Allegro is a machine learning interatomic potential (MLIP) model designed to predict atomic properties in molecules using E(3) equivariant neural networks. When training this model, there tends to be a trade-off between accuracy and inference time. For this reason we apply multi-objective hyperparameter optimization to the two objectives. Additionally, we experiment with modified architectures by making variants of Allegro some by adding strictly classical multi-layer perceptron (MLP) layers and some by adding quantum-classical hybrid layers. We compare the results from QM9, rMD17-aspirin, rMD17-benzene and our own proprietary dataset consisting of copper and lithium atoms. As results, we have a list of variants that surpass the Allegro in accuracy and also results which demonstrate the trade-off with inference times.
@article{arxiv.2602.16908,
title = {Multi-objective optimization and quantum hybridization of equivariant deep learning interatomic potentials on organic and inorganic compounds},
author = {G. Laskaris and D. Morozov and D. Tarpanov and A. Seth and J. Procelewska and G. Sai Gautam and A. Sagingalieva and R. Brasher and A. Melnikov},
journal= {arXiv preprint arXiv:2602.16908},
year = {2026}
}