Hierarchical modeling of molecular energies using a deep neural network
This enables accurate energy predictions for molecular systems, with potential applications in chemistry and materials science, though it appears incremental as it builds on existing neural network and many-body expansion approaches.
The paper tackles the problem of modeling molecular energies from quantum calculations by introducing HIP-NN, a deep neural network that decomposes energies hierarchically, achieving state-of-the-art performance with 0.26 kcal/mol mean absolute error on a dataset of 131k organic molecules.
We introduce the Hierarchically Interacting Particle Neural Network (HIP-NN) to model molecular properties from datasets of quantum calculations. Inspired by a many-body expansion, HIP-NN decomposes properties, such as energy, as a sum over hierarchical terms. These terms are generated from a neural network--a composition of many nonlinear transformations--acting on a representation of the molecule. HIP-NN achieves state-of-the-art performance on a dataset of 131k ground state organic molecules, and predicts energies with 0.26 kcal/mol mean absolute error. With minimal tuning, our model is also competitive on a dataset of molecular dynamics trajectories. In addition to enabling accurate energy predictions, the hierarchical structure of HIP-NN helps to identify regions of model uncertainty.