DeepSphere: towards an equivariant graph-based spherical CNN

Michaël Defferrard, Nathanaël Perraudin, Tomasz Kacprzak, Raphael Sgier
4/8/2019
cs.LGstat.ML

Official code: deepsphere/deepsphere-tf1 (14 stars, MIT, TensorFlow, last commit 2021-01-01).

Abstract

Spherical data is found in many applications. By modeling the discretized sphere as a graph, we can accommodate non-uniformly distributed, partial, and changing samplings. Moreover, graph convolutions are computationally more efficient than spherical convolutions. As equivariance is desired to exploit rotational symmetries, we discuss how to approach rotation equivariance using the graph neural network introduced in Defferrard et al. (2016). Experiments show good performance on rotation-invariant learning problems. Code and examples are available at https://github.com/SwissDataScienceCenter/DeepSphere

View on arXivView PDF

Code Implementations(1)

deepsphere/deepsphere-tf1Official100%
TensorFlowMIT

DeepSphere: a graph-based spherical CNN (TensorFlow)

142Shell, PythonNov 7, 20195 years agoMIT
climate-sciencecosmological-inferencedeepspheregraph-neural-networkssphere+3 more

Similar Papers

DeepSphere: a graph-based spherical CNN

92% match1 repo142020

A Complete Guide to Spherical Equivariant Graph Transformers

86% match2025

SO(3)-Equivariant Neural Networks for Learning Vector Fields on Spheres

85% match2025

Rotational Equivariance in Machine Learning: A Comprehensive Tutorial

85% match2026

Learning SO(3) Equivariant Representations with Spherical CNNs

85% match1 repo3072017

Representing spherical tensors with scalar-based machine-learning models

84% match2025

Cite this paper

@article{defferrard2019deepsphere,
  title  = {DeepSphere: towards an equivariant graph-based spherical CNN},
  author = {Michaël Defferrard and Nathanaël Perraudin and Tomasz Kacprzak and Raphael Sgier},
  year   = {2019},
  eprint = {1904.05146},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1904.05146}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1904.05146.svg)](https://codeofpaper.com/paper/1904.05146)

Discussion