Materials Informatics Transformer: A Language Model for Interpretable Materials Properties Prediction

• DOI: 10.48550/arxiv.2308.16259
• Publication Date: 2023-01-01
• Authors: Huang, Hongshuo; Magar, Rishikesh; Xu, Changwen; Farimani, Amir Ba...
• Keywords: Chemical Physics (physics.chem-ph); FOS: Computer and information sciences; Computer Science - Machine Learning; Condensed Matter - Materials Science; Physics - Chemical Physics; Materials Science (cond-mat.mtrl-sci); FOS: Physical sciences; Machine Learning (cs.LG)

Recently, the remarkable capabilities of large language models (LLMs) have been illustrated across a variety of research domains such as natural language processing, computer vision, and molecular modeling. We extend this paradigm by utilizing LLMs for material property prediction by introducing our model Materials Informatics Transformer (MatInFormer). Specifically, we introduce a novel approach that involves learning the grammar of crystallography through the tokenization of pertinent space group information. We further illustrate the adaptability of MatInFormer by incorporating task-specific data pertaining to Metal-Organic Frameworks (MOFs). Through attention visualization, we uncover the key features that the model prioritizes during property prediction. The effectiveness of our proposed model is empirically validated across 14 distinct datasets, hereby underscoring its potential for high throughput screening through accurate material property prediction.