Band-gap regression with architecture-optimized message-passing neural networks
This work addresses the challenge of accurately predicting band gaps for materials science applications, representing an incremental improvement through architecture optimization and ensembling.
The authors tackled the problem of predicting material band gaps by first classifying materials as metallic or non-metallic using an MPNN trained on DFT data, then performing a neural-architecture search to optimize MPNNs for band-gap regression, resulting in an ensemble model that significantly outperforms existing models.
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 non-metals. The parameters in the search include the number of message-passing steps, latent size, and activation-function, among others. The top-performing models from the search are pooled into an ensemble that significantly outperforms existing models from the literature. 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 calculations, and the atomic species building up the materials.