Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

Michaël Defferrard, Xavier Bresson, Pierre Vandergheynst
6/30/2016
cs.LGstat.ML

Official code: mdeff/cnn_graph (1,367 stars, MIT, last commit 2020-06-13).

Abstract

In this work, we are interested in generalizing convolutional neural networks (CNNs) from low-dimensional regular grids, where image, video and speech are represented, to high-dimensional irregular domains, such as social networks, brain connectomes or words' embedding, represented by graphs. We present a formulation of CNNs in the context of spectral graph theory, which provides the necessary mathematical background and efficient numerical schemes to design fast localized convolutional filters on graphs. Importantly, the proposed technique offers the same linear computational complexity and constant learning complexity as classical CNNs, while being universal to any graph structure. Experiments on MNIST and 20NEWS demonstrate the ability of this novel deep learning system to learn local, stationary, and compositional features on graphs.

View on arXivView PDF

Code Implementations(1)

mdeff/cnn_graphOfficial100%
MIT

Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

1,367386Python, MakefileSep 13, 20166 years agoMIT
convolutional-neural-networksdeep-learninggraph-neural-networksgraph-signal-processinggraphs

Similar Papers

CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filters

89% match1 repo262017

Heterogeneous Graph Convolutional Neural Network via Hodge-Laplacian for Brain Functional Data

87% match2023

Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs

86% match1 repo2332017

Semi-Supervised Classification with Graph Convolutional Networks

85% match2 repos7.4k2016

Specformer: Spectral Graph Neural Networks Meet Transformers

85% match1 repo882023

Equivariant Machine Learning on Graphs with Nonlinear Spectral Filters

83% match2024

Cite this paper

@article{defferrard2016convolutional,
  title  = {Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering},
  author = {Michaël Defferrard and Xavier Bresson and Pierre Vandergheynst},
  year   = {2016},
  eprint = {1606.09375},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1606.09375}
}

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/1606.09375.svg)](https://codeofpaper.com/paper/1606.09375)

Discussion