arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2606.09480cs.LG
收藏

损失引导的自适应尺度细化用于分子力预测

Loss-Guided Adaptive Scale Refinement for Molecular Force Prediction

Tianjin Medical University(天津医科大学)

Limin Yu

AI总结:

提出损失引导的自适应尺度细化框架,通过插值、路由和尺度池更新自动发现任务有效尺度,在NaCl水溶液体系中降低力预测误差。

摘要:

分子系统涉及多个空间尺度的相互作用,从局部配位和短程扰动到长程静电和溶剂介导效应。然而,大多数分子表示学习方法依赖于手动预定义的尺度,而任务最优建模尺度可能与这些固定水平不一致。本研究引入了一个损失引导的自适应尺度细化框架用于分子力预测,将预定义尺度视为初始锚点,通过插值、路由、可微尺度更新和尺度池细化来发现任务有效的分辨率。使用NaCl水溶液离子系统作为最小测试平台,构建了短尺度和长程力预测分支并分析了它们的互补性。Oracle硬路由将整体力MAE从399.65降低到382.67,而连续Oracle插值进一步将其降低到380.96。在最近离子距离低于0.6 nm的紧密接触区域,紧密接触MAE从327.22降低到260.51。一个最小尺度池更新实验表明,从端点锚点{0,1}开始,损失引导的更新自动生成中间尺度并恢复了大部分连续Oracle性能。最终更新的尺度池{0,0.125,0.25,0.375,0.5,0.75,1}实现了381.23的整体MAE。这些结果支持自适应尺度细化作为分子表示学习的一个有前景的方向,特别是当固定尺度建模不足时。

英文摘要:

Molecular systems involve interactions across multiple spatial scales, from local coordination and short-range perturbations to long-range electrostatic and solvent-mediated effects. However, most molecular representation learning methods rely on manually predefined scales, and the task-optimal modeling scale may not coincide with these fixed levels. This study introduces a loss-guided adaptive scale refinement framework for molecular force prediction, treating predefined scales as initial anchors and discovering task-effective resolutions through interpolation, routing, differentiable scale updates, and scale pool refinement. Using a NaCl aqueous ionic system as a minimal testbed, this study constructs short-scale and long-range force prediction branches and analyzes their complementarity. Oracle hard routing reduces the overall force MAE from 399.65 to 382.67, while continuous oracle interpolation further reduces it to 380.96. In close-contact regimes with nearest-ion distance below 0.6 nm, the close-contact MAE decreases from 327.22 to 260.51. A minimal scale pool update experiment shows that starting from endpoint anchors {0,1}, loss-guided updates automatically generate intermediate scales and recover most of the continuous oracle performance. The final updated scale pool {0,0.125,0.25,0.375,0.5,0.75,1} achieves an overall MAE of 381.23. These results support adaptive scale refinement as a promising direction for molecular representation learning, especially when fixed-scale modeling is insufficient.

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。

↑