Rotational Equivariance in Machine Learning: A Comprehensive Tutorial
2026-08-31 • Machine Learning
Machine Learning
AI summaryⓘ
The authors explain how machine learning models that work with 3D data can be designed to respect rotational symmetry, meaning their outputs change predictably when the input is rotated. They introduce important math concepts like group theory and spherical harmonics to help understand and build these models. The tutorial covers different methods to ensure models handle rotations properly and compares their benefits and drawbacks. Overall, the authors aim to make the complex math accessible and help practitioners choose the best approach for their needs.
Rotational equivarianceGroup theoryRepresentation theorySpherical harmonicsWigner matricesTensor productsClebsch-Gordan decompositionMessage passingGroup convolutionsCanonicalization
Authors
Peter Lippmann, Fred A. Hamprecht
Abstract
Rotational symmetry is one of the most important structural principles in machine learning on 3D data. In applications ranging from physics and materials science to 3D computer vision, predictions should not depend on an arbitrary choice of coordinate frame. Rotational equivariance captures this requirement mathematically by enforcing that a rotation of the input induces a corresponding transformation of the model output. This tutorial provides a comprehensive introduction to rotational equivariance, starting from the physical and geometric intuition behind coordinate independence and building up the necessary machinery from geometric deep learning, group theory, and representation theory. We introduce message passing on Euclidean graphs, group actions and representations, spherical harmonics, Wigner matrices, tensor products, and Clebsch-Gordan decomposition, and explain how these ingredients give rise to modern equivariant architectures. We then survey the principal strategies for incorporating rotational equivariance in deep learning, including group convolutions, internal tensorial representations, and canonicalization-based methods, and discuss their practical strengths and limitations. The tutorial aims to lower the barrier to the subject by connecting the underlying mathematics to practical model design, by unifying ideas that are often expressed in different formal languages, and by helping practitioners choose among competing approaches through a clear discussion of their trade-offs.