LFaB: Low Fidelity as Bias for Active Learning in the Chemical Configuration Space
- 21 May 2026
- journal article
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 22 (11) , 5637-5648
Abstract
Active learning promises to provide an optimal training sample selection procedure in the construction of machine learning models. It often relies on minimizing the model's variance, which is assumed to decrease the prediction error. Still, it is frequently even less efficient than pure random sampling. Motivated by the bias-variance decomposition, we propose to minimize the model's bias instead of its variance. By doing so, we are able to almost exactly match the best-case error over all possible greedy sample selection procedures for a relevant application. Our bias approximation is based on using cheap to calculate low fidelity data as known from Δ-ML or multifidelity machine learning. We exemplify our approach for a wider class of applications in quantum chemistry including predicting excitation energies and ab initio potential energy surfaces. Here, the proposed method reduces training data consumption by up to an order of magnitude compared to standard active learning.Keywords
All Related Versions
Funding Information
- Deutsche Forschungsgemeinschaft (ZA 1175/3-1)
- Deutsche Forschungsgemeinschaft (ZA 1175/4-1)
- Bergische Universität Wuppertal
This publication has 51 references indexed in Scilit:
- Data Generation for Machine Learning Interatomic Potentials and BeyondChemical Reviews, 2024
- Machine learning small molecule properties in drug discoveryArtificial Intelligence Chemistry, 2023
- Artificial Intelligence in Chemistry: Current Trends and Future DirectionsJournal of Chemical Information and Modeling, 2021
- Machine Learning for Electronically Excited States of MoleculesChemical Reviews, 2020
- TorchANI: A Free and Open Source PyTorch-Based Deep Learning Implementation of the ANI Neural Network PotentialsJournal of Chemical Information and Modeling, 2020
- Constructing high‐dimensional neural network potentials: A tutorial reviewInternational Journal of Quantum Chemistry, 2015
- Active Learning2012
- An improved subspace selection algorithm for meshless collocation methodsInternational Journal for Numerical Methods in Engineering, 2009
- An Introduction to Coupled Cluster Theory for Computational Chemists2000
- Bootstrap Methods: Another Look at the Jackknife1992