Cross-functional transferability in foundation machine learning interatomic potentials

Journal Article · Wed Jan 01 00:00:00 EST 2025 · npj Computational Materials

DOI:https://doi.org/10.1038/s41524-025-01796-y· OSTI ID:3014169

Huang, Xu; Deng, Bowen; Zhong, Peichen; Kaplan, Aaron D; Persson, Kristin A; Ceder, Gerbrand

The rapid development of foundation potentials (FPs) in machine learning interatomic potentials demonstrates the possibility for generalizable learning of the universal potential energy surface. The accuracy of FPs can be further improved by bridging the model from lower-fidelity datasets to high-fidelity ones. In this work, we analyze the challenge of this transfer learning (TL) problem within the CHGNet framework. We show that significant energy scale shifts and poor correlations between GGA and r2SCAN hinder cross-functional transferability. By benchmarking different TL approaches on the MP-r2SCAN dataset, we demonstrate the importance of elemental energy referencing in the TL of FPs. By comparing the scaling law with and without the pre-training on a low-fidelity dataset, we show that significant data efficiency can still be achieved through TL, even with a target dataset of sub-million structures. We highlight the importance of proper TL and multi-fidelity learning in creating next-generation FPs on high-fidelity data.

• Research Organization: Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
• Sponsoring Organization: US Department of Energy; USDOE Office of Science (SC), Basic Energy Sciences (BES) (SC-22), Materials Sciences & Engineering Division (SC-22.2)
• Grant/Contract Number: AC02-05CH11231
• OSTI ID: 3014169
• Journal Information: npj Computational Materials, Journal Name: npj Computational Materials Journal Issue: 1 Vol. 11
• Country of Publication: United States
• Language: English