DMFlow：通过流匹配生成无序材料
DMFlow: Disordered Materials Generation by Flow Matching
AI总结：
DMFlow通过流匹配框架生成无序材料，引入统一表示和黎曼流模型，实现对有序、取代性和位置性无序晶体的联合生成，提升材料发现效率。
摘要：
材料设计具有定制性质对于技术进步至关重要。然而，大多数深度生成模型仅专注于完美有序晶体，忽视了重要的无序材料类别。为解决这一差距，我们引入了DMFlow，一种专门用于无序晶体的生成框架。我们的方法引入了一种统一的表示方法，用于有序、取代性无序（SD）和位置性无序（PD）晶体，并采用流匹配模型联合生成所有结构组件。关键创新是一个黎曼流匹配框架，具有球形重参数化，这确保了概率单纯形上的物理有效的无序权重。向量场通过一种新的图神经网络（GNN）学习，该网络结合了物理对称性和专门的消息传递方案。最后，两阶段离散化程序将连续权重转换为多热原子分配。为了支持该领域的研究，我们发布了包含SD、PD和混合结构的基准数据集，这些结构来自晶体学开放数据库。在晶体结构预测（CSP）和从头生成（DNG）任务上的实验表明，DMFlow显著优于从有序晶体生成中改编的最先进基线。我们希望我们的工作为人工智能驱动的无序材料发现提供基础。
英文摘要：
The design of materials with tailored properties is crucial for technological progress. However, most deep generative models focus exclusively on perfectly ordered crystals, neglecting the important class of disordered materials. To address this gap, we introduce DMFlow, a generative framework specifically designed for disordered crystals. Our approach introduces a unified representation for ordered, Substitutionally Disordered (SD), and Positionally Disordered (PD) crystals, and employs a flow matching model to jointly generate all structural components. A key innovation is a Riemannian flow matching framework with spherical reparameterization, which ensures physically valid disorder weights on the probability simplex. The vector field is learned by a novel Graph Neural Network (GNN) that incorporates physical symmetries and a specialized message-passing scheme. Finally, a two-stage discretization procedure converts the continuous weights into multi-hot atomic assignments. To support research in this area, we release a benchmark containing SD, PD, and mixed structures curated from the Crystallography Open Database. Experiments on Crystal Structure Prediction (CSP) and De Novo Generation (DNG) tasks demonstrate that DMFlow significantly outperforms state-of-the-art baselines adapted from ordered crystal generation. We hope our work provides a foundation for the AI-driven discovery of disordered materials.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
