Skip to Main content Skip to Navigation
Conference papers

Inferring Graph Signal Translations as Invariant Transformations for Classification Tasks

Raphael Baena 1, 2 Lucas Drumetz 3, 1 Vincent Gripon 2, 1
2 Lab-STICC_2AI - Equipe Algorithm Architecture Interactions
Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance : UMR6285
3 Lab-STICC_OSE - Equipe Observations Signal & Environnement
Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance : UMR6285
Abstract : The field of Graph Signal Processing (GSP) has proposed tools to generalize harmonic analysis to complex domains represented through graphs. Among these tools are translations, which are required to define many others. Most works propose to define translations using solely the graph structure (i.e. edges). Such a problem is ill-posed in general as a graph conveys information about neighborhood but not about directions. In this paper, we propose to infer translations as edge-constrained operations that make a supervised classification problem invariant using a deep learning framework. As such, our methodology uses both the graph structure and labeled signals to infer translations. We perform experiments with regular 2D images and abstract hyperlink networks to show the effectiveness of the proposed methodology in inferring meaningful translations for signals supported on graphs.
Complete list of metadata

https://hal-imt-atlantique.archives-ouvertes.fr/hal-03235669
Contributor : Raphael Baena <>
Submitted on : Tuesday, May 25, 2021 - 10:23:55 PM
Last modification on : Friday, May 28, 2021 - 3:41:01 AM

File

Graph_convolution_Eusipco.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03235669, version 1

Citation

Raphael Baena, Lucas Drumetz, Vincent Gripon. Inferring Graph Signal Translations as Invariant Transformations for Classification Tasks. Eusipco 2021, Aug 2021, Dublin, Ireland. ⟨hal-03235669⟩

Share

Metrics

Record views

30

Files downloads

11