Published May 9, 2025 | Version v1
Dataset Open

Representing spherical tensors with scalar-based machine-learning models

  • 1. COSMO—Laboratory of Computational Science and Modelling, IMX, École Polytechnique Fédérale de Lausanne, 1015 Lausanne, Switzerland

* Contact person

Description

Rotational symmetry plays a central role in physics, providing an elegant framework to describe how the properties of 3D objects – from atoms to the macroscopic scale – transform under the action of rigid rotations. Equivariant models of 3D point clouds are able to approximate structure-property relations in a way that is fully consistent with the structure of the rotation group, by combining intermediate representations that are themselves spherical tensors. The symmetry constraints however make this approach computationally demanding and cumbersome to implement, which motivates increasingly popular unconstrained architectures that learn approximate symmetries as part of the training process. In this work, we explore a third route to tackle this learning problem, where equivariant functions are expressed as the product of a scalar function of the point cloud coordinates and a small basis of tensors with the appropriate symmetry. We also propose approximations of the general expressions that, while lacking universal approximation properties, are fast, simple to implement, and accurate in practical settings.

Files

File preview

files_description.md

All files

Files (2.7 GiB)

Name Size
md5:72e55ce327426c91c3e434a6e2f12d47
1.1 KiB Preview Download
md5:0667af7651789f90f22aa9c9dc423717
343.3 MiB Preview Download
md5:f1eb6625dbb20ab8279392bdd94f1fdb
356 Bytes Download
md5:06e64a0600bb208209655d75e857ceb7
25.4 MiB Preview Download
md5:c8eced2c1b23f543f6408d716a026996
2.5 KiB Preview Download
md5:5413ebda8490d55237338e8f33757d85
96.8 MiB Preview Download
md5:d38dbb9d76599c9d779021309bba81c9
2.2 GiB Preview Download