Kernel-based reconstruction of space-time functions via extended graphs

Vassilis N. Ioannidis; Daniel Romero; Georgios B. Giannakis

doi:10.1109/ACSSC.2016.7869700

Kernel-based reconstruction of space-time functions via extended graphs

Vassilis N. Ioannidis, Daniel Romero, Georgios B. Giannakis

Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

7 Scopus citations

Abstract

Signals evolving over graphs emerge naturally in a number of applications related to network science. A frequently encountered challenge pertains to reconstructing such signals given their values on subsets of vertices at possibly different time instants. Spatiotemporal dynamics can be leveraged so that a small number of vertices suffices to achieve accurate reconstruction. The present paper broadens the existing kernel-based graph-function reconstruction framework to handle time-evolving functions over (possibly dynamic) graphs. The proposed approach introduces the novel notion of graph extension to enable kernel-based estimators over time and space. Numerical tests with real data corroborate that judiciously capturing time-space dynamics markedly improves reconstruction performance.

Original language	English (US)
Title of host publication	Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016
Editors	Michael B. Matthews
Publisher	IEEE Computer Society
Pages	1829-1833
Number of pages	5
ISBN (Electronic)	9781538639542
DOIs	https://doi.org/10.1109/ACSSC.2016.7869700
State	Published - Mar 1 2017
Event	50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016 - Pacific Grove, United States Duration: Nov 6 2016 → Nov 9 2016

Publication series

Name	Conference Record - Asilomar Conference on Signals, Systems and Computers
ISSN (Print)	1058-6393

Other

Other	50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016
Country/Territory	United States
City	Pacific Grove
Period	11/6/16 → 11/9/16

Bibliographical note

Publisher Copyright:
© 2016 IEEE.

Keywords

Graph signal reconstruction
graph extension
kernel ridge regression
space-time kernels

Publisher link

10.1109/ACSSC.2016.7869700

Find It

Find It at U of M Libraries

Cite this

Ioannidis, V. N., Romero, D., & Giannakis, G. B. (2017). Kernel-based reconstruction of space-time functions via extended graphs. In M. B. Matthews (Ed.), Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016 (pp. 1829-1833). Article 7869700 (Conference Record - Asilomar Conference on Signals, Systems and Computers). IEEE Computer Society. https://doi.org/10.1109/ACSSC.2016.7869700

Kernel-based reconstruction of space-time functions via extended graphs. / Ioannidis, Vassilis N.; Romero, Daniel; Giannakis, Georgios B.
Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016. ed. / Michael B. Matthews. IEEE Computer Society, 2017. p. 1829-1833 7869700 (Conference Record - Asilomar Conference on Signals, Systems and Computers).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Ioannidis, VN, Romero, D & Giannakis, GB 2017, Kernel-based reconstruction of space-time functions via extended graphs. in MB Matthews (ed.), Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016., 7869700, Conference Record - Asilomar Conference on Signals, Systems and Computers, IEEE Computer Society, pp. 1829-1833, 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016, Pacific Grove, United States, 11/6/16. https://doi.org/10.1109/ACSSC.2016.7869700

Ioannidis VN, Romero D, Giannakis GB. Kernel-based reconstruction of space-time functions via extended graphs. In Matthews MB, editor, Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016. IEEE Computer Society. 2017. p. 1829-1833. 7869700. (Conference Record - Asilomar Conference on Signals, Systems and Computers). doi: 10.1109/ACSSC.2016.7869700

Ioannidis, Vassilis N. ; Romero, Daniel ; Giannakis, Georgios B. / Kernel-based reconstruction of space-time functions via extended graphs. Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016. editor / Michael B. Matthews. IEEE Computer Society, 2017. pp. 1829-1833 (Conference Record - Asilomar Conference on Signals, Systems and Computers).

@inproceedings{11a6069c28db49a0be1be63e64115f89,

title = "Kernel-based reconstruction of space-time functions via extended graphs",

abstract = "Signals evolving over graphs emerge naturally in a number of applications related to network science. A frequently encountered challenge pertains to reconstructing such signals given their values on subsets of vertices at possibly different time instants. Spatiotemporal dynamics can be leveraged so that a small number of vertices suffices to achieve accurate reconstruction. The present paper broadens the existing kernel-based graph-function reconstruction framework to handle time-evolving functions over (possibly dynamic) graphs. The proposed approach introduces the novel notion of graph extension to enable kernel-based estimators over time and space. Numerical tests with real data corroborate that judiciously capturing time-space dynamics markedly improves reconstruction performance.",

keywords = "Graph signal reconstruction, graph extension, kernel ridge regression, space-time kernels",

author = "Ioannidis, {Vassilis N.} and Daniel Romero and Giannakis, {Georgios B.}",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016 ; Conference date: 06-11-2016 Through 09-11-2016",

year = "2017",

month = mar,

day = "1",

doi = "10.1109/ACSSC.2016.7869700",

language = "English (US)",

series = "Conference Record - Asilomar Conference on Signals, Systems and Computers",

publisher = "IEEE Computer Society",

pages = "1829--1833",

editor = "Matthews, {Michael B.}",

booktitle = "Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016",

}

TY - GEN

T1 - Kernel-based reconstruction of space-time functions via extended graphs

AU - Ioannidis, Vassilis N.

AU - Romero, Daniel

AU - Giannakis, Georgios B.

PY - 2017/3/1

Y1 - 2017/3/1

N2 - Signals evolving over graphs emerge naturally in a number of applications related to network science. A frequently encountered challenge pertains to reconstructing such signals given their values on subsets of vertices at possibly different time instants. Spatiotemporal dynamics can be leveraged so that a small number of vertices suffices to achieve accurate reconstruction. The present paper broadens the existing kernel-based graph-function reconstruction framework to handle time-evolving functions over (possibly dynamic) graphs. The proposed approach introduces the novel notion of graph extension to enable kernel-based estimators over time and space. Numerical tests with real data corroborate that judiciously capturing time-space dynamics markedly improves reconstruction performance.

AB - Signals evolving over graphs emerge naturally in a number of applications related to network science. A frequently encountered challenge pertains to reconstructing such signals given their values on subsets of vertices at possibly different time instants. Spatiotemporal dynamics can be leveraged so that a small number of vertices suffices to achieve accurate reconstruction. The present paper broadens the existing kernel-based graph-function reconstruction framework to handle time-evolving functions over (possibly dynamic) graphs. The proposed approach introduces the novel notion of graph extension to enable kernel-based estimators over time and space. Numerical tests with real data corroborate that judiciously capturing time-space dynamics markedly improves reconstruction performance.

KW - Graph signal reconstruction

KW - graph extension

KW - kernel ridge regression

KW - space-time kernels

UR - http://www.scopus.com/inward/record.url?scp=85016306331&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016306331&partnerID=8YFLogxK

U2 - 10.1109/ACSSC.2016.7869700

DO - 10.1109/ACSSC.2016.7869700

M3 - Conference contribution

AN - SCOPUS:85016306331

T3 - Conference Record - Asilomar Conference on Signals, Systems and Computers

SP - 1829

EP - 1833

BT - Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016

A2 - Matthews, Michael B.

PB - IEEE Computer Society

T2 - 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016

Y2 - 6 November 2016 through 9 November 2016

ER -

Kernel-based reconstruction of space-time functions via extended graphs

Abstract

Publication series

Other

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this