Optimizing Cross-Domain Transfer for Universal Machine Learning Interatomic Potentials

TL;DR

This paper presents a novel training strategy for machine-learning interatomic potentials that significantly improves their transferability across diverse chemical and functional domains, enabling more reliable and universal applications.

Contribution

It introduces a multi-domain training approach with selective regularization and a domain-bridging set, achieving state-of-the-art cross-domain accuracy in MLIPs.

Findings

Achieves adsorption-energy errors below 0.06 eV on metallic surfaces.

Reproduces high-fidelity r$^2$SCAN energetics with only 0.5% of r$^2$SCAN data.

Enhances out-of-distribution generalization while maintaining in-domain fidelity.

Abstract

Accurate yet transferable machine-learning interatomic potentials (MLIPs) are essential for accelerating materials and chemical discovery. However, most universal MLIPs overfit to narrow datasets or computational protocols, limiting their reliability across chemical and functional domains. We introduce a transferable multi-domain training strategy that jointly optimizes universal and task-specific parameters through selective regularization, coupled with a domain-bridging set (DBS) that aligns potential-energy surfaces across datasets. Systematic ablation experiments show that small DBS fractions (0.1%) and targeted regularization synergistically enhance out-of-distribution generalization while preserving in-domain fidelity. Trained on fifteen open databases spanning molecules, crystals, and surfaces, our model, SevenNet-Omni, achieves state-of-the-art cross-domain accuracy, including adsorption-energy errors below 0.06 eV on metallic surfaces and 0.1 eV on metal-organic frameworks. Despite containing only 0.5% r$^2$SCAN data, SevenNet-Omni reproduces high-fidelity r$^2$SCAN energetics, demonstrating effective cross-functional transfer from large PBE datasets. This framework offers a scalable route toward universal, transferable MLIPs that bridge quantum-mechanical fidelities and chemical domains.