Graph atomic cluster expansion for foundational machine learning interatomic potentials

TL;DR

This paper introduces the GRACE framework for universal, accurate, and efficient machine learning interatomic potentials, demonstrating superior performance and versatility across diverse materials datasets.

Contribution

The paper presents the novel GRACE framework, establishing a new accuracy-efficiency Pareto front and showing its adaptability through fine-tuning and knowledge distillation.

Findings

GRACE models set a new accuracy-efficiency benchmark.

Models can be adapted to specific tasks with minimal loss of performance.

Achieves high-fidelity simulations across the periodic table.

Abstract

Foundational machine learning interatomic potentials that can accurately and efficiently model a vast range of materials are critical for accelerating atomistic discovery. We introduce universal potentials based on the graph atomic cluster expansion (GRACE) framework, trained on several of the largest available materials datasets. Through comprehensive benchmarks, we demonstrate that the GRACE models establish a new Pareto front for accuracy versus efficiency among foundational interatomic potentials. We further showcase their exceptional versatility by adapting them to specialized tasks and simpler architectures via fine-tuning and knowledge distillation, achieving high accuracy while preventing catastrophic forgetting. This work establishes GRACE as a robust and adaptable foundation for the next generation of atomistic modeling, enabling high-fidelity simulations across the periodic table.