When learning a property from data, it is often useful or required that the model obeys symmetries of the underlying data. E(3)-equivariant networks obey the symmetry of rotation and translation in 3D space. They are therefore a natural choice when modelling data in 3D space, e.g. atomic coordinates of a molecule or point clouds obtained from 3D imaging. In this talk I plan to:

• Explain the concept of equivariance
• Describe the basic building blocks of an E(3) equivariant network
• Briefly discuss an application: Learning properties of molecules

Resources:

• Geiger 2022, Review of E(3) equivariance
• Batzner 2022, Application for molecules
• Google colab using e3nn
• Jing 2021, Geometric Vector Perceptron