提出几何不变损失函数，提升非聚合物晶体结构预测精度
Challenges in Non-Polymeric Crystal Structure Prediction: Why a Geometric, Permutation-Invariant Loss is Needed
- 设计兼顾几何特性和分子排列不变性的新损失函数
- 简单回归模型在COD-Cluster17上超越流匹配等先进方法
- 适用于材料设计与药物发现中的分子晶体生成任务
晶体结构预测是设计具有特定性能材料的关键步骤，但在材料设计与药物发现中仍具挑战性。尽管计算材料科学取得进展，准确预测三维非聚合物晶体结构依然困难。本文聚焦分子组装问题：一组相同刚性分子$\\(mathcal{S}\\)$被堆积形成晶态结构。该简化模型可近似实际问题。然而，当前先进方法虽采用复杂技术，其学习目标仍存在定义不清的问题。我们提出一种新公式，引入捕捉关键几何分子属性且对$\\(mathcal{S}\\)$实现排列不变性的损失函数。显著的是，在此框架下，简单回归模型已在COD-Cluster17基准（晶体学开放数据库的非聚合物子集）上超越先前方法，包括流匹配技术。
原文摘要 · Abstract (English)
Crystalline structure prediction is an essential prerequisite for designing materials with targeted properties. Yet, it is still an open challenge in materials design and drug discovery. Despite recent advances in computational materials science, accurately predicting three-dimensional non-polymeric crystal structures remains elusive. In this work, we focus on the molecular assembly problem, where a set $\mathcal{S}$ of identical rigid molecules is packed to form a crystalline structure. Such a simplified formulation provides a useful approximation to the actual problem. However, while recent state-of-the-art methods have increasingly adopted sophisticated techniques, the underlying learning objective remains ill-posed. We propose a better formulation that introduces a loss function capturing key geometric molecular properties while ensuring permutation invariance over $\mathcal{S}$. Remarkably, we demonstrate that within this framework, a simple regression model already outperforms prior approaches, including flow matching techniques, on the COD-Cluster17 benchmark, a curated non-polymeric subset of the Crystallography Open Database (COD).
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。