Share Email Print

Proceedings Paper

Comparing linear structure-based and data-driven latent spatial representations for sequence prediction
Author(s): Myriam Bontonou; Carlos Lassance; Vincent Gripon; Nicolas Farrugia
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Predicting the future of Graph-supported Time Series (GTS) is a key challenge in many domains, such as climate monitoring, finance or neuroimaging. Yet it is a highly difficult problem as it requires to account jointly for time and graph (spatial) dependencies. To simplify this process, it is common to use a two-step procedure in which spatial and time dependencies are dealt with separately. In this paper, we are interested in comparing various linear spatial representations, namely structure-based ones and data-driven ones, in terms of how they help predict the future of GTS. To that end, we perform experiments with various datasets including spontaneous brain activity and raw videos.

Paper Details

Date Published: 9 September 2019
PDF: 9 pages
Proc. SPIE 11138, Wavelets and Sparsity XVIII, 111380Z (9 September 2019); doi: 10.1117/12.2528450
Show Author Affiliations
Myriam Bontonou, IMT Atlantique, Lab-STICC (France)
Univ. of Montréal, MILA (Canada)
Carlos Lassance, IMT Atlantique, Lab-STICC (France)
Univ. of Montréal, MILA (Canada)
Vincent Gripon, IMT Atlantique, Lab-STICC (France)
Univ. of Montréal, MILA (Canada)
Nicolas Farrugia, IMT Atlantique, Lab-STICC (France)

Published in SPIE Proceedings Vol. 11138:
Wavelets and Sparsity XVIII
Dimitri Van De Ville; Manos Papadakis; Yue M. Lu, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?