Knowledge Distillation of Noisy Force Labels for Improved Coarse-Grained Force Fields
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918489491505152 |
|---|---|
| author | Olowookere, Feranmi V. Matin, Sakib Pachalieva, Aleksandra Lubbers, Nicholas Shinkle, Emily |
| author_facet | Olowookere, Feranmi V. Matin, Sakib Pachalieva, Aleksandra Lubbers, Nicholas Shinkle, Emily |
| contents | Molecular dynamics simulations are an integral tool for studying the atomistic behavior of materials under diverse conditions. However, they can be computationally demanding in wall-clock time, especially for large systems, which limits the time and length scales accessible. Coarse-grained (CG) models reduce computational expense by grouping atoms into simplified representations commonly called beads, but sacrifice atomic detail and introduce mapping noise, complicating the training of machine-learned surrogates. Moreover, because CG models inherently include entropic contributions, they cannot be fit directly to all-atom energies, leaving instantaneous, noisy forces as the only state-specific quantities available for training. Here, we apply a knowledge distillation framework by first training an initial CG neural network potential (the teacher) solely on AA-to-CG mapped forces to denoise those labels, then distill its force and energy predictions to train refined CG models (the student) in both single- and ensemble-training setups while exploring different force and energy target combinations. We validate this framework on a complex molecular fluid, a deep eutectic solvent, by evaluating two-, three-, and many-body properties and compare the CG and all-atom results. Our findings demonstrate that training a student model on ensemble teacher-predicted forces and per-bead energies improves the quality and stability of CG force fields. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_26650 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Knowledge Distillation of Noisy Force Labels for Improved Coarse-Grained Force Fields Olowookere, Feranmi V. Matin, Sakib Pachalieva, Aleksandra Lubbers, Nicholas Shinkle, Emily Chemical Physics Molecular dynamics simulations are an integral tool for studying the atomistic behavior of materials under diverse conditions. However, they can be computationally demanding in wall-clock time, especially for large systems, which limits the time and length scales accessible. Coarse-grained (CG) models reduce computational expense by grouping atoms into simplified representations commonly called beads, but sacrifice atomic detail and introduce mapping noise, complicating the training of machine-learned surrogates. Moreover, because CG models inherently include entropic contributions, they cannot be fit directly to all-atom energies, leaving instantaneous, noisy forces as the only state-specific quantities available for training. Here, we apply a knowledge distillation framework by first training an initial CG neural network potential (the teacher) solely on AA-to-CG mapped forces to denoise those labels, then distill its force and energy predictions to train refined CG models (the student) in both single- and ensemble-training setups while exploring different force and energy target combinations. We validate this framework on a complex molecular fluid, a deep eutectic solvent, by evaluating two-, three-, and many-body properties and compare the CG and all-atom results. Our findings demonstrate that training a student model on ensemble teacher-predicted forces and per-bead energies improves the quality and stability of CG force fields. |
| title | Knowledge Distillation of Noisy Force Labels for Improved Coarse-Grained Force Fields |
| topic | Chemical Physics |
| url | https://arxiv.org/abs/2510.26650 |