用预训练模型指导梯度优化，高效设计满足多约束的晶体。
Adaptable Method for Crystal Design across Diverse Constraints and Objectives with Pretrained Property Predictors
- 用现成预测器+元素掩码+模板初始化，无需重训练。
- 在钙钛矿中三目标两约束下优于生成与贝叶斯方法。
- 模块化框架可灵活适配半金属等不同应用需求。
先进晶体设计可加速光伏到自旋电子学等领域的材料发现。实际设计需满足多种性质和物理约束，但现有基于机器学习的方法常依赖大量数据、重新训练或任务专用生成器。本文展示，通过结合现成预测器、位点级元素掩码、模板初始化和任务特定损失，直接由预测器引导的梯度优化可实现数据高效、约束丰富的晶体设计。在钙钛矿中，该方法在带隙、形成能和容忍因子三个目标及两个硬约束下均优于生成模型与贝叶斯基线。密度泛函理论（DFT）评估显示，尽管所用预测器仅训练于约十分之一的数据量，其带隙目标性能仍媲美领先生成模型。通过灵活组合预训练预测器、应用导向掩码与定制损失，同一框架还支持半金属设计。这种模块化策略使研究人员能以极低计算成本，将多样化应用需求直接转化为优化候选晶体。
原文摘要 · Abstract (English)
Advanced crystal design can accelerate materials discovery across applications from photovoltaics to spintronics. Practical design must satisfy multiple properties and physical constraints, yet existing machine-learning-based approaches to such design often depend on large datasets, retraining, or task-specific generators. Here, we show that direct predictor-guided gradient optimization enables data-efficient, constraint-rich crystal design by combining off-the-shelf predictors with site-wise element masks, template initialization, and task-specific losses. In perovskites, it outperformed generative and Bayesian baselines under three targets -- band gap, formation energy, and tolerance factor -- and two hard constraints. DFT assessment further showed band-gap targeting competitive with a leading generative model despite using predictors trained on roughly one-tenth of the data. By flexibly combining pretrained predictors with application-oriented masks and custom losses, the same framework supported half-metal design. Such modularity could help researchers and engineers translate diverse application requirements directly into optimized candidate crystals with minimal computational cost.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。