PFT: Phonon Fine-tuning for Machine Learned Interatomic Potentials

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Koker, Teddy, Gangan, Abhijeet, Kotak, Mit, Marian, Jaime, Smidt, Tess
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913175403757568
author Koker, Teddy
Gangan, Abhijeet
Kotak, Mit
Marian, Jaime
Smidt, Tess
author_facet Koker, Teddy
Gangan, Abhijeet
Kotak, Mit
Marian, Jaime
Smidt, Tess
contents Many materials properties depend on higher-order derivatives of the potential energy surface, yet machine learned interatomic potentials (MLIPs) trained with a standard loss on energy, force, and stress errors can exhibit error in curvature, degrading the prediction of vibrational properties. We introduce phonon fine-tuning (PFT), which directly supervises second-order force constants of materials by matching MLIP energy Hessians to DFT-computed force constants from finite displacement phonon calculations. To scale to large supercells, PFT stochastically samples Hessian columns and computes the loss with a single Hessian-vector product. We also use a simple co-training scheme to incorporate upstream data to mitigate catastrophic forgetting. On the MDR Phonon benchmark, PFT improves Nequix MP by 55% on average across phonon thermodynamic properties and achieves state-of-the-art accuracy among models trained on Materials Project trajectories. PFT also generalizes to improve properties beyond second-derivatives, improving thermal conductivity predictions that rely on third-order derivatives of the potential energy.
format Preprint
id arxiv_https___arxiv_org_abs_2601_07742
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PFT: Phonon Fine-tuning for Machine Learned Interatomic Potentials
Koker, Teddy
Gangan, Abhijeet
Kotak, Mit
Marian, Jaime
Smidt, Tess
Materials Science
Machine Learning
Many materials properties depend on higher-order derivatives of the potential energy surface, yet machine learned interatomic potentials (MLIPs) trained with a standard loss on energy, force, and stress errors can exhibit error in curvature, degrading the prediction of vibrational properties. We introduce phonon fine-tuning (PFT), which directly supervises second-order force constants of materials by matching MLIP energy Hessians to DFT-computed force constants from finite displacement phonon calculations. To scale to large supercells, PFT stochastically samples Hessian columns and computes the loss with a single Hessian-vector product. We also use a simple co-training scheme to incorporate upstream data to mitigate catastrophic forgetting. On the MDR Phonon benchmark, PFT improves Nequix MP by 55% on average across phonon thermodynamic properties and achieves state-of-the-art accuracy among models trained on Materials Project trajectories. PFT also generalizes to improve properties beyond second-derivatives, improving thermal conductivity predictions that rely on third-order derivatives of the potential energy.
title PFT: Phonon Fine-tuning for Machine Learned Interatomic Potentials
topic Materials Science
Machine Learning
url https://arxiv.org/abs/2601.07742