用可微分流程优化晶体结构，高效生成目标局部环境材料
Crystal Generation using the Fully Differentiable Pipeline and Latent Space Optimization
- 构建可微分管道，同时优化直接与潜在空间晶体表示
- 相比旧版CPU流程提速五倍，生成结果质量相当
- 双层优化策略提升复杂结构生成成功率，适合多组分系统
我们提出一种材料生成框架，将对称性约束的变分自编码器（CVAE）与可微分SO(3)谱目标结合，引导候选结构满足特定局部环境且符合晶格约束。特别地，实现了一个完全可微分的流水线，支持直接与潜在晶格表示的批量优化。借助GPU加速，该实现相较以往的CPU工作流提速约五倍，同时保持相近生成效果。此外，引入交替优化直接与潜在表示的策略，通过双层松弛有效避开由不同目标梯度定义的局部极小值，显著提升生成满足目标局部环境的复杂结构的成功率。该框架可扩展至多组分、多环境体系，为实现目标局部环境材料的规模化生成提供可行路径。
原文摘要 · Abstract (English)
We present a materials generation framework that couples a symmetry-conditioned variational autoencoder (CVAE) with a differentiable SO(3) power spectrum objective to steer candidates toward a specified local environment under the crystallographic constraints. In particular, we implement a fully differentiable pipeline to enable batch-wise optimization on both direct and latent crystallographic representations. Using the GPU acceleration, this implementation achieves about fivefold speed compared to our previous CPU workflow, while yielding comparable outcomes. In addition, we introduce the optimization strategy that alternatively performs optimization on the direct and latent crystal representations. This dual-level relaxation approach can effectively escape local minima defined by different objective gradients, thus increasing the success rate of generating complex structures satisfying the target local environments. This framework can be extended to systems consisting of multi-components and multi-environments, providing a scalable route to generate material structures with the target local environment.
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。