Rethinking Gradient-Based Methods: Multi-Property Materials Design Beyond Differentiable Targets

TL;DR

This paper introduces SMOACS, a novel gradient-based method for multi-property materials design that effectively handles non-differentiable constraints and large crystal systems, outperforming existing approaches.

Contribution

The paper extends gradient-based optimization to address non-differentiable constraints and large-scale crystal structures, enabling multi-property materials design without retraining.

Findings

SMOACS successfully designs complex perovskite structures with multiple property constraints.

Outperforms existing generative and Bayesian optimization methods on five properties.

Scales effectively to large crystal systems, including 135-atom structures.

Abstract

Gradient-based methods offer a simple, efficient strategy for materials design by directly optimizing candidates using gradients from pretrained property predictors. However, their use in crystal structure optimization is hindered by two key challenges: handling non-differentiable constraints, such as charge neutrality and structural fidelity, and susceptibility to poor local minima. We revisit and extend the gradient-based methods to address these issues. We propose Simultaneous Multi-property Optimization using Adaptive Crystal Synthesizer (SMOACS), which integrates oxidation-number masks and template-based initialization to enforce non-differentiable constraints, avoid poor local minima, and flexibly incorporate additional constraints without retraining. SMOACS enables multi-property optimization. including exceptional targets such as high-temperature superconductivity, and scales to large crystal systems, both persistent challenges for generative models, even those enhanced with gradient-based guidance from property predictors. In experiments on five target properties and three datasets, SMOACS outperforms generative models and Bayesian optimization methods, successfully designing 135-atom perovskite structures that satisfy multiple property targets and constraints, a task at which the other methods fail entirely.