$Δ$-model correction of Foundation Model based on the models own understanding

Abstract: Foundation models of interatomic potentials, so called universal potentials, may require fine-tuning or residual corrections when applied to specific subclasses of materials. In the present work, we demonstrate how such augmentation can be accomplished via $\Delta$-learning based on the representation already embedded in the universal potentials. The $\Delta$-model introduced is a Gaussian Process Regression (GPR) model and various types of aggregation (global, species-separated, and atomic) of the representation vector are discussed. Employing a specific universal potential, CHGNet [Deng et al., Nat. Mach. Intell. 5, 1031 (2023)], in a global structure optimization setting, we find that it correctly describes the energetics of the "8" Cu oxide, which is an ultra-thin oxide film on Cu(111). The universal potential model even predicts a more favorable structure compared to that discussed in recent DFT-based literature. Moving to sulfur adatom overlayers on Cu(111), Ag(111), and Au(111) the CHGNet model, however, requires corrections. We demonstrate that these are efficiently provided via the GPR-based $\Delta$-model formulated on the CHGNet's own internal atomic embedding representation. The need for corrections is tracked to the scarcity of metal-sulfur atomic environments in the materials project database that CHGNet is trained on leading to an overreliance on sulfur-sulfur atomic environments. Other universal potentials trained on the same data, MACE-MP0, SevenNet-0, and ORB-v2-only-MPtrj show similar behavior, but with varying degrees of error, demonstrating the general need for augmentation schemes for universal potential models.