Loss-Guided Adaptive Scale Refinement for Molecular Force Prediction
2026-06-08 • Machine Learning
Machine Learning
AI summaryⓘ
The authors look at how molecules interact at different distances, from very close to far away. They point out that most current methods use fixed scales to predict molecular forces, but these fixed choices may not be the best for the task. Their approach adapts the scale automatically based on the prediction error, improving accuracy by mixing information from both short and long distances. Tests with saltwater molecules show this adaptive method reduces errors compared to fixed scales, especially when ions are very close. This suggests that adjusting the scale during learning can better capture molecular interactions.
molecular force predictionmulti-scale modelingadaptive scale refinementmean absolute error (MAE)ionic systemsshort-range interactionslong-range interactionsscale interpolationmachine learning in chemistryloss-guided optimization
Authors
Limin Yu
Abstract
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.