Band-Gap Regression with Architecture-Optimized Message-Passing Neural Networks

Graph-based neural networks and, specifically, message-passing neural networks (MPNNs) have shown great potential in predicting physical properties of solids. In this work, we train an MPNN to first classify materials through density functional theory data from the AFLOW database as being metallic or semiconducting/insulating. We then perform a neural-architecture search to explore the model architecture and hyperparameter space of MPNNs to predict the band gaps of the materials identified as nonmetals. The top-performing models from the search are pooled into an ensemble that significantly outperforms the best single model. Uncertainty quantification is evaluated with Monte Carlo dropout and ensembling, with the ensemble method proving superior. The domain of applicability of the ensemble model is analyzed with respect to the crystal systems, the inclusion of a Hubbard parameter in the density-functional-theory calculations, and the atomic species building up the materials.