NIPS Proceedingsβ

Unsupervised Deep Haar Scattering on Graphs

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

[PDF] [BibTeX] [Supplemental] [Reviews]


Conference Event Type: Poster


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.