Graphs are extensively used to represent networked data. In many applications, especially when considering large datasets, it is a desirable feature to focus the analysis onto specific subgraphs of interest. Slepian theory and its extension to graphs allows to do this and has been applied recently to analyze various types of networks. One limitation of this framework, however, is that the number of subgraphs of interest is typically limited to one. We introduce an extended Slepian design that allows to consider an arbitrary number of subgraphs of interest. This extension offers the possibility to encode prior information about multiple subgraphs in a two-dimensional plane. As a proof of concept and potential application, we demonstrate that this framework allows to perform time-resolved and spatio-temporal analyses of dynamic graphs.

Date Published: 9 September 2019
PDF: 7 pages
Proc. SPIE 11138, Wavelets and Sparsity XVIII, 1113810 (9 September 2019); doi: 10.1117/12.2530550

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