基于专家混合的机器学习原子势扩展
Mixture of experts architectures for machine learning interatomic potentials
AI总结：
本文提出基于专家混合的MLIPs架构，通过非线性专家专业化提升模型性能，实现元素级路由的高效稳定模拟，并在多个基准测试中取得最佳精度。
摘要：
机器学习原子势（MLIPs）能够实现准确的大规模原子模拟，但高效提升其表达能力仍具挑战性。本文系统开发了用于MLIPs的专家混合（MoE）和线性专家混合（MoLE）架构，并分析了路由策略和专家设计的影响。研究表明，稀疏激活结合共享专家可带来显著性能提升，且非线性MoE架构在存在共享专家时优于MoLE，凸显了非线性专家专业化的重要性。此外，元素级路由一致优于配置级路由，而全局MoE路由常导致数值不稳定。所得到的元素级MoE模型在OMol25、OMat24和OC20M基准测试中均达到最先进水平。路由模式分析揭示了与元素周期表趋势一致的化学可解释性专家专业化，表明模型能有效捕捉元素特定的化学特性以实现精确的原子间建模。
英文摘要：
Machine Learning Interatomic Potentials (MLIPs) enable accurate large-scale atomistic simulations, yet improving their expressive capacity efficiently remains challenging. Here we systematically investigate Mixture-of-Experts (MoE) and Mixture-of-Linear-Experts (MoLE) architectures within the DPA3 framework for MLIPs and analyze the effects of routing strategies and expert designs. We show that sparse activation combined with shared experts yields substantial performance gains, and that nonlinear MoE formulations outperform MoLE when shared experts are present, underscoring the importance of nonlinear expert specialization. Furthermore, element-wise routing consistently surpasses configuration-level routing, while global MoE routing often leads to numerical instability. The resulting element-wise MoE model consistently outperforms all DPA3-based baselines across the OMol25, OMat24, and OC20M benchmarks. Analysis of routing patterns reveals chemically interpretable expert specialization aligned with periodic-table trends, indicating that the model effectively captures element-specific chemical characteristics for precise interatomic modeling.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
