发表机构
Kumamoto University; University of Southern California（熊本大学; 南加州大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出E3D-IQA诊断框架，连接Allegro型MLIP的潜在边能量表示与IQA能量分解，发现原子内监督对恢复IQA类能量分配的关键作用，为诊断和指导潜在科学表示提供了途径。
AI 中文摘要
机器学习原子间势（MLIP）可准确再现势能和力，但其内部能量分配往往难以解释。本文引入E3D-IQA作为诊断框架，将Allegro型MLIP的潜在边能量表示与相互作用量子原子（IQA）能量分解相连接。Allegro的边能量路径保留为潜在对贡献，而节点能量路径则针对IQA原子内能量进行训练。IQA原子间能量并非直接训练目标，而是在训练后针对IQA对项评估学习到的边能量。对H/C/N/O有机反应结构的测试表明，原子内监督至关重要：仅进行能量和力训练无法恢复类似IQA的单体/双体分配。在原子内监督下，节点能量可再现IQA原子内项，且潜在边能量与IQA原子间项存在有意义的对应关系。残差误差集中在正或弱对相互作用中，暴露出在总能量和力指标中隐藏的内部分配缺陷。添加仅标记有能量和力的结构可提升对更大分子的迁移性并减少分解误差。因此，E3D-IQA提供了一条利用部分标记的量子化学数据集诊断和指导潜在科学表示的途径。
英文摘要
Machine-learning interatomic potentials (MLIPs) can reproduce potential energies and forces accurately, but their internal energy allocation is often difficult to interpret. E3D-IQA is introduced as a diagnostic framework connecting the latent edge-energy representation of an Allegro-type MLIP with Interacting Quantum Atoms (IQA) energy decomposition. The Allegro edge-energy path is retained as a latent pair contribution, while a node-energy path is trained against the IQA intra-atomic energy. IQA interatomic energies are not direct training targets; instead, the learned edge energies are evaluated after training against the IQA pair terms. Tests on H/C/N/O organic reaction structures show that intra-atomic supervision is essential: energy and force training alone does not recover an IQA-like one-body/two-body allocation. With intra-atomic supervision, node energies reproduce IQA intra-atomic terms, and latent edge energies show meaningful correspondence with IQA interatomic terms. Residual errors are concentrated in positive or weak pair interactions, exposing internal allocation failures that remain hidden in total-energy and force metrics. Adding structures labeled only with energies and forces improves transfer to larger molecules and reduces decomposition errors. E3D-IQA therefore provides a route for diagnosing and guiding latent scientific representations using partially labeled quantum-chemical datasets.
