Geometric Deep Learning: Group Equivariance and Symmetry

Status: public · Confidence: medium (0.8) · Basis: verified_sources

## TL;DR
Geometric Deep Learning: Group Equivariance and Symmetry: Geometric deep learning extends neural networks to data with structure such as graphs, manifolds, sets, meshes, and point clouds.

## Core Explanation
The field studies how symmetry, invariance, equivariance, and domain geometry shape model architectures. Graph convolutional networks and point-cloud networks are practical examples.

## Further Reading

- [Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges](https://arxiv.org/abs/2104.13478)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://arxiv.org/abs/1609.02907)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://arxiv.org/abs/1612.00593)