CDVAE model, an extension of the Crystal Diffusion Variational Autoencoder (CDVAE), for conditional crystal generation. We introduce innovative components, design a two-step training method, and develop three unique generation strategies to enhance model performance. The effectiveness of Con-CDVAE is demonstrated through extensive testing under various conditions, including both single and combined property targets. Ablation studies further underscore the critical role of the new components in achieving our model's performance. Additionally, we validate the physical credibility of the generated crystals through Density Functional Theory (DFT) calculations, confirming Con-CDVAE's potential in material science research.