Unsupervised Deep Haar Scattering on Graphs

Part of Advances in Neural Information Processing Systems 27 (NIPS 2014)

Bibtex Metadata Paper Reviews Supplemental

Authors

Xu Chen, Xiuyuan Cheng, Stephane Mallat

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.