CrystalFlow: A Flow-Based Generative Model for Crystalline Materials

TL;DR

CrystalFlow is a novel flow-based generative model that efficiently produces high-quality crystalline material structures by capturing symmetries and enabling conditional generation, advancing computational materials science.

Contribution

We introduce CrystalFlow, a flow-based model utilizing continuous normalizing flows and graph neural networks for realistic and conditional crystal structure generation.

Findings

Achieves state-of-the-art performance on standard benchmarks.

Enables versatile conditional generation for specific material properties.

Effectively captures symmetries in crystalline data.

Abstract

Deep learning-based generative models have emerged as powerful tools for modeling complex data distributions and generating high-fidelity samples, offering a transformative approach to efficiently explore the configuration space of crystalline materials. In this work, we present CrystalFlow, a flow-based generative model specifically developed for the generation of crystalline materials. CrystalFlow constructs Continuous Normalizing Flows to model lattice parameters, atomic coordinates, and/or atom types, which are trained using Conditional Flow Matching techniques. Through an appropriate choice of data representation and the integration of a graph-based equivariant neural network, the model effectively captures the fundamental symmetries of crystalline materials, which ensures data-efficient learning and enables high-quality sampling. Our experiments demonstrate that CrystalFlow achieves state-of-the-art performance across standard generation benchmarks, and exhibits versatile conditional generation capabilities including producing structures optimized for specific external pressures or desired material properties. These features highlight the model's potential to address realistic crystal structure prediction challenges, offering a robust and efficient framework for advancing data-driven research in condensed matter physics and material science.