改进原子势模型，兼顾精度与速度，量子混合架构表现更优。
Multi-objective optimization and quantum hybridization of equivariant deep learning interatomic potentials
- 用多目标优化平衡预测精度与推理速度
- 量子-经典混合架构在铜锂体系上精度提升13%
- 无需重新调参即可在多个数据集保持竞争力
Allegro 是一种基于 E(3) 等变神经网络的机器学习原子势模型，用于预测分子中原子性质。训练时常面临精度与推理时间的权衡。为此，本文采用多目标超参数优化同时优化两项指标。此外，构建了两种 Allegro 变体：一种增加经典层，另一种引入量子-经典混合层。在 QM9、rMD17-aspirin、rMD17-benzene 和自生成的铜锂结构数据集上进行评估。结果表明，两种变体在多个数据集上的力预测精度均优于原始 Allegro。经典变体始终优于基线；量子-经典混合变体在铜锂数据集（完全优化）上表现最佳，较经典变体提升约13%。值得注意的是，该混合变体在其他数据集上也取得良好结果，且未进行特定数据集调参，仅使用铜锂优化的超参数，表明量子-经典混合是提升机器学习势能架构的有前景方向。
原文摘要 · Abstract (English)
Allegro is a machine learning interatomic potential model designed to predict atomic properties in molecules using E(3) equivariant neural networks. When training this model, there tends to be a trade-off between accuracy and inference time. For this reason, we apply multi-objective hyperparameter optimization to both objectives. Additionally, we experiment with modified architectures by constructing variants of Allegro: one extended with additional classical layers and one incorporating quantum-classical hybrid layers. We evaluate all models on QM9, rMD17-aspirin, rMD17-benzene, and a self-generated dataset of copper-lithium structures. As results, both variants surpass Allegro in force prediction accuracy across multiple datasets. The classical variant consistently improves over the baseline, while the quantum-classical hybrid variant achieves the best overall force prediction accuracy on the Cu-Li dataset, where it was fully optimized, outperforming the classical variant by approximately 13%. Notably, the hybrid variant also achieves competitive results on the remaining datasets despite using hyperparameters transferred from Cu-Li without dataset-specific optimization, suggesting that quantum-classical hybridization is a promising direction for enhancing MLIP architectures.
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。