Related papers: Band-gap regression with architecture-optimized message-passing neural networks

Band-gap regression with architecture-optimized message-passing neural networks

URL: http://arxiv.org/abs/2309.06348v1
Date: Tue, 12 Sep 2023 16:13:10 GMT
Title: Band-gap regression with architecture-optimized message-passing neural networks
Authors: Tim Bechtel, Daniel T. Speckhard, Jonathan Godwin, Claudia Draxl
Abstract summary: 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 hyper parameter space of MPNNs to predict the band gaps of the materials identified as non-metals. The top-performing models from the search are pooled into an ensemble that significantly outperforms existing models from the literature.
Score: 1.9590152885845324
License: http://creativecommons.org/licenses/by-nc-sa/4.0/
Abstract: 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.