Distributed algorithm for graph signal inpainting

Siheng Chen, Aliaksei Sandryhaila, Jelena Kovacevic

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present a distributed and decentralized algorithm for graph signal inpainting. The previous work obtained a closed-form solution with matrix inversion. In this paper, we ease the computation by using a distributed algorithm, which solves graph signal inpainting by restricting each node to communicate only with its local nodes. We show that the solution of the distributed algorithm converges to the closed-form solution with the corresponding convergence speed. Experiments on online blog classification and temperature prediction suggest that the convergence speed of the proposed distributed algorithm is competitive with that of the centralized algorithm, especially when a graph tends to be regular. Since a distributed algorithm does not require to collect data to a center, it is more practical and efficient.

Original languageEnglish (US)
Title of host publication2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3731-3735
Number of pages5
Volume2015-August
ISBN (Electronic)9781467369978
DOIs
StatePublished - Jan 1 2015
Event40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Brisbane, Australia
Duration: Apr 19 2014Apr 24 2014

Other

Other40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015
CountryAustralia
CityBrisbane
Period4/19/144/24/14

Fingerprint

Parallel algorithms
Blogs
Experiments
Temperature

Keywords

  • distributed computing
  • graph signal inpainting
  • Signal processing on graphs

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Chen, S., Sandryhaila, A., & Kovacevic, J. (2015). Distributed algorithm for graph signal inpainting. In 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings (Vol. 2015-August, pp. 3731-3735). [7178668] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2015.7178668

Distributed algorithm for graph signal inpainting. / Chen, Siheng; Sandryhaila, Aliaksei; Kovacevic, Jelena.

2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings. Vol. 2015-August Institute of Electrical and Electronics Engineers Inc., 2015. p. 3731-3735 7178668.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chen, S, Sandryhaila, A & Kovacevic, J 2015, Distributed algorithm for graph signal inpainting. in 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings. vol. 2015-August, 7178668, Institute of Electrical and Electronics Engineers Inc., pp. 3731-3735, 40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015, Brisbane, Australia, 4/19/14. https://doi.org/10.1109/ICASSP.2015.7178668
Chen S, Sandryhaila A, Kovacevic J. Distributed algorithm for graph signal inpainting. In 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings. Vol. 2015-August. Institute of Electrical and Electronics Engineers Inc. 2015. p. 3731-3735. 7178668 https://doi.org/10.1109/ICASSP.2015.7178668
Chen, Siheng ; Sandryhaila, Aliaksei ; Kovacevic, Jelena. / Distributed algorithm for graph signal inpainting. 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings. Vol. 2015-August Institute of Electrical and Electronics Engineers Inc., 2015. pp. 3731-3735
@inproceedings{3ef23f3e0cd94b199a2dae605e518741,
title = "Distributed algorithm for graph signal inpainting",
abstract = "We present a distributed and decentralized algorithm for graph signal inpainting. The previous work obtained a closed-form solution with matrix inversion. In this paper, we ease the computation by using a distributed algorithm, which solves graph signal inpainting by restricting each node to communicate only with its local nodes. We show that the solution of the distributed algorithm converges to the closed-form solution with the corresponding convergence speed. Experiments on online blog classification and temperature prediction suggest that the convergence speed of the proposed distributed algorithm is competitive with that of the centralized algorithm, especially when a graph tends to be regular. Since a distributed algorithm does not require to collect data to a center, it is more practical and efficient.",
keywords = "distributed computing, graph signal inpainting, Signal processing on graphs",
author = "Siheng Chen and Aliaksei Sandryhaila and Jelena Kovacevic",
year = "2015",
month = "1",
day = "1",
doi = "10.1109/ICASSP.2015.7178668",
language = "English (US)",
volume = "2015-August",
pages = "3731--3735",
booktitle = "2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Distributed algorithm for graph signal inpainting

AU - Chen, Siheng

AU - Sandryhaila, Aliaksei

AU - Kovacevic, Jelena

PY - 2015/1/1

Y1 - 2015/1/1

N2 - We present a distributed and decentralized algorithm for graph signal inpainting. The previous work obtained a closed-form solution with matrix inversion. In this paper, we ease the computation by using a distributed algorithm, which solves graph signal inpainting by restricting each node to communicate only with its local nodes. We show that the solution of the distributed algorithm converges to the closed-form solution with the corresponding convergence speed. Experiments on online blog classification and temperature prediction suggest that the convergence speed of the proposed distributed algorithm is competitive with that of the centralized algorithm, especially when a graph tends to be regular. Since a distributed algorithm does not require to collect data to a center, it is more practical and efficient.

AB - We present a distributed and decentralized algorithm for graph signal inpainting. The previous work obtained a closed-form solution with matrix inversion. In this paper, we ease the computation by using a distributed algorithm, which solves graph signal inpainting by restricting each node to communicate only with its local nodes. We show that the solution of the distributed algorithm converges to the closed-form solution with the corresponding convergence speed. Experiments on online blog classification and temperature prediction suggest that the convergence speed of the proposed distributed algorithm is competitive with that of the centralized algorithm, especially when a graph tends to be regular. Since a distributed algorithm does not require to collect data to a center, it is more practical and efficient.

KW - distributed computing

KW - graph signal inpainting

KW - Signal processing on graphs

UR - http://www.scopus.com/inward/record.url?scp=84946061803&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84946061803&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2015.7178668

DO - 10.1109/ICASSP.2015.7178668

M3 - Conference contribution

VL - 2015-August

SP - 3731

EP - 3735

BT - 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -