A Lightweight Universal Machine-Learning Interatomic Potential via Knowledge Distillation for Scalable Atomistic Simulations

TL;DR

This paper presents SevenNet-Nano, a lightweight, accurate, and transferable machine-learning interatomic potential derived via knowledge distillation from a large foundation model, enabling scalable atomistic simulations.

Contribution

The authors develop a compact, universal ML interatomic potential using knowledge distillation from a large foundation model, achieving high accuracy and efficiency.

Findings

SevenNet-Nano achieves over an order-of-magnitude speedup.

It accurately models diverse interatomic interactions.

Demonstrates broad applicability across different materials and conditions.

Abstract

We introduce a lightweight universal machine-learning interatomic potential (uMLIP), SevenNet-Nano, based on the graph neural network architecture SevenNet and enabled by a knowledge-distillation framework. The model inherits the broad generalization capability of a large multi-task foundation model, SevenNet-Omni, trained on diverse materials datasets across chemical, configurational, and computational spaces. By learning chemical representations from high-quality inference data generated by the teacher model within a unified computational framework, SevenNet-Nano achieves high accuracy and strong transferability despite its compact architecture. The model also accurately captures a wide range of interatomic interactions, enabling reliable simulations under both equilibrium and extreme conditions, including plasma etching of SiO$_2$. Comprehensive benchmarks on static and dynamical properties--such as Li-ion diffusion and liquid densities--demonstrate its broad applicability with minimal fine-tuning. Importantly, SevenNet-Nano significantly reduces computational cost, achieving over an order-of-magnitude speedup and enabling large-scale atomistic simulations involving thousands of atoms.