Investigating Data Hierarchies in Multifidelity Machine Learning for Excitation Energies

Abstract

Recent progress in machine learning (ML) has made high-accuracy quantum chemistry (QC) calculations more accessible. Of particular interest are multifidelity machine learning (MFML) methods where training data from differing accuracies or fidelities are used. These methods usually employ a fixed scaling factor, $\gamma$, to relate the number of training samples across different fidelities, which reflects the cost and assumed sparsity of the data. This study investigates the impact of modifying $\gamma$ on model efficiency and accuracy for the prediction of vertical excitation energies using the QeMFi benchmark dataset. Further, this work introduces QC compute time informed scaling factors, denoted as $\theta$, that vary based on QC compute times at different fidelities. A novel error metric, error contours of MFML, is proposed to provide a comprehensive view of model error contributions from each fidelity. The results indicate that high model accuracy can be achieved with just 2 training samples at the target fidelity when a larger number of samples from lower fidelities are used. This is further illustrated through a novel concept, the $\Gamma$-curve, which compares model error against the time-cost of generating training samples, demonstrating that multifidelity models can achieve high accuracy while minimizing training data costs.

Modified errors to be relative MAE. Transferability tests of training on QeMFi and testing on QUESTDB have now been added

References in corpus (17)

• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications
• Machine learning for molecular simulation
• Big Data meets Quantum Chemistry Approximations: The $\Delta$-Machine Learning Approach
• Machine learning for electronically excited states of molecules
• A Mountaineering Strategy to Excited States: Highly-Accurate Reference Energies and Benchmarks
• A foundation model for atomistic materials chemistry
• Learning Properties of Ordered and Disordered Materials from Multi-fidelity Data
• Perspective on integrating machine learning into computational chemistry and materials science
• QUESTDB: a database of highly-accurate excitation energies for the electronic structure community
• Efficient and Accurate Simulations of Vibrational and Electronic Spectra with Symmetry-Preserving Neural Network Models for Tensorial Properties
• Deep Learning for UV Absorption Spectra with SchNarc: First Steps Towards Transferability in Chemical Compound Space
• Multi-Fidelity Machine Learning for Excited State Energies of Molecules
• Optimized Multifidelity Machine Learning for Quantum Chemistry
• Multitask methods for predicting molecular properties from heterogeneous data
• Assessing Non-Nested Configurations of Multifidelity Machine Learning for Quantum-Chemical Properties
• Alchemical harmonic approximation based potential for iso-electronic diatomics: Foundational baseline for $\Delta$-machine learning