Cross Learning between Electronic Structure Theories for Unifying Molecular, Surface, and Inorganic Crystal Foundation Force Fields

TL;DR

This paper presents a novel machine learning framework that unifies molecular, surface, and inorganic crystal chemistry force fields, achieving high accuracy and transferability across diverse chemical domains.

Contribution

It introduces enhancements to the MACE architecture and a multi-head replay training protocol for cross-domain knowledge transfer in interatomic potentials.

Findings

Achieves state-of-the-art performance across multiple chemical domains.

Demonstrates superior cross-domain transferability compared to existing models.

Maintains high accuracy in materials-property predictions.

Abstract

Creating a single unified interatomic potential capable of attaining ab initio accuracy across all chemistry remains a long-standing challenge in computational chemistry and materials science. This work introduces a training protocol for foundation machine-learning interatomic potentials (MLIPs) that bridge molecular, surface, and materials chemistry through cross-domain learning. First, we introduce enhancements to the MACE architecture that improve its performance on chemically diverse databases by increasing weight sharing across chemical elements and introducing non-linear factors into the tensor decomposition of the product basis. Second, we develop a multi-head replay post-training methodology that enables efficient knowledge transfer across diverse chemical domains. By fine-tuning on datasets at different levels of electronic structure theory, including inorganic crystals, molecular systems, surface chemistry, and reactive organic chemistry, we demonstrate that a single unified model achieves state-of-the-art performance across several chemical domains. Comprehensive benchmarking reveals superior cross-domain transferability compared with existing specialised and multi-task models, with notable improvements in molecular and surface properties while maintaining state-of-the-art performance in materials-property prediction.