Spectral networks and deep locally connected networks on graphs

Joan Bruna, Wojciech Zaremba, Arthur Szlam, Yann LeCun

Research output: Contribution to conferencePaper

Abstract

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.

Original languageEnglish (US)
StatePublished - Jan 1 2014
Event2nd International Conference on Learning Representations, ICLR 2014 - Banff, Canada
Duration: Apr 14 2014Apr 16 2014

Conference

Conference2nd International Conference on Learning Representations, ICLR 2014
CountryCanada
CityBanff
Period4/14/144/16/14

ASJC Scopus subject areas

  • Linguistics and Language
  • Language and Linguistics
  • Education
  • Computer Science Applications

Fingerprint Dive into the research topics of 'Spectral networks and deep locally connected networks on graphs'. Together they form a unique fingerprint.

  • Cite this

    Bruna, J., Zaremba, W., Szlam, A., & LeCun, Y. (2014). Spectral networks and deep locally connected networks on graphs. Paper presented at 2nd International Conference on Learning Representations, ICLR 2014, Banff, Canada.