The reviewed record of science sign in
Pith

arxiv: 2405.07105 · v1 · pith:6GOSTSQL · submitted 2024-05-11 · cond-mat.mtrl-sci · cs.AI· cs.LG

Overcoming systematic softening in universal machine learning interatomic potentials by fine-tuning

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:6GOSTSQLrecord.jsonopen to challenge →

classification cond-mat.mtrl-sci cs.AIcs.LG
keywords mlipssofteningatomicfine-tuninglearningmachinesystematicuniversal
0
0 comments X
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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Synthesizability, hardness, and stacking order in multicomponent transition metal carbides from machine-learned potentials

    cond-mat.mtrl-sci 2026-05 unverdicted novelty 7.0

    Fine-tuned MACE potentials screen 1500 equiatomic multicomponent carbides, showing group number controls stability/hardness, short-range order effects are small, and a new family of stacking-ordered phases appears in ...

  2. Bayesian E(3)-Equivariant Interatomic Potential with Iterative Restratification of Many-body Message Passing

    cs.LG 2025-10 unverdicted novelty 6.0

    Bayesian E(3)-equivariant MLPs with joint energy-force NLL loss achieve competitive accuracy while enabling uncertainty-guided active learning, OOD detection, and calibration.

  3. Data-driven atomistic modelling of hybrid halide perovskite passivation

    cond-mat.mtrl-sci 2026-07 accept novelty 5.0

    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.

  4. Scalable Prediction of Complex Surface Reconstructions under Operating Conditions via Harmony-Search-Based Global Optimization

    cond-mat.mtrl-sci 2026-06 unverdicted novelty 5.0

    HASGO combines harmony search with universal MLIPs and multi-head replay fine-tuning to locate operando surface reconstructions, demonstrated by identifying the square-pyramidal O5 subsurface motif on Ag(100) during e...

  5. Comparing the latent features of universal machine-learning interatomic potentials

    physics.chem-ph 2025-12 unverdicted novelty 5.0

    Different uMLIPs encode chemical space in distinct ways, with high cross-model feature reconstruction errors, and fine-tuning preserves strong pre-training bias in the latent features.

  6. Comparing fine-tuning strategies of MACE machine learning force field for modeling Li-ion diffusion in LiF for batteries

    cond-mat.mtrl-sci 2025-10 conditional novelty 4.0

    MACE-MPA-0 predicts Li diffusion Ea of 0.22 eV in LiF, fine-tuned version with 300 points gives 0.20 eV, close to DeePMD reference of 0.24 eV, using far less training data.

  7. SLUSCHI-UP: A Web Infrastructure for SLUSCHI Melting-Temperature Calculations Using Universal Machine-Learning Interatomic Potentials

    cond-mat.mtrl-sci 2026-06 accept novelty 2.0

    SLUSCHI-UP deploys the SLUSCHI melting-temperature workflow as a web service backed by selectable universal ML interatomic potentials with reported validation errors on benchmark sets.