Paying attention to long-range electron correlation: a size-independent deep-learning approach to predicting molecules' electronic energies from one- and two-electron integrals

2025/04/04 by Valerii Chuiko, Chuiko, Valerii, Da Rosa, Giovanni B. +1
Materials Science · Physics and Astronomy · Biochemistry, Genetics and Molecular Biology · #Machine Learning in Materials Science #Quantum many-body systems #Advanced Electron Microscopy Techniques and Applications

paper · pdf · doi:10.48550/arxiv.2504.03849

Abstract

We propose a descriptor for molecular electronic structure that is based solely on the one- and two-electron integrals but is translationally, rotationally, and unitarily invariant. Then, directly exploiting size consistency, we train and fine tune a neural network to predict the energies of strongly-correlated systems, specifically hydrogen clusters. We use an attention mechanism to formulate a size-independent approach that uses and preserves size-consistency. Therefore, training on few-electron systems can guide predictions for systems with more electrons. Our results are more accurate than alternative geometry-based machine-learning models.

Related

• Learning Full Configuration Interaction Electron Correlations with Deep Learning
• Stacked Generalization Approach to Improve Prediction of Molecular Atomization Energies
• Unified Deep Learning Framework for Many-Body Quantum Chemistry via Green's Functions
• Incorporating electronic information into Machine Learning potential energy surfaces via approaching the ground-state electronic energy as a function of atom-based electronic populations
• Advancing Natural Orbital Functional Calculations Through Deep Learning-Inspired Techniques for Large-Scale Strongly Correlated Electron Systems