Unsupervised Deep Haar Scattering on Graphs

Abstract

The classification of high-dimensional data defined on graphs is particularly difficult when the graph geometry is unknown. We introduce a Haar scattering transform on graphs, which computes invariant signal descriptors. It is implemented with a deep cascade of additions, subtractions and absolute values, which iteratively compute orthogonal Haar wavelet transforms. Multiscale neighborhoods of unknown graphs are estimated by minimizing an average total variation, with a pair matching algorithm of polynomial complexity. Supervised classification with dimension reduction is tested on data bases of scrambled images, and for signals sampled on unknown irregular grids on a sphere.

Cite

Text

Chen et al. "Unsupervised Deep Haar Scattering on Graphs." Neural Information Processing Systems, 2014.

Markdown

[Chen et al. "Unsupervised Deep Haar Scattering on Graphs." Neural Information Processing Systems, 2014.](https://mlanthology.org/neurips/2014/chen2014neurips-unsupervised/)

BibTeX

@inproceedings{chen2014neurips-unsupervised,
  title     = {{Unsupervised Deep Haar Scattering on Graphs}},
  author    = {Chen, Xu and Cheng, Xiuyuan and Mallat, Stephane},
  booktitle = {Neural Information Processing Systems},
  year      = {2014},
  pages     = {1709-1717},
  url       = {https://mlanthology.org/neurips/2014/chen2014neurips-unsupervised/}
}