arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.09301cond-mat.mtrl-sciphysics.comp-ph
收藏

材料信息学中的迁移学习:通过极简但高信息量的多模态输入构建结构-性质关系

Transfer Learning in Materials Informatics: structure-property relationships through minimal but highly informative multimodal input

Dario Massa, Grzegorz Kaszuba, Stefanos Papanikolaou, Piotr Sankowski

AI总结:

本研究针对材料结构-性质关系预测,提出基于图像和文本架构的多模态迁移学习方法,验证预训练模型知识的跨域迁移性,为材料信息学领域低成本AI方法提供新思路。

摘要:

本研究针对材料领域的结构-性质关系预测问题,提出了简单、有效且计算高效的迁移学习方法,该方法可利用来自不同模态的高信息量输入。由于材料性质源于其电子结构,我们通过神经网络直接从电子电荷密度分布图图像数据集中提取表征。我们验证了现有预训练卷积神经网络(Convolutional Neural Networks, CNN)和大语言模型(Large Language Models, LLM)的知识向物理领域数据的可迁移性,探索了用于能量相关或结构相关性质回归的广泛组分集合,以及语义晶体学信息在多模态方法中的作用。我们测试了CLIP多模态模型的适用性,还采用了一种训练协议,用于从不同的预训练模态构建更具可解释性和通用性的堆叠式定制解决方案。该研究为提升物理系统中描述符识别的有效性提供了一条有前景的途径,揭示了多模态迁移学习在材料性质预测中的潜力。我们并未采用成熟的基于图神经网络(GNN)的方法,而是探索了基于图像和文本的架构的迁移学习,这可能会影响材料与化学信息学领域新型低成本AI方法的决策制定。

英文摘要:

In this work we propose simple, effective and computationally efficient transfer learning approaches for structure-property relation predictions in the context of materials, with highly informative input from different modalities. As materials properties stand from their electronic structure, representations are extracted directly from datasets of electronic charge density profile images using Neural Networks. We demonstrate transferability of the existing pre-trained Convolutional Neural Networks and Large Language Models knowledge to physics domain data, exploring a wide set of compositions for the regression of energetics- or structure- related properties, and the role of semantic crystallographic information in the context of multimodal approaches. We test the applicability of the CLIP multimodal model, and employ as well a training protocol for building a more interpretable and versatile stacked custom solution from different pre-trained modalities. The study offers a promising avenue for enhancing the effectiveness of descriptor identification in physical systems, shedding light on the power of multimodal transfer learning for materials property prediction. Instead of using the well-established GNN-based approaches, we explore the transfer learning of image- and text-based architectures, which can impact decision making for new low-cost AI methods in the field of Materials and Chemoinformatics.

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。

↑