Crystal Diffusion Variational Autoencoder for Periodic Material Generation

TL;DR

This paper introduces a novel generative model, the Crystal Diffusion Variational Autoencoder, which effectively captures physical and invariance constraints to generate realistic, stable periodic materials, outperforming previous methods in multiple tasks.

Contribution

The paper presents a new diffusion-based VAE that incorporates physical stability and invariance properties for periodic material generation, advancing the state-of-the-art in material design.

Findings

Outperforms previous methods in reconstructing input structures

Generates valid, diverse, and realistic materials

Optimizes specific material properties effectively

Abstract

Generating the periodic structure of stable materials is a long-standing challenge for the material design community. This task is difficult because stable materials only exist in a low-dimensional subspace of all possible periodic arrangements of atoms: 1) the coordinates must lie in the local energy minimum defined by quantum mechanics, and 2) global stability also requires the structure to follow the complex, yet specific bonding preferences between different atom types. Existing methods fail to incorporate these factors and often lack proper invariances. We propose a Crystal Diffusion Variational Autoencoder (CDVAE) that captures the physical inductive bias of material stability. By learning from the data distribution of stable materials, the decoder generates materials in a diffusion process that moves atomic coordinates towards a lower energy state and updates atom types to satisfy bonding preferences between neighbors. Our model also explicitly encodes interactions across periodic boundaries and respects permutation, translation, rotation, and periodic invariances. We significantly outperform past methods in three tasks: 1) reconstructing the input structure, 2) generating valid, diverse, and realistic materials, and 3) generating materials that optimize a specific property. We also provide several standard datasets and evaluation metrics for the broader machine learning community.