Efficient Equivariant High-Order Crystal Tensor Prediction via Cartesian Local-Environment Many-Body Coupling
This work addresses a domain-specific problem in materials science by improving computational efficiency and accuracy for predicting crystal tensor properties, representing an incremental advance over existing methods.
The paper tackled the challenge of predicting high-order crystal tensor properties from atomic structures by proposing CEITNet, which uses Cartesian local environment tensors and channel-space interactions to achieve efficient and accurate predictions, surpassing prior methods on benchmark datasets for order-2, -3, and -4 tensors.
End-to-end prediction of high-order crystal tensor properties from atomic structures remains challenging: while spherical-harmonic equivariant models are expressive, their Clebsch-Gordan tensor products incur substantial compute and memory costs for higher-order targets. We propose the Cartesian Environment Interaction Tensor Network (CEITNet), an approach that constructs a multi-channel Cartesian local environment tensor for each atom and performs flexible many-body mixing via a learnable channel-space interaction. By performing learning in channel space and using Cartesian tensor bases to assemble equivariant outputs, CEITNet enables efficient construction of high-order tensor. Across benchmark datasets for order-2 dielectric, order-3 piezoelectric, and order-4 elastic tensor prediction, CEITNet surpasses prior high-order prediction methods on key accuracy criteria while offering high computational efficiency.