元素先验与目标支撑塑造材料图网络中的化学迁移
Element priors and target support shape chemical transfer in materials graph networks
浏览论文内容
中文总结 AI 辅助
该研究通过拆分元素与增量目标支撑区分材料图网络的两类化学迁移路径，发现少量含目标结构可显著降低误差，为弱表示化学区域的材料预测提供了方法支撑。
中文摘要 AI 辅助
材料图神经网络常需迁移至训练数据中弱表示的化学区域，这类迁移可依赖元素间的预定义关系或含目标结构的监督证据，但这些路径通常相互纠缠。本文利用留出元素拆分与增量目标支撑来区分二者作用：无含目标的训练结构时，形成能误差强烈依赖元素表示，尤其对H、O、F；匹配扰动显示，除输入维度或数值形式外，表示诱导的共享也很重要，而无标签相似度图先验可减少部分零样本误差；添加少量含目标的结构可大幅降低误差，并缩小ALIGNN和CGCNN中独热、k热与连续输入间的差异；校准仅能解释部分恢复，冻结初始元素投影在6个ALIGNN拆分中的5个上保留了大部分增益，因此，目标支撑将化学迁移从依赖静态元素关系转向从含目标的环境中学习。
英文摘要
Materials graph neural networks must often transfer to chemical regions weakly represented in training data. Such transfer can rely on predefined relations among elements or supervised evidence from target-containing structures, but these pathways are usually entangled. Here, held-out-element splits and incremental target support separate their roles. Without target-containing training structures, formation-energy errors depend strongly on the element representation, particularly for H, O and F. Matched perturbations show that representation-induced sharing matters beyond input dimension or numerical form, while a label-free similarity-graph prior reduces selected zero-shot errors. Adding a few target-containing structures sharply lowers errors and contracts differences among one-hot, k-hot and continuous inputs across ALIGNN and CGCNN. Calibration explains only part of this recovery, and freezing the initial element projection preserves most gains in five of six ALIGNN splits. Target support therefore shifts chemical transfer from reliance on static element relations toward learning from target-containing environments.
发表机构
- King Abdullah University of Science and Technology (KAUST)（阿卜杜拉国王科技大学）
机构由 AI 辅助整理，请以论文原文为准。
