Bias in Universal Machine-Learned Interatomic Potentials and its Effects on Fine-Tuning

TL;DR

This paper investigates biases in universal machine-learned interatomic potentials (uMLIPs), showing that periodic fine-tuning improves their accuracy and generalizability in molecular dynamics, and introduces methods to quantify uncertainty and extrapolation risks.

Contribution

It reveals the impact of model bias in uMLIPs, compares naive and periodic fine-tuning approaches, and proposes analysis techniques for uncertainty quantification in MD simulations.

Findings

Naive fine-tuning produces datasets that fail to represent MD simulations.

Periodic fine-tuning results in more accurate and generalizable models.

Q-residual analysis serves as a proxy for epistemic uncertainty.

Abstract

Universal machine learned interatomic potentials (uMLIPs) embody a growing area of interest due to their transferability across the periodic table, displaying an error of about 0.6 kcal/mol against the Matbench Discovery test set. However, we show that achieving more accurate predictions on out-of-domain tasks requires fine-tuning. Additionally, we investigate the existence and influence of model biases in molecular dynamics (MD) by examining two approaches for data generation: from multiple MD trajectories in parallel, which we call naive fine-tuning, and from a single MD trajectory with fine-tuning after set intervals, which we call periodic fine-tuning. Our results find that naive fine-tuning generates constrained datasets that fail to represent MD simulations, and thus downstream fine-tuned models fail during extrapolation. In contrast, periodic fine-tuning yields models which are more generalizable and accurate, producing low-error dynamics. These findings indicate the role of uMLIP bias in fine-tuning, and highlights the need for multiple fine-tuning steps. Lastly, we relate unphysical behavior to principal component space, and quantify extrapolations through Q-residual analysis, which are useful as a proxy for epistemic uncertainty for larger simulations.