摘要
Moderngenerative modelsbasedondeep learning havemadeit possible to design millions of hypothetical materials.To screen these candidate materials and identify promising new materials,we need fast and accuratemodels to predictmaterial properties.Graphical neural networks(GNNs)have become a current research focusdue to their ability todirectly act on the graphical representationofmolecules andmaterials,enabling comprehensive capture of important information and showing excellent performance in predicting material properties.Nevertheless,GNNsstill face several key problems in practical applications:First,although existing nested graph network strategies increase critical structural information such as bond angles,they significantly increase the number of trainable parameters in the model,resulting in a increase in training costs;Second,extending GNN models to broader domains such as molecules,crystallinematerials,and catalysis,aswell as adapting to small data sets,remains a challenge.
基金
Weare grateful for the financial support fromthe National Key Research and Development Program of China(Grant Nos.2021YFB3702104).
