Local stationarity of graph signals: insights and experiments - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2017

Local stationarity of graph signals: insights and experiments

Abstract

In this paper, we look at one of the most crucial ingredient to graph signal processing: the graph. By taking a step back on the conventional approach using Gaussian weights, we are able to obtain a better spectral representation of a stochastic graph signal. Our approach focuses on learning the weights of the graphs, thus enabling better richness in the structure by incorporating both the distance and the local structure into the weights. Our results show that the graph power spectrum we obtain is closer to what we expect, and stationarity is better preserved when going from a continuous signal to its sampled counterpart on the graph. We further validate the approach on a real weather dataset.
Fichier principal
Vignette du fichier
wavelet_sparsity_xvii.pdf (6.74 Mo) Télécharger le fichier
DataDrivenGraphWeightsLearning.zip (1.81 Mo) Télécharger le fichier
wavelet_sparsity_xvii_slides.pdf (3.47 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Other
Origin : Files produced by the author(s)
Comment : Matlab Code
Format : Presentation
Origin : Files produced by the author(s)

Dates and versions

hal-01574215 , version 1 (11-08-2017)

Identifiers

Cite

Benjamin Girault, Shrikanth S Narayanan, Antonio Ortega. Local stationarity of graph signals: insights and experiments. Wavelets and Sparsity XVII, Aug 2017, San Diego, United States. pp.1-17, ⟨10.1117/12.2274584⟩. ⟨hal-01574215⟩
152 View
318 Download

Altmetric

Share

Gmail Facebook X LinkedIn More