Fine-Tuning Universal Machine-Learned Interatomic Potentials: A Tutorial on Methods and Applications

Abstract: Universal machine-learned interatomic potentials (U-MLIPs) have demonstrated broad applicability across diverse atomistic systems but often require fine-tuning to achieve task-specific accuracy. While the number of available U-MLIPs and their fine-tuning applications is rapidly expanding, there remains a lack of systematic guidance on how to effectively fine-tune these models. This tutorial provides a comprehensive, step-by-step guide to fine-tuning U-MLIPs for computational materials modeling. Using the recently released MACE-MP-0 as a representative example, we cover key aspects of the fine-tuning process, including dataset preparation, hyperparameter selection, model training, and validation. The effectiveness of fine-tuning is demonstrated through case studies involving force prediction in solid-state electrolytes, stacking fault defects in metals, and solid--liquid interfacial interactions in low-dimensional systems. To support practical applications, we include code examples that enable researchers, particularly those new to the field, to efficiently incorporate fine-tuned U-MLIPs into their workflows.