LightPFP: A Lightweight Route to Ab Initio Accuracy at Scale

TL;DR

LightPFP introduces a data-efficient distillation framework that creates accurate, lightweight machine learning interatomic potentials, enabling large-scale atomistic simulations with DFT-level accuracy at a fraction of the computational cost.

Contribution

The paper presents a novel knowledge distillation approach that leverages universal MLIPs to efficiently generate high-quality training data for task-specific MLIPs without extensive DFT calculations.

Findings

Achieves three orders of magnitude faster model development than DFT-based methods.

Maintains accuracy comparable to first-principles predictions across various materials.

Enables efficient correction of systematic errors with minimal high-accuracy data.

Abstract

Atomistic simulation methods have evolved through successive computational levels, each building upon more fundamental approaches: from quantum mechanics to density functional theory (DFT), and subsequently, to machine learning interatomic potentials (MLIPs). While universal MLIPs (u-MLIPs) offer broad transferability, their computational overhead limits large-scale applications. Task-specific MLIPs (ts-MLIPs) achieve superior efficiency but require prohibitively expensive DFT data generation for each material system. In this paper, we propose LightPFP, a data-efficient knowledge distillation framework. Instead of using costly DFT calculations, LightPFP generates a distilled ts-MLIP by leveraging u-MLIP to generate high-quality training data tailored for specific materials and utilizing a pre-trained light-weight MLIP to further enhance data efficiency. Across a broad spectrum of materials, including solid-state electrolytes, high-entropy alloys, and reactive ionic systems, LightPFP delivers three orders of magnitude faster model development than conventional DFT-based methods, while maintaining accuracy on par with first-principles predictions. Moreover, the distilled ts-MLIPs further sustain the computational efficiency essential for large-scale molecular dynamics, achieving 1-2 orders of magnitude faster inference than u-MLIPs. The framework further enables efficient precision transfer learning, where systematic errors from the u-MLIP can be corrected using as few as 10 high-accuracy DFT data points, as demonstrated for MgO melting point prediction. This u-MLIP-driven distillation approach enables rapid development of high-fidelity, efficient MLIPs for materials science applications.