Generative Inverse Design of Crystal Structures via Diffusion Models with Transformers

TL;DR

This paper introduces a novel diffusion model with a Transformer backbone for the inverse design of crystal structures, demonstrating superior versatility and effectiveness in generating materials with desired properties.

Contribution

The study presents a new diffusion-based generative model for crystal structures that outperforms previous methods and explores dataset-dependent conditioning strategies.

Findings

Model outperforms previous methods in generating crystal structures

Versatility in generating structures with desired properties

Optimal conditioning methods vary by dataset

Abstract

Recent advances in deep learning have enabled the generation of realistic data by training generative models on large datasets of text, images, and audio. While these models have demonstrated exceptional performance in generating novel and plausible data, it remains an open question whether they can effectively accelerate scientific discovery through the data generation and drive significant advancements across various scientific fields. In particular, the discovery of new inorganic materials with promising properties poses a critical challenge, both scientifically and for industrial applications. However, unlike textual or image data, materials, or more specifically crystal structures, consist of multiple types of variables - including lattice vectors, atom positions, and atomic species. This complexity in data give rise to a variety of approaches for representing and generating such data. Consequently, the design choices of generative models for crystal structures remain an open question. In this study, we explore a new type of diffusion model for the generative inverse design of crystal structures, with a backbone based on a Transformer architecture. We demonstrate our models are superior to previous methods in their versatility for generating crystal structures with desired properties. Furthermore, our empirical results suggest that the optimal conditioning methods vary depending on the dataset.