DISTAL：面向结构无关材料属性预测的蒸馏与自监督预训练框架
DISTAL: Distillation and Self-Supervised Pretraining for Structure-Agnostic Materials Property Prediction
- Jilin University（吉林大学）
- Jilin University of Chemical Technology（吉林化工学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对低数据下材料属性预测依赖结构的问题，提出 DISTAL 框架，结合自监督组成预训练与结构感知蒸馏，在 39 项基准任务中表现最优，实现仅基于组成的稳健预测。
AI中文摘要：
在低数据场景下，材料属性预测仍面临困难，许多目标属性仅由有限数量的标记样本支撑。预测精度最高的模型通常依赖晶体结构，这限制了它们在结构信息有限或不可用的早期筛选中的应用。为应对这一挑战，我们提出 DISTAL，一种面向结构无关材料属性预测的双先验框架，它结合了自监督组成预训练与结构感知知识蒸馏。DISTAL 首先利用 145 个组成衍生描述符，从大型虚拟组成空间中学习可迁移的组成表示；随后，它将预训练的 ALIGNN 教师模型中的结构知识蒸馏到以组成条件为约束的学生模型中。该设置允许在训练过程中使用结构先验，而无需在推理时提供结构输入。通过在统一预测流程中整合显式组成描述符、预训练潜在特征和蒸馏结构特征，DISTAL 捕获了仅从单一表示中难以恢复的互补信号。在 39 项基准任务中，性能最佳的多模态配置结合了所有三种信号，并在 37 项任务上优于参考基准；在所有评估的特征组合中，DISTAL 实现了最强的整体性能。这些结果表明，组成预训练和结构蒸馏提供了互补先验，为小数据材料信息学中仅基于组成的稳健预测提供了实用途径。源代码和预训练模型可匿名获取于此 https URL，接受后将在官方链接发布。
英文摘要：
Materials property prediction remains difficult in low-data settings, where many target properties are supported by only a limited number of labeled samples. Models with the strongest predictive accuracy often depend on crystal structures, which restricts their use in early-stage screening when structural information is limited or unavailable. To address this challenge, we propose DISTAL, a dual-prior framework for structure-agnostic materials property prediction that combines self-supervised compositional pretraining with structure-aware knowledge distillation. DISTAL first learns transferable compositional representations from a large virtual composition space using 145 composition-derived descriptors. It then distills structural knowledge from a pretrained ALIGNN teacher into a composition-conditioned student. This setting allows structural priors to be used during training without requiring structural inputs at inference. By integrating explicit compositional descriptors, pretrained latent features, and distilled structural features within a unified prediction pipeline, DISTAL captures complementary signals that are difficult to recover from any single representation alone. Across 39 benchmark tasks, the best-performing multimodal configuration combines all three signals, and improves over the reference benchmark on 37 tasks. DISTAL achieves the strongest overall performance among all evaluated feature combinations. These results indicate that compositional pretraining and structural distillation provide complementary priors and offer a practical route to robust composition-only prediction in small-data materials informatics. The source code and the pre-trained models are anonymously available at: https://osf.io/eq96d/overview?view_only=451617f42f7849e08750bd1852b48980 and will be released at the official link after acceptance.
