Open Materials Generation with Stochastic Interpolants

TL;DR

This paper introduces OMatG, a novel generative framework using stochastic interpolants for designing and discovering inorganic crystalline materials, achieving state-of-the-art results in structure prediction and novel material generation.

Contribution

It adapts stochastic interpolants with equivariant graph representations for crystal structures, extending generative modeling capabilities in materials science.

Findings

Sets new state-of-the-art in crystal structure prediction and de novo generation.

Outperforms previous flow-based and diffusion-based models.

Demonstrates the effectiveness of flexible deep learning frameworks in materials discovery.

Abstract

The discovery of new materials is essential for enabling technological advancements. Computational approaches for predicting novel materials must effectively learn the manifold of stable crystal structures within an infinite design space. We introduce Open Materials Generation (OMatG), a unifying framework for the generative design and discovery of inorganic crystalline materials. OMatG employs stochastic interpolants (SI) to bridge an arbitrary base distribution to the target distribution of inorganic crystals via a broad class of tunable stochastic processes, encompassing both diffusion models and flow matching as special cases. In this work, we adapt the SI framework by integrating an equivariant graph representation of crystal structures and extending it to account for periodic boundary conditions in unit cell representations. Additionally, we couple the SI flow over spatial coordinates and lattice vectors with discrete flow matching for atomic species. We benchmark OMatG's performance on two tasks: Crystal Structure Prediction (CSP) for specified compositions, and 'de novo' generation (DNG) aimed at discovering stable, novel, and unique structures. In our ground-up implementation of OMatG, we refine and extend both CSP and DNG metrics compared to previous works. OMatG establishes a new state of the art in generative modeling for materials discovery, outperforming purely flow-based and diffusion-based implementations. These results underscore the importance of designing flexible deep learning frameworks to accelerate progress in materials science. The OMatG code is available at https://github.com/FERMat-ML/OMatG.