Representing Born effective charges with equivariant graph convolutional neural networks

2024/09/13 by Alex Kutana, Kōji Shimizu, Kutana, Alex +5
Computer Science · #Disordered Systems and Neural Networks (cond-mat.dis-nn) #FOS: Physical sciences #Graph Theory and Algorithms #Materials Science (cond-mat.mtrl-sci)

paper · pdf · doi:10.48550/arxiv.2409.08940

openalex publication_date 2024/09/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Graph convolutional neural networks have been instrumental in machine learning of material properties. When representing tensorial properties, weights and descriptors of a physics-informed network must obey certain transformation rules to ensure the independence of the property on the choice of the reference frame. Here we explicitly encode such properties using an equivariant graph convolutional neural network. The network respects rotational symmetries of the crystal throughout by using equivariant weights and descriptors and provides a tensorial output of the target value. Applications to tensors of atomic Born effective charges in diverse materials including perovskite oxides, Li3PO4, and ZrO2, are demonstrated, and good performance and generalization ability is obtained.

Related

• Equivariant Graph Neural Networks for Prediction of Tensor Material Properties of Crystals
• Edge-based Tensor prediction via graph neural networks
• Point Group Equivariant Graph Neural Networks for Materials
• Equivariant Networks for Crystal Structures
• Constructing 3D Rotational Invariance and Equivariance with Symmetric Tensor Networks