Lattice Lingo:文本细节对晶体性质预测多模态学习的影响
Lattice Lingo: Effect of Textual Detail on Multimodal Learning for Property Prediction of Crystals
AI总结:
本文通过拼接图表示与 Robocrystallographer 生成的不同细节文本,评估全局、局部和半全局信息对晶体剪切模量与体积模量预测的影响,发现半全局文本提升最大。
摘要:
大多数晶体性质预测模型采用单模态视角,使用基于图的表示,忽略了影响晶体性质的重要非局部信息。近期一些研究探索了整合图与文本信息对晶体性质预测的影响,通过嵌入拼接为模型提供这种“缺失”信息。然而,这些研究并未评估哪类文本信息真正有益。我们将图表示与来自不同细节程度文本描述的文本表示进行拼接。这些描述使用 Robocrystallographer 包生成,包含结构的全局信息(如空间群、晶体类型)、局部信息(如键长、配位环境)和半全局信息(如连接性、排列方式)。我们的方法考察了以不同细节程度的文本信息增强基于图的信息,如何影响剪切模量和体积模量的预测性能。我们证明,尽管图表示能够捕捉局部结构信息,但纳入半全局文本信息对模型性能的提升最大。在存在半全局信息时,全局信息可进一步支持性能。我们的发现表明,策略性地纳入文本信息可以增强性质预测,从而推进电池电极、催化剂等先进新型材料的设计与发现。
英文摘要:
Most prediction models for crystal properties employ a unimodal perspective, with graph-based representations, overlooking important non-local information that affects crystal properties. Some recent studies explore the impact of integrating graph and textual information on crystal property predictions to provide the model with this "missing" information by concatenation of embeddings. However, such studies do not evaluate which type of textual information is actually beneficial. We concatenate graph representations with text representations derived from textual descriptions with varying levels of detail. These descriptions, generated using the Robocrystallographer package, encompass global (e.g., space group, crystal type), local (e.g., bond lengths, coordination environment), and semiglobal (e.g., connectivity, arrangements) information about the structures. Our approach investigates how augmenting graph-based information with various levels of textual detail influences the performance for predictions for shear modulus and bulk modulus. We demonstrate that while graph representations can capture local structural information, incorporating semiglobal textual information enhances model performance the most. Global information can support performance further in the presence of semiglobal information. Our findings suggest that the strategic inclusion of textual information can enhance property prediction, thereby advancing the design and discovery of advanced novel materials for battery electrodes, catalysts, etc.
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。