Signal Recovery on Graphs

Variation Minimization

Siheng Chen, Aliaksei Sandryhaila, Jose M.F. Moura, Jelena Kovacevic

Research output: Contribution to journalArticle

Abstract

We consider the problem of signal recovery on graphs. Graphs model data with complex structure as signals on a graph. Graph signal recovery recovers one or multiple smooth graph signals from noisy, corrupted, or incomplete measurements. We formulate graph signal recovery as an optimization problem, for which we provide a general solution through the alternating direction methods of multipliers. We show how signal inpainting, matrix completion, robust principal component analysis, and anomaly detection all relate to graph signal recovery and provide corresponding specific solutions and theoretical analysis. We validate the proposed methods on real-world recovery problems, including online blog classification, bridge condition identification, temperature estimation, recommender system for jokes, and expert opinion combination of online blog classification.

Original languageEnglish (US)
Article number7117446
Pages (from-to)4609-4624
Number of pages16
JournalIEEE Transactions on Signal Processing
Volume63
Issue number17
DOIs
StatePublished - Sep 1 2015

Fingerprint

Recovery
Blogs
Recommender systems
Principal component analysis
Temperature

Keywords

  • Matrix completion
  • Semi-supervised learning
  • Signal processing on graphs
  • Signal recovery

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Signal Recovery on Graphs : Variation Minimization. / Chen, Siheng; Sandryhaila, Aliaksei; Moura, Jose M.F.; Kovacevic, Jelena.

In: IEEE Transactions on Signal Processing, Vol. 63, No. 17, 7117446, 01.09.2015, p. 4609-4624.

Research output: Contribution to journalArticle

Chen, Siheng ; Sandryhaila, Aliaksei ; Moura, Jose M.F. ; Kovacevic, Jelena. / Signal Recovery on Graphs : Variation Minimization. In: IEEE Transactions on Signal Processing. 2015 ; Vol. 63, No. 17. pp. 4609-4624.
@article{1e06f7016a8843048d2f34db851ace2a,
title = "Signal Recovery on Graphs: Variation Minimization",
abstract = "We consider the problem of signal recovery on graphs. Graphs model data with complex structure as signals on a graph. Graph signal recovery recovers one or multiple smooth graph signals from noisy, corrupted, or incomplete measurements. We formulate graph signal recovery as an optimization problem, for which we provide a general solution through the alternating direction methods of multipliers. We show how signal inpainting, matrix completion, robust principal component analysis, and anomaly detection all relate to graph signal recovery and provide corresponding specific solutions and theoretical analysis. We validate the proposed methods on real-world recovery problems, including online blog classification, bridge condition identification, temperature estimation, recommender system for jokes, and expert opinion combination of online blog classification.",
keywords = "Matrix completion, Semi-supervised learning, Signal processing on graphs, Signal recovery",
author = "Siheng Chen and Aliaksei Sandryhaila and Moura, {Jose M.F.} and Jelena Kovacevic",
year = "2015",
month = "9",
day = "1",
doi = "10.1109/TSP.2015.2441042",
language = "English (US)",
volume = "63",
pages = "4609--4624",
journal = "IEEE Transactions on Signal Processing",
issn = "1053-587X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "17",

}

TY - JOUR

T1 - Signal Recovery on Graphs

T2 - Variation Minimization

AU - Chen, Siheng

AU - Sandryhaila, Aliaksei

AU - Moura, Jose M.F.

AU - Kovacevic, Jelena

PY - 2015/9/1

Y1 - 2015/9/1

N2 - We consider the problem of signal recovery on graphs. Graphs model data with complex structure as signals on a graph. Graph signal recovery recovers one or multiple smooth graph signals from noisy, corrupted, or incomplete measurements. We formulate graph signal recovery as an optimization problem, for which we provide a general solution through the alternating direction methods of multipliers. We show how signal inpainting, matrix completion, robust principal component analysis, and anomaly detection all relate to graph signal recovery and provide corresponding specific solutions and theoretical analysis. We validate the proposed methods on real-world recovery problems, including online blog classification, bridge condition identification, temperature estimation, recommender system for jokes, and expert opinion combination of online blog classification.

AB - We consider the problem of signal recovery on graphs. Graphs model data with complex structure as signals on a graph. Graph signal recovery recovers one or multiple smooth graph signals from noisy, corrupted, or incomplete measurements. We formulate graph signal recovery as an optimization problem, for which we provide a general solution through the alternating direction methods of multipliers. We show how signal inpainting, matrix completion, robust principal component analysis, and anomaly detection all relate to graph signal recovery and provide corresponding specific solutions and theoretical analysis. We validate the proposed methods on real-world recovery problems, including online blog classification, bridge condition identification, temperature estimation, recommender system for jokes, and expert opinion combination of online blog classification.

KW - Matrix completion

KW - Semi-supervised learning

KW - Signal processing on graphs

KW - Signal recovery

UR - http://www.scopus.com/inward/record.url?scp=84939163707&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84939163707&partnerID=8YFLogxK

U2 - 10.1109/TSP.2015.2441042

DO - 10.1109/TSP.2015.2441042

M3 - Article

VL - 63

SP - 4609

EP - 4624

JO - IEEE Transactions on Signal Processing

JF - IEEE Transactions on Signal Processing

SN - 1053-587X

IS - 17

M1 - 7117446

ER -