SchNet: A continuous-filter convolutional neural network for modeling quantum interactions

TL;DR

SchNet introduces a continuous-filter convolutional neural network architecture that effectively models quantum interactions in molecules, capturing physical invariances and enabling accurate energy and force predictions for chemical systems.

Contribution

The paper presents SchNet, a novel deep learning architecture utilizing continuous-filter convolutions to model quantum interactions without grid restrictions, improving accuracy and physical consistency.

Findings

Achieves state-of-the-art results on molecular benchmarks.

Models total energy and forces consistent with quantum principles.

Introduces a new challenging benchmark for chemical and structural diversity.

Abstract

Deep learning has the potential to revolutionize quantum chemistry as it is ideally suited to learn representations for structured data and speed up the exploration of chemical space. While convolutional neural networks have proven to be the first choice for images, audio and video data, the atoms in molecules are not restricted to a grid. Instead, their precise locations contain essential physical information, that would get lost if discretized. Thus, we propose to use continuous-filter convolutional layers to be able to model local correlations without requiring the data to lie on a grid. We apply those layers in SchNet: a novel deep learning architecture modeling quantum interactions in molecules. We obtain a joint model for the total energy and interatomic forces that follows fundamental quantum-chemical principles. This includes rotationally invariant energy predictions and a smooth, differentiable potential energy surface. Our architecture achieves state-of-the-art performance for benchmarks of equilibrium molecules and molecular dynamics trajectories. Finally, we introduce a more challenging benchmark with chemical and structural variations that suggests the path for further work.