A Caltech Library Service

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

Qiao, Zhuoran and Ding, Feizhi and Welborn, Matthew and Bygrave, Peter J. and Smith, Daniel G. A. and Anandkumar, Animashree and Manby, Frederick R. and Miller, Thomas F., III (2020) Multi-task learning for electronic structure to predict and explore molecular potential energy surfaces. In: 34th Conference on Neural Information Processing Systems. Advances in Neural Information Processing Systems. No.33. Neural Information Processing Systems Foundation , Red Hook, NY, pp. 1-23.

[img] PDF - Published Version
See Usage Policy.

[img] PDF - Accepted Version
See Usage Policy.


Use this Persistent URL to link to this item:


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.

Item Type:Book Section
Related URLs:
URLURL TypeDescription Paper
Qiao, Zhuoran0000-0002-5704-7331
Welborn, Matthew0000-0001-8659-6535
Manby, Frederick R.0000-0001-7611-714X
Miller, Thomas F., III0000-0002-1882-5380
Additional Information:© 2021 Neural Information Processing Systems Foundation. Z.Q. acknowledges the graduate research funding from Caltech. T.F.M. and A.A. acknowledge partial support from the Caltech DeLogi fund, and A.A. acknowledges support from a Caltech Bren professorship. The authors gratefully acknowledge NVIDIA, including Abe Stern and Tom Gibbs, for helpful discussions regarding GPU implementations of graph neural networks.
Funding AgencyGrant Number
Caltech De Logi FundUNSPECIFIED
Bren Professor of Computing and Mathematical SciencesUNSPECIFIED
Series Name:Advances in Neural Information Processing Systems
Issue or Number:33
Record Number:CaltechAUTHORS:20201203-151028849
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:106900
Deposited By: George Porter
Deposited On:05 Dec 2020 01:51
Last Modified:02 Jun 2023 01:12

Repository Staff Only: item control page