OrbGNN: A Wave function-based Machine Learning Interelectronic Representation
Abstract
Machine learning interatomic potentials (MLIPs) have become emerging tools in molecular modeling and computational chemistry. By learning high-dimensional potential energy surfaces from quantum chemical data, MLIPs enable accurate and efficient predictions of structural, thermodynamic, and dynamical properties. However, such models have limitations in predictions of electronic properties and the effects of static electron correlation due to their lack of electronic structure information. This work presents OrbGNN, an electronic structure graph architecture analogous to molecular graph and MLIP frameworks, where pair-orbital interactions constitute the graph representation, while orbital entanglement encodes the connectivity between them. By embedding information derived from orbital correlation metrics directly into the graph topology, OrbGNN provides a compact representation of a molecule s orbital landscape and electron correlation patterns. Analysis of the behavior of the feature space in an orbital graph are shown to demonstrate model robustness. The model is evaluated for the dissociation of nitrogen and for a larger dataset of diatomic molecules. Finally, the OrbGNN model is applied to a set of octahedral iron(II) complexes to predict spin-state energy gaps.
Related
- A Hybrid Message-Passing and Electric-Field Representation for Electrostatic QM/MM Embedding with Machine Learning Interatomic Potentials
- MACHINE LEARNING FOR CELLULOSE MEMBRANES: A REPRESENTATION–MODEL–TASK FRAMEWORK FOR SMALL-DATA REGIMES
- Machine learning-assisted highly efficient thermal management in function-oriented thermochromic smart windows
- Fragment-Based Representation Learning for Polymers and Heterogeneous Formulations
- Multimodal Representation Learning for Exploring Natural Product Chemical Space
BibTeX
@misc{quebedeaux2026orbgnn,
title = {{OrbGNN: A Wave function-based Machine Learning Interelectronic Representation}},
author = {Brody Quebedeaux and Shahzad Akram and Markus Reiher and Konstantinos D. Vogiatzis},
howpublished = {arXiv},
year = {2026},
month = aug,
doi = {10.48550/arxiv.2608.27806},
eprint = {2608.27806},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.27806},
note = {CC BY-SA 4.0},
}
RIS
TY - UNPB
TI - OrbGNN: A Wave function-based Machine Learning Interelectronic Representation
AU - Brody Quebedeaux
AU - Shahzad Akram
AU - Markus Reiher
AU - Konstantinos D. Vogiatzis
PY - 2026
DA - 2026/08/31
PB - arXiv
DO - 10.48550/arxiv.2608.27806
UR - https://arxiv.org/abs/2608.27806
AB - Machine learning interatomic potentials (MLIPs) have become emerging tools in molecular modeling and computational chemistry. By learning high-dimensional potential energy surfaces from quantum chemical data, MLIPs enable accurate and efficient predictions of structural, thermodynamic, and dynamical properties. However, such models have limitations in predictions of electronic properties and the effects of static electron correlation due to their lack of electronic structure information. This work presents OrbGNN, an electronic structure graph architecture analogous to molecular graph and MLIP frameworks, where pair-orbital interactions constitute the graph representation, while orbital entanglement encodes the connectivity between them. By embedding information derived from orbital correlation metrics directly into the graph topology, OrbGNN provides a compact representation of a molecule s orbital landscape and electron correlation patterns. Analysis of the behavior of the feature space in an orbital graph are shown to demonstrate model robustness. The model is evaluated for the dissociation of nitrogen and for a larger dataset of diatomic molecules. Finally, the OrbGNN model is applied to a set of octahedral iron(II) complexes to predict spin-state energy gaps.
ER -