Geometric Prediction: Moving Beyond Scalars

Abstract

Many quantities we are interested in predicting are geometric tensors; we refer to this class of problems as geometric prediction. Attempts to perform geometric prediction in real-world scenarios have been limited to approximating them through scalar predictions, leading to losses in data efficiency. In this work, we demonstrate that equivariant networks have the capability to predict real-world geometric tensors without the need for such approximations. We show the applicability of this method to the prediction of force fields and then propose a novel formulation of an important task, biomolecular structure refinement, as a geometric prediction problem, improving state-of-the-art structural candidates. In both settings, we find that our equivariant network is able to generalize to unseen systems, despite having been trained on small sets of examples. This novel and data-efficient ability to predict real-world geometric tensors opens the door to addressing many problems through the lens of geometric prediction, in areas such as 3D vision, robotics, and molecular and structural biology.

10 pages, 8 figures

References in corpus (7)

• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• Group Equivariant Convolutional Networks
• Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
• N-body Networks: a Covariant Hierarchical Neural Network Architecture for Learning Atomic Potentials

Cited by in corpus (3)

• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• Relevance of Rotationally Equivariant Convolutions for Predicting Molecular Properties
• HEroBM: a deep equivariant graph neural network for universal backmapping from coarse-grained to all-atom representations