REVIEW 6 cited by
Overcoming systematic softening in universal machine learning interatomic potentials by fine-tuning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Machine learning interatomic potentials (MLIPs) have introduced a new paradigm for atomic simulations. Recent advancements have seen the emergence of universal MLIPs (uMLIPs) that are pre-trained on diverse materials datasets, providing opportunities for both ready-to-use universal force fields and robust foundations for downstream machine learning refinements. However, their performance in extrapolating to out-of-distribution complex atomic environments remains unclear. In this study, we highlight a consistent potential energy surface (PES) softening effect in three uMLIPs: M3GNet, CHGNet, and MACE-MP-0, which is characterized by energy and force under-prediction in a series of atomic-modeling benchmarks including surfaces, defects, solid-solution energetics, phonon vibration modes, ion migration barriers, and general high-energy states. We find that the PES softening behavior originates from a systematic underprediction error of the PES curvature, which derives from the biased sampling of near-equilibrium atomic arrangements in uMLIP pre-training datasets. We demonstrate that the PES softening issue can be effectively rectified by fine-tuning with a single additional data point. Our findings suggest that a considerable fraction of uMLIP errors are highly systematic, and can therefore be efficiently corrected. This result rationalizes the data-efficient fine-tuning performance boost commonly observed with foundational MLIPs. We argue for the importance of a comprehensive materials dataset with improved PES sampling for next-generation foundational MLIPs.
Forward citations
Cited by 6 Pith papers
-
Phase Stability and Transformations in Lead Mixed Halide Perovskites from Machine Learning Force Fields
Machine-learned force fields predict that methylammonium suppresses the beta-to-gamma transition in mixed lead-halide perovskites unless the organic cations rearrange, while formamidinium stabilizes a cubic low-temper...
-
Fast and Fourier Features for Transfer Learning of Interatomic Potentials
Using random Fourier features on top of frozen graph neural network descriptors gives a fast and data-efficient way to adapt pretrained interatomic potentials to new systems.
-
Data-driven atomistic modelling of hybrid halide perovskite passivation
A continual fine-tuning protocol for machine-learned interatomic potentials enables large-scale simulation of amino-silane passivation at hybrid perovskite surfaces, revealing coverage-dependent lattice disruption.
-
Egret-1: Pretrained Neural Network Potentials for Efficient and Accurate Bioorganic Simulation
Egret-1, a MACE-based neural network potential trained on public organic-chemistry datasets, reaches small-basis DFT-level accuracy on several zero-shot benchmarks and reveals dataset diversity tradeoffs that hurt gra...
-
AutoPot: Automated and massively parallelized construction of Machine-Learning Potentials
AutoPot automates active-learning construction of moment tensor potentials, demonstrated on W and Mo-Ta, but its on-the-fly abort logic is unreachable and the claimed 'couple of hours' runtime is never measured.
-
A Study on the Fine-Tuning Performance of Universal Machine-Learned Interatomic Potentials (U-MLIPs)
Fine-tuning universal MACE potentials on targeted datasets generally improves accuracy and convergence speed, though data selection, not the foundation model alone, determines success.
Discussion (0). Continue with ORCID to comment.