Answers are grounded in this paper and cite their sources.
Atomistic foundation models achieve high accuracy by training on very large labeled datasets. However, it remains unclear how much of this data is actually needed. Data-efficient training requires a better understanding of the roles of both data selection and model optimization. Here, we study these two factors separately using MACE-OFF24 as a baseline. We build smaller training sets by selecting configurations to cover diverse local atomic environments and include cases with large teacher-model errors. We then compare AdamW with the matrix-aware Muon optimizer using the same training data. We selected approximately 21% of the available configurations (190,000 for training and 10,000 for validation). Training from scratch produced energy and force root-mean-square errors within 8.1% and 6% of those obtained with the published checkpoint. On the fixed 200k subset, Muon reduced mean energy and force errors by 29% and 6% relative to AdamW. In a single-run comparison of selection rules within a fixed candidate pool at 49k, the 80:20 representative/residual allocation gave the lowest observed energy and force errors. On a separate small test set of approximately 7,000 3BPA conformers, AdamW instead gave the lowest mean relative-energy and energy-span errors. Our results show that data-efficient training of atomistic foundation models is jointly controlled by configuration coverage, optimizer geometry, chemical regime, and target observable. Especially, for training on big datasets, matrix-aware updates can improve broad from-scratch energy-force training.
No takes yet. Share an insight, caveat, or question.
Liu et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: