English

An Efficient High-Degree, High-Order Equivariant Graph Neural Network for Direct Crystal Structure Optimization

Materials Science 2026-03-26 v1

Abstract

Crystal structure optimization is fundamental to materials modeling but remains computationally expensive when performed with density-functional theory (DFT). Machine-learning (ML) approaches offer substantial acceleration, yet existing methods face three key limitations: (i) most models operate solely on atoms and treat lattice vectors implicitly, despite their central role in structural optimization; (ii) they lack efficient mechanisms to capture high-degree angular information and higher-order geometric correlations simultaneously, which are essential for distinguishing subtle structural differences; and (iii) many pipelines are multi-stage or iterative rather than truly end-to-end, making them prone to error accumulation and limiting scalability. Here we present E3^{3}Relax-H2^{2}, an end-to-end high-degree, high-order equivariant graph neural network that maps an initial crystal directly to its relaxed structure. The key idea is to promote both atoms and lattice vectors to graph nodes, enabling a unified and symmetry-consistent representation of structural degrees of freedom. Building on this formulation, E3^{3}Relax-H2^{2} introduces two message-passing mechanisms: (i) a high-degree, high-order message-passing module that efficiently captures high-degree angular representations and high-order many-body correlations; and (ii) a lattice-atom message-passing module that explicitly models the bidirectional coupling between lattice deformation and atomic displacement. In addition, we propose a differentiable periodicity-aware Cartesian displacement loss tailored for one-shot structure prediction under periodic boundary conditions.

Keywords

Cite

@article{arxiv.2603.23941,
  title  = {An Efficient High-Degree, High-Order Equivariant Graph Neural Network for Direct Crystal Structure Optimization},
  author = {Ziduo Yang and Wei Zhuo and Huiqiang Xie and Xiaoqing Liu and Lei Shen},
  journal= {arXiv preprint arXiv:2603.23941},
  year   = {2026}
}
R2 v1 2026-07-01T11:36:43.598Z