Structural Constraint Integration in Generative Model for Discovery of Quantum Material Candidates

TL;DR

This paper introduces SCIGEN, a novel method that integrates structural constraints into generative diffusion models to efficiently discover stable quantum material candidates with specific geometric patterns.

Contribution

The paper presents a new framework, SCIGEN, that modifies diffusion models with structural constraints, enabling targeted generation of quantum materials with high stability.

Findings

Generated 8 million compounds with prototype constraints.

Over 10% of generated compounds passed stability screening.

More than 50% of stable compounds passed DFT structural optimization.

Abstract

Billions of organic molecules are known, but only a tiny fraction of the functional inorganic materials have been discovered, a particularly relevant problem to the community searching for new quantum materials. Recent advancements in machine-learning-based generative models, particularly diffusion models, show great promise for generating new, stable materials. However, integrating geometric patterns into materials generation remains a challenge. Here, we introduce Structural Constraint Integration in the GENerative model (SCIGEN). Our approach can modify any trained generative diffusion model by strategic masking of the denoised structure with a diffused constrained structure prior to each diffusion step to steer the generation toward constrained outputs. Furthermore, we mathematically prove that SCIGEN effectively performs conditional sampling from the original distribution, which is crucial for generating stable constrained materials. We generate eight million compounds using Archimedean lattices as prototype constraints, with over 10% surviving a multi-staged stability pre-screening. High-throughput density functional theory (DFT) on 26,000 survived compounds shows that over 50% passed structural optimization at the DFT level. Since the properties of quantum materials are closely related to geometric patterns, our results indicate that SCIGEN provides a general framework for generating quantum materials candidates.