提出新型原子间势能模型，显著提升分子动力学模拟精度与外推能力。
Edge Cluster Expansion with Radial Rotary Attention for Interatomic Potentials
- 基于旋转对称性设计复数等变交互模块，直接构建高阶相互作用
- 在Matbench上实现当前最优性能，外推能力超越现有注意力机制
- 适用于材料发现与分子动力学模拟，尤其适合复杂多体系统
本文系统研究了SO(2)理论在机器学习原子间势能（MLIPs）中的应用，揭示了传统SO(2)线性架构相对于SO(3) Clebsch-Gordan张量积的局限性。基于此，我们提出直接笛卡尔构造与递归Clebsch-Gordan构造Wigner D-矩阵的方法，并引入两种新型交互构建块。首先，提出基于广义非对称压缩的边复数乘积基（Edge Complex Product Basis），通过复数等变乘法在边上直接构建高阶相互作用。其次，引入径向旋转复数注意力（Radial Rotary Complex Attention, RRA），显著增强外推性能，优于现有注意力向量形式。同时改进原子簇展开模块。基于上述进展，在OMat24、sAlex和MPTrj数据集上训练模型，推出TECE-OAM-RRA-1.0，在Matbench Discovery任务中达到当前最优（SOTA）表现。
原文摘要 · Abstract (English)
In this paper, we provide a systematic investigation of SO(2) theory to machine learning interatomic potentials (MLIPs) and identify the limitations of conventional SO(2) Linear architectures relative to SO(3) Clebsch-Gordan Tensor Products (CGTP). Building on these insights, we propose direct Cartesian construction and recursive Clebsch-Gordan construction of Wigner D-matrices and introduce two novel interaction building blocks. First, we propose the Edge Complex Product Basis based on Generalized Asymmetric Contraction, a new formulation for many-body expansion that directly constructs higher-order interactions on edges through complex-valued equivariant multiplications. Second, we introduce Radial Rotary Complex Attention(RRA), which enhances extrapolation performance and surpasses existing attention vector formulations. We also introduce several improvements to the Atomic Cluster Expansion module. Building on these advances, we train our models on OMat24, sAlex, and MPTrj, and introduce TECE-OAM-RRA-1.0, which achieve state-of-the-art (SOTA) performance on the Matbench Discovery.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。