Search papers, labs, and topics across Lattice.
This paper introduces an active-learning workflow utilizing last-layer-projection regression (LLPR) to efficiently construct diverse training sets for machine-learning force fields (MLFFs). By leveraging LLPR as a cheap uncertainty estimator, the authors demonstrate that it can identify compact, high-value training sets that achieve full-data accuracy with significantly fewer electronic-structure labels across various systems. The results show that LLPR not only enhances the efficiency of foundation-model fine-tuning but also improves the detection of unphysical configurations in iterative training processes.
LLPR can achieve full-data accuracy with a fraction of the labels, revolutionizing how we approach training machine-learning force fields.
Machine-learning force fields (MLFFs) are reliable only near their training distribution, making efficient construction of diverse training sets a major bottleneck for both train-from-scratch and foundation fine-tuning workflows. Active learning can reduce this cost, but standard model-committee uncertainty is impractical for foundation MLFFs because each committee member requires a separate fine-tuning run. We present an active-learning workflow based on last-layer-projection regression (LLPR), a forward-pass-cheap per-configuration uncertainty estimator. Across molecular, condensed-phase, and electrolyte systems, LLPR identifies compact, high-value training sets that recover full-data accuracy using only a small fraction of electronic-structure labels. In foundation-model fine-tuning, LLPR-selected configurations reach the full-pool fine-tuning ceiling with substantially fewer labels than random selection. In iterative electrolyte fine-tuning, LLPR detects unphysical local coordination before DFT labelling, provides an absolute force-error threshold, and enables automatic termination of the learning loop. The resulting models reproduce reference density and ion-coordination structure, providing a scalable uncertainty-quantification strategy across MLFF training regimes.
