Crystal Fractional Graph Neural Network for Energy Prediction of High-Entropy Alloys

TL;DR

This paper introduces a novel graph neural network model that combines local atomic interactions and global compositional data to accurately predict the energy of high-entropy alloys, demonstrating comparable accuracy to first-principles methods.

Contribution

The proposed crystal fractional graph neural network explicitly integrates local and global features for improved energy prediction in high-entropy alloys, a novel approach in this domain.

Findings

Achieves RMSE comparable to first-principles calculations

Maintains high accuracy for low-energy configurations

Limited performance on large crystal cells

Abstract

High-entropy alloys (HEAs) have attracted growing attention for their exceptional mechanical and thermal properties arising from complex atomic configurations. In this paper, we propose crystal fractional graph neural network for predicting the energy of high-entropy alloys by explicitly integrating both local atomic environments and global compositional information. The model consists of three components: a crystal graph neural network, which employs graph attention network layers to learn local interactions among 16 on-site atoms within the crystal lattice; fractional neural network, a fully connected network that embeds the global fraction of constituent elements; and feature fusion neural network, which fuses the outputs of the two submodels to predict the total crystal energy. We train the model on a dataset of 1,049 crystal structures and validate it on 198 quaternary structures, optimizing all hyperparameters via Optuna. Our results show that our model achieves an RMSE comparable to first-principles calculations and maintains high accuracy even for low-energy configurations. However, the model exhibits limitations in handling large crystal cells, which we aim to address in future work to extend its applicability to more complex systems.