Spectral Networks and Locally Connected Networks on Graphs

By Joan Bruna, Wojciech Zaremba, Arthur Szlam, Yann LeCun. 2013

5,411 citations recorded by the source corpus.

Convolutional Neural Networks are extremely efficient architectures in image and audio recognition tasks, thanks to their ability to exploit the local translational invariance of signal classes over their domain. In this paper we consider possible generalizations of CNNs to signals defined on more general domains without the action of a translation group. In particular, we propose two constructions, one based upon a hierarchical clustering of the domain, and another based on the spectrum of the graph Laplacian. We show through experiments that for low-dimensional graphs it is possible to learn convolutional layers with a number of parameters independent of the input size, resulting in efficient deep architectures.

Subfields: Applied Mathematics, Artificial Intelligence, Graph Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Applied Mathematics

  1. Joan Bruna
  2. Michael M. Bronstein
  3. Max Welling
  4. Pierre Vandergheynst
  5. Thomas Kipf
  6. Pascal Frossard
  7. José M. F. Moura
  8. William L. Hamilton

In Artificial Intelligence

  1. Yoshua Bengio
  2. Mohit Bansal
  3. Percy Liang
  4. Quoc V. Le
  5. Jianfeng Gao
  6. Sergey Levine
  7. Ruslan Salakhutdinov
  8. Dacheng Tao

In Graph Learning

  1. Jure Leskovec
  2. William L. Hamilton
  3. Stephan Günnemann
  4. Matthias Fey
  5. Michael M. Bronstein
  6. Aleksandar Bojchevski
  7. Rex Ying
  8. Max Welling

Citations in the corpus