Multi-task learning for electronic structure to predict and explore molecular potential energy surfaces

*Qiao, Zhuoran*,
Ding, Feizhi,
Welborn, Matthew,
Bygrave, Peter J,
Anandkumar, Animashree,
Manby, Frederick R,
and Miller III, Thomas F

*arXiv preprint arXiv:2011.02680*
2020
(Appeared at *Machine Learning for Molecules workshop at NeurIPS 2020* as a **contributed talk**)

We refine the OrbNet model to accurately predict energy, forces, and other response properties for molecules using a graph neural-network architecture based on features from low-cost approximated quantum operators in the symmetry-adapted atomic orbital basis. The model is end-to-end differentiable due to the derivation of analytic gradients for all electronic structure terms, and is shown to be transferable across chemical space due to the use of domain-specific features. The learning efficiency is improved by incorporating physically motivated constraints on the electronic structure through multi-task learning. The model outperforms existing methods on energy prediction tasks for the QM9 dataset and for molecular geometry optimizations on conformer datasets, at a computational cost that is thousand-fold or more reduced compared to conventional quantum-chemistry calculations (such as density functional theory) that offer similar accuracy.