Implicit Delta Learning of High Fidelity Neural Network Potentials

TL;DR

The paper introduces Implicit Delta Learning (IDLe), a multi-task neural network approach that reduces high-fidelity quantum data requirements for molecular simulations by effectively leveraging cheaper semi-empirical computations.

Contribution

It presents a novel multi-task architecture for NNPs that maintains accuracy while drastically reducing the need for costly high-fidelity data.

Findings

IDLe achieves high accuracy with up to 50x less high-fidelity data.

The method maintains inference speed comparable to single-fidelity models.

Provides a large dataset of semi-empirical QM calculations for future research.

Abstract

Neural network potentials (NNPs) offer a fast and accurate alternative to ab-initio methods for molecular dynamics (MD) simulations but are hindered by the high cost of training data from high-fidelity Quantum Mechanics (QM) methods. Our work introduces the Implicit Delta Learning (IDLe) method, which reduces the need for high-fidelity QM data by leveraging cheaper semi-empirical QM computations without compromising NNP accuracy or inference cost. IDLe employs an end-to-end multi-task architecture with fidelity-specific heads that decode energies based on a shared latent representation of the input atomistic system. In various settings, IDLe achieves the same accuracy as single high-fidelity baselines while using up to 50x less high-fidelity data. This result could significantly reduce data generation cost and consequently enhance accuracy and generalization, and expand chemical coverage for NNPs, advancing MD simulations for material science and drug discovery. Additionally, we provide a novel set of 11 million semi-empirical QM calculations to support future multi-fidelity NNP modeling.