Pith. sign in

REVIEW 2 cited by

Knowledge Distillation Framework for Accelerating High-Accuracy Neural Network-Based Molecular Dynamics Simulations

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.15337 v2 pith:GBEK6UEA submitted 2025-06-18 cs.LG cond-mat.mtrl-sciphysics.comp-ph

classification cs.LGcond-mat.mtrl-sciphysics.comp-ph
keywords simulationsstructuresframeworkteachertrainingcompareddatahigh-energy
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Neural network potentials (NNPs) offer a powerful alternative to traditional force fields for molecular dynamics (MD) simulations. Accurate and stable MD simulations, crucial for evaluating material properties, require training data encompassing both low-energy stable structures and high-energy structures. Conventional knowledge distillation (KD) methods fine-tune a pre-trained NNP as a teacher model to generate training data for a student model. However, in material-specific models, this fine-tuning process increases energy barriers, making it difficult to create training data containing high-energy structures. To address this, we propose a novel KD framework that leverages a non-fine-tuned, off-the-shelf pre-trained NNP as a teacher. Its gentler energy landscape facilitates the exploration of a wider range of structures, including the high-energy structures crucial for stable MD simulations. Our framework employs a two-stage training process: first, the student NNP is trained with a dataset generated by the off-the-shelf teacher; then, it is fine-tuned with a smaller, high-accuracy density functional theory (DFT) dataset. We demonstrate the effectiveness of our framework by applying it to both organic (polyethylene glycol) and inorganic (L$_{10}$GeP$_{2}$S$_{12}$) materials, achieving comparable or superior accuracy in reproducing physical properties compared to existing methods. Importantly, our method reduces the number of expensive DFT calculations by 10x compared to existing NNP generation methods, without sacrificing accuracy. Furthermore, the resulting student NNP achieves up to 106x speedup in inference compared to the teacher NNP, enabling significantly faster and more efficient MD simulations.

Discussion (0). Sign in to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Lang2MLIP: End-to-End Language-to-Machine Learning Interatomic Potential Development with Autonomous Agentic Workflows

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    Lang2MLIP is an LLM multi-agent framework that automates end-to-end development of machine learning interatomic potentials from natural language input for heterogeneous materials systems.

  2. Distilling first-principles accuracy into compact machine learning potentials for condensed-phase chemistry

    physics.chem-ph 2026-06 unverdicted novelty 6.0 of 10

    Distilled compact MLIPs from transfer-learned teachers reproduce observables more reliably than same-size models trained directly and enable practical PIMD umbrella sampling of water dissociation at TiO2 interface wit...

Pith tools