Saved in:
Bibliographic Details
Main Authors: Novelli, Pietro, Meanti, Giacomo, Buigues, Pedro J., Rosasco, Lorenzo, Parrinello, Michele, Pontil, Massimiliano, Bonati, Luigi
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.05652
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Training machine learning interatomic potentials that are both computationally and data-efficient is a key challenge for enabling their routine use in atomistic simulations. To this effect, we introduce franken, a scalable and lightweight transfer learning framework that extracts atomic descriptors from pretrained graph neural networks and transfer them to new systems using random Fourier features-an efficient and scalable approximation of kernel methods. Franken enables fast and accurate adaptation of general-purpose potentials to new systems or levels of quantum mechanical theory without requiring hyperparameter tuning or architectural modifications. On a benchmark dataset of 27 transition metals, franken outperforms optimized kernel-based methods in both training time and accuracy, reducing model training from tens of hours to minutes on a single GPU. We further demonstrate the framework's strong data-efficiency by training stable and accurate potentials for bulk water and the Pt(111)/water interface using just tens of training structures. Our open-source implementation (https://franken.readthedocs.io) offers a fast and practical solution for training potentials and deploying them for molecular dynamics simulations across diverse systems.