Bayesian Estimation of Graph Signals

We consider the problem of recovering random graph signals from nonlinear measurements. For this setting, closed-form Bayesian estimators are usually intractable and even numerical evaluation may be difficult to compute for large networks. In this paper, we propose a graph signal processing (GSP) fr...

Full description

Saved in:
Bibliographic Details
Published inIEEE transactions on signal processing Vol. 70; pp. 2207 - 2223
Main Authors Kroizer, Ariel, Routtenberg, Tirza, Eldar, Yonina C.
Format Journal Article
LanguageEnglish
Published New York IEEE 2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Online AccessGet full text
ISSN1053-587X
1941-0476
DOI10.1109/TSP.2022.3159393

Cover

Abstract We consider the problem of recovering random graph signals from nonlinear measurements. For this setting, closed-form Bayesian estimators are usually intractable and even numerical evaluation may be difficult to compute for large networks. In this paper, we propose a graph signal processing (GSP) framework for random graph signal recovery that utilizes information on the structure behind the data. First, we develop the GSP-linear minimum mean-squared-error (GSP-LMMSE) estimator, which minimizes the mean-squared-error (MSE) among estimators that are represented as an output of a graph filter. The GSP-LMMSE estimator is based on diagonal covariance matrices in the graph frequency domain, and thus, has reduced complexity compared with the LMMSE estimator. This property is especially important when using the sample-mean estimators that are based on a training dataset. We then state conditions under which the low-complexity GSP-LMMSE estimator coincides with the optimal LMMSE estimator. Next, we develop an approximate parametrization of the GSP-LMMSE estimator by graph filters. We present three implementations of the parametric GSP-LMMSE estimator for typical graph filters. These parametric graph filters are more robust to outliers and to network topology changes. In our simulations, we evaluate the performance of the proposed GSP-LMMSE estimators for the problem of state estimation in power systems, which can be interpreted as a graph signal recovery task. We show that the proposed sample-GSP estimators outperform the sample-LMMSE estimator for a limited training dataset and that the parametric GSP-LMMSE estimators are more robust to topology changes in the form of adding/removing vertices/edges.
AbstractList We consider the problem of recovering random graph signals from nonlinear measurements. For this setting, closed-form Bayesian estimators are usually intractable and even numerical evaluation may be difficult to compute for large networks. In this paper, we propose a graph signal processing (GSP) framework for random graph signal recovery that utilizes information on the structure behind the data. First, we develop the GSP-linear minimum mean-squared-error (GSP-LMMSE) estimator, which minimizes the mean-squared-error (MSE) among estimators that are represented as an output of a graph filter. The GSP-LMMSE estimator is based on diagonal covariance matrices in the graph frequency domain, and thus, has reduced complexity compared with the LMMSE estimator. This property is especially important when using the sample-mean estimators that are based on a training dataset. We then state conditions under which the low-complexity GSP-LMMSE estimator coincides with the optimal LMMSE estimator. Next, we develop an approximate parametrization of the GSP-LMMSE estimator by graph filters. We present three implementations of the parametric GSP-LMMSE estimator for typical graph filters. These parametric graph filters are more robust to outliers and to network topology changes. In our simulations, we evaluate the performance of the proposed GSP-LMMSE estimators for the problem of state estimation in power systems, which can be interpreted as a graph signal recovery task. We show that the proposed sample-GSP estimators outperform the sample-LMMSE estimator for a limited training dataset and that the parametric GSP-LMMSE estimators are more robust to topology changes in the form of adding/removing vertices/edges.
Author Eldar, Yonina C.
Routtenberg, Tirza
Kroizer, Ariel
Author_xml – sequence: 1
  givenname: Ariel
  surname: Kroizer
  fullname: Kroizer, Ariel
  email: arielkro@post.bgu.ac.il
  organization: School of Electrical and Computer Engineering, Ben-Gurion University of the Negev, Beer Sheva, Israel
– sequence: 2
  givenname: Tirza
  orcidid: 0000-0002-7238-7764
  surname: Routtenberg
  fullname: Routtenberg, Tirza
  email: tirzar@bgu.ac.il
  organization: School of Electrical and Computer Engineering, Ben-Gurion University of the Negev, Beer Sheva, Israel
– sequence: 3
  givenname: Yonina C.
  surname: Eldar
  fullname: Eldar, Yonina C.
  email: yonina@weizmann.ac.il
  organization: Faculty of Mathematics and Computer Science, Weizmann Institute of Science, Rehovot, Israel
BookMark eNp9kEFLAzEQRoNUsK3eBS8Let2ayWSTzVFLrUJBoRW8hWyaaErdrcn20H_v1hYPHjzNHL43fPMGpFc3tSPkEugIgKrbxfxlxChjI4RCocIT0gfFIadcil630wLzopRvZ2SQ0opS4FyJPrm5NzuXgqmzSWrDp2lDU2eNz6bRbD6yeXivzTqdk1PfDXdxnEPy-jBZjB_z2fP0aXw3yy1T0OZcVdSCZ5ZVVgJXwLxSVeG5MpaDkBVlwlnBlwJLjmIpJVpvSutFYUqJFIfk-nB3E5uvrUutXjXbuG-gmRAoOEqhupQ4pGxsUorOaxvan-JtNGGtgeq9Ed0Z0Xsj-mikA-kfcBO7l-PuP-TqgATn3G9cSSywLPEbp9hrdg
CODEN ITPRED
CitedBy_id crossref_primary_10_1109_TSP_2024_3435935
crossref_primary_10_1109_LSP_2024_3514800
crossref_primary_10_1109_TSIPN_2024_3375593
crossref_primary_10_1109_TSP_2024_3395021
crossref_primary_10_1016_j_automatica_2022_110796
crossref_primary_10_3390_s22239183
crossref_primary_10_1109_TSP_2023_3256536
crossref_primary_10_1109_TSP_2024_3510434
crossref_primary_10_1109_TII_2024_3369715
crossref_primary_10_1109_LSP_2023_3298280
crossref_primary_10_1109_TSP_2023_3340009
crossref_primary_10_1109_TSP_2024_3439554
crossref_primary_10_1109_TSP_2023_3284364
crossref_primary_10_1109_TSP_2024_3495225
Cites_doi 10.1109/TSP.2019.2901356
10.1002/0471221104
10.1016/j.sigpro.2021.108216
10.1109/TSP.2014.2321121
10.1109/TSP.2010.2053029
10.1109/TSIPN.2018.2854627
10.1007/s00440-021-01092-y
10.1017/CBO9781139020411
10.1109/MSP.2012.2235192
10.1201/9780203913673
10.1109/TSIPN.2020.2964214
10.1109/TSIPN.2021.3107628
10.1109/JPROC.2018.2820126
10.1016/j.patcog.2008.05.007
10.1109/TSP.2016.2602809
10.1109/JPROC.2018.2804318
10.1016/j.orl.2019.08.009
10.1109/TSP.2018.2876313
10.1109/TSP.2014.2313528
10.1109/ICASSP.2014.6854325
10.1109/ICASSP39728.2021.9414909
10.1109/TSP.2017.2703660
10.1109/JSTSP.2016.2600859
10.1109/TSP.2015.2441042
10.1093/acprof:oso/9780199206650.001.0001
10.1109/MSP.2020.3014590
10.1109/TSP.2019.2940122
10.1109/TSP.2014.2329420
10.1016/S0047-259X(03)00096-4
10.1109/JSYST.2019.2927469
10.1109/ICASSP.2013.6638849
10.1109/MSP.2020.3016143
10.1109/TSP.2017.2706179
10.1109/TSP.2015.2507546
10.1109/JPROC.2021.3055400
10.1109/TSP.2016.2614793
10.1109/TKDE.2007.46
10.1109/CDC.2005.1583238
10.1109/MSP.2020.3016908
10.1109/TSP.2015.2469645
10.1109/GlobalSIP45357.2019.8969536
10.1109/TSP.2004.828931
10.1109/TIT.2014.2354403
10.1109/DSW.2019.8755601
10.1109/LSP.2014.2387204
10.1137/S0895479897330182
10.1109/TSP.2020.3026980
10.1109/TSP.2021.3119430
10.1109/TSP.2021.3054523
10.1109/TSP.2017.2690388
10.1109/TSP.2019.2932882
10.1109/TSP.2009.2021500
10.1109/TSP.2016.2634543
10.1109/ICDM.2006.18
10.1109/TSP.2012.2202112
10.1109/GlobalSIP.2014.7032244
10.1109/VETEC.1996.501446
10.1109/TSIPN.2017.2710619
10.1109/TSP.2020.2982325
10.3390/w9080593
10.1109/TSP.2021.3054995
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
DBID 97E
RIA
RIE
AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
DOI 10.1109/TSP.2022.3159393
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle CrossRef
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
DatabaseTitleList
Technology Research Database
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1941-0476
EndPage 2223
ExternalDocumentID 10_1109_TSP_2022_3159393
9735388
Genre orig-research
GrantInformation_xml – fundername: Israeli Ministry of National Infrastructure, Energy and Water Resources
GroupedDBID -~X
.DC
0R~
29I
3EH
4.4
53G
5GY
5VS
6IK
85S
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABFSI
ABQJQ
ABVLG
ACGFO
ACIWK
ACKIV
ACNCT
AENEX
AETIX
AGQYO
AGSQL
AHBIQ
AI.
AIBXA
AJQPL
AKJIK
AKQYR
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
E.L
EBS
EJD
F5P
HZ~
H~9
ICLAB
IFIPE
IFJZH
IPLJI
JAVBF
LAI
MS~
O9-
OCL
P2P
RIA
RIE
RNS
TAE
TN5
VH1
AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c291t-49b0c1f2c2bc714912f99b5f49ac4167b026ec64d638436d773cfa8cf65a87303
IEDL.DBID RIE
ISSN 1053-587X
IngestDate Mon Jun 30 10:12:33 EDT 2025
Thu Apr 24 22:55:11 EDT 2025
Wed Oct 01 03:34:38 EDT 2025
Wed Aug 27 02:37:56 EDT 2025
IsPeerReviewed true
IsScholarly true
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c291t-49b0c1f2c2bc714912f99b5f49ac4167b026ec64d638436d773cfa8cf65a87303
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-7238-7764
PQID 2663643769
PQPubID 85478
PageCount 17
ParticipantIDs crossref_citationtrail_10_1109_TSP_2022_3159393
proquest_journals_2663643769
ieee_primary_9735388
crossref_primary_10_1109_TSP_2022_3159393
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate 20220000
2022-00-00
20220101
PublicationDateYYYYMMDD 2022-01-01
PublicationDate_xml – year: 2022
  text: 20220000
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on signal processing
PublicationTitleAbbrev TSP
PublicationYear 2022
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref13
ref57
ref12
ref56
ref15
ref59
ref14
ref58
ref53
ref52
ref11
ref55
ref10
ref54
ref17
ref16
ref19
ref18
Hayes (ref43) 1996
ref51
ref46
ref45
ref48
ref42
ref41
ref44
Kenlay (ref64) 2021
ref49
ref8
ref7
ref9
ref4
ref3
ref6
ref5
Kay (ref50) 1993; 1
ref40
ref35
ref34
ref37
ref36
ref31
ref30
ref33
ref32
ref2
ref1
ref38
Dabush (ref47) 2021
ref24
ref23
ref67
ref26
ref25
ref20
ref63
ref22
ref66
ref21
ref65
Newman (ref39) 2010
ref28
ref27
Mohar (ref61) 1991
ref29
ref60
ref62
References_xml – ident: ref15
  doi: 10.1109/TSP.2019.2901356
– ident: ref52
  doi: 10.1002/0471221104
– ident: ref67
  article-title: Power systems test case archive
– ident: ref63
  doi: 10.1016/j.sigpro.2021.108216
– year: 2021
  ident: ref47
  article-title: State estimation in unobservable power systems via graph signal processing tools
– ident: ref28
  doi: 10.1109/TSP.2014.2321121
– ident: ref54
  doi: 10.1109/TSP.2010.2053029
– ident: ref29
  doi: 10.1109/TSIPN.2018.2854627
– ident: ref49
  doi: 10.1007/s00440-021-01092-y
– ident: ref60
  doi: 10.1017/CBO9781139020411
– ident: ref4
  doi: 10.1109/MSP.2012.2235192
– ident: ref18
  doi: 10.1201/9780203913673
– ident: ref36
  doi: 10.1109/TSIPN.2020.2964214
– ident: ref16
  doi: 10.1109/TSIPN.2021.3107628
– ident: ref3
  doi: 10.1109/JPROC.2018.2820126
– ident: ref26
  doi: 10.1016/j.patcog.2008.05.007
– ident: ref57
  doi: 10.1109/TSP.2016.2602809
– ident: ref11
  doi: 10.1109/JPROC.2018.2804318
– ident: ref17
  doi: 10.1016/j.orl.2019.08.009
– volume: 1
  volume-title: Fundamentals of Statistical Signal Processing: Estimation Theory.
  year: 1993
  ident: ref50
– ident: ref13
  doi: 10.1109/TSP.2018.2876313
– ident: ref27
  doi: 10.1109/TSP.2014.2313528
– ident: ref7
  doi: 10.1109/ICASSP.2014.6854325
– ident: ref37
  doi: 10.1109/ICASSP39728.2021.9414909
– ident: ref30
  doi: 10.1109/TSP.2017.2703660
– ident: ref1
  doi: 10.1109/JSTSP.2016.2600859
– ident: ref31
  doi: 10.1109/TSP.2015.2441042
– volume-title: Networks: An Introduction
  year: 2010
  ident: ref39
  doi: 10.1093/acprof:oso/9780199206650.001.0001
– ident: ref59
  doi: 10.1109/MSP.2020.3014590
– ident: ref12
  doi: 10.1109/TSP.2019.2940122
– ident: ref51
  doi: 10.1109/TSP.2014.2329420
– ident: ref55
  doi: 10.1016/S0047-259X(03)00096-4
– ident: ref14
  doi: 10.1109/JSYST.2019.2927469
– ident: ref40
  doi: 10.1109/ICASSP.2013.6638849
– ident: ref34
  doi: 10.1109/MSP.2020.3016143
– ident: ref20
  doi: 10.1109/TSP.2017.2706179
– ident: ref8
  doi: 10.1109/TSP.2015.2507546
– ident: ref33
  doi: 10.1109/JPROC.2021.3055400
– ident: ref5
  doi: 10.1109/TSP.2016.2614793
– ident: ref41
  doi: 10.1109/TKDE.2007.46
– ident: ref2
  doi: 10.1109/CDC.2005.1583238
– ident: ref6
  doi: 10.1109/MSP.2020.3016908
– ident: ref45
  doi: 10.1109/TSP.2015.2469645
– ident: ref38
  doi: 10.1109/GlobalSIP45357.2019.8969536
– ident: ref22
  doi: 10.1109/TSP.2004.828931
– volume-title: Statistical Digital Signal Processing and Modeling
  year: 1996
  ident: ref43
– ident: ref19
  doi: 10.1109/TIT.2014.2354403
– ident: ref58
  doi: 10.1109/DSW.2019.8755601
– ident: ref44
  doi: 10.1109/LSP.2014.2387204
– ident: ref56
  doi: 10.1137/S0895479897330182
– ident: ref62
  doi: 10.1109/TSP.2020.3026980
– ident: ref21
  doi: 10.1109/TSP.2021.3119430
– ident: ref10
  doi: 10.1109/TSP.2021.3054523
– ident: ref32
  doi: 10.1109/TSP.2017.2690388
– ident: ref66
  doi: 10.1109/TSP.2019.2932882
– ident: ref53
  doi: 10.1109/TSP.2009.2021500
– ident: ref35
  doi: 10.1109/TSP.2016.2634543
– ident: ref42
  doi: 10.1109/ICDM.2006.18
– start-page: 871
  year: 1991
  ident: ref61
  article-title: The Laplacian spectrum of graphs
  publication-title: Graph Theory, Combinatorics., Appl.
– ident: ref24
  doi: 10.1109/TSP.2012.2202112
– ident: ref25
  doi: 10.1109/GlobalSIP.2014.7032244
– start-page: 5388
  volume-title: Proc. Int. Conf. Mach. Learn.
  year: 2021
  ident: ref64
  article-title: Interpretable stability bounds for spectral graph filters
– ident: ref23
  doi: 10.1109/VETEC.1996.501446
– ident: ref65
  doi: 10.1109/TSIPN.2017.2710619
– ident: ref9
  doi: 10.1109/TSP.2020.2982325
– ident: ref48
  doi: 10.3390/w9080593
– ident: ref46
  doi: 10.1109/TSP.2021.3054995
SSID ssj0014496
Score 2.547351
Snippet We consider the problem of recovering random graph signals from nonlinear measurements. For this setting, closed-form Bayesian estimators are usually...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 2207
SubjectTerms Apexes
Bayesian analysis
Bayesian estimation
Complexity
Covariance matrices
Covariance matrix
Datasets
Estimation
Estimators
Filtering theory
graph filters
Graph signal processing (GSP)
graph signal recovery
Graph theory
Graphical representations
GSP-LMMSE estimator
Information filters
linear minimum mean-squared-error (LMMSE) estimator
Maximum likelihood detection
Network topologies
Nonlinear filters
Outliers (statistics)
Parameterization
Performance evaluation
Robustness (mathematics)
sample-LMMSE estimator
Signal processing
Signal reconstruction
State estimation
Training
Title Bayesian Estimation of Graph Signals
URI https://ieeexplore.ieee.org/document/9735388
https://www.proquest.com/docview/2663643769
Volume 70
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 1941-0476
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0014496
  issn: 1053-587X
  databaseCode: RIE
  dateStart: 19910101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LSwMxEB7anvTgq4rVKnvoRXDb3SSbbI4qrUWoCG2htyXJJiJKK7o96K832Re-EG97SEL4ktl8k8l8A9ATaaiQMtRX3BifxJr7UkWRbwgOdEg1odLlO09u6XhObhbRogHndS6M1jp_fKb77jOP5acrtXZXZQPOsLXPuAlNFtMiV6uOGBCS1-KydAH7UcwWVUgy4IPZ9M46gghZ_zTimOMvR1BeU-XHjzg_XUbbMKnmVTwqeeyvM9lX798kG_878R3YKmmmd1Hsi11o6OUebH4SH2xD71K8aZdC6Q2tmRcZjN7KeNdOwtqbPtw7ZeV9mI-Gs6uxX9ZM8BXiYeYTLgMVGqSQVMx6PyEynMvIEC6U5V5MWp9LK0pSa3cE05QxrIyI7WpFIrbWjg-gtVwt9SF4nKY0DpAJkTREMCY1FSpVUmthSVAadWBQwZioUlDc1bV4SnLHIuCJBT5xwCcl8B04q3s8F2Iaf7RtOxzrdiWEHehWK5WU1vaaWJKBXQCS8qPfex3Dhhu7uDrpQit7WesTSyYyeZrvog8cw8Tl
linkProvider IEEE
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV07T8MwED5BGYCBV0EUCmTogkTaxK_EI6CWAm2F1FbqFsWOjRCoRZAO8Oux86h4CbFlsGXrsy_-zuf7DqARJ75EUjNXcq1dEiruCkmpqwn2lM8UYcLmO_cHrDsmNxM6WYKzRS6MUip7fKaa9jOL5SczObdXZS0eYGOf4TKsUEIIzbO1FjEDQrJqXIYwYJeGwaQMSnq8NRreGVcQIeOhUo45_nIIZVVVfvyKs_Olswn9cmb5s5LH5jwVTfn-TbTxv1Pfgo2CaDrn-c7YhiU13YH1T_KDVWhcxG_KJlE6bWPoeQ6jM9POlRWxdoYP91ZbeRfGnfbosusWVRNcibifuoQLT_oaSSRkYPwfH2nOBdWEx9Kwr0AYr0tJRhJjeQSzJAiw1HFo1ovGobF3vAeV6Wyq9sHhLGGhh7SPhCZxEAjFYplIoVRsaFBCa9AqYYxkISluK1s8RZlr4fHIAB9Z4KMC-BqcLno853Iaf7StWhwX7QoIa1AvVyoq7O01MjQD2xAk4we_9zqB1e6o34t614PbQ1iz4-QXKXWopC9zdWSoRSqOsx31AZy4yDI
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Bayesian+Estimation+of+Graph+Signals&rft.jtitle=IEEE+transactions+on+signal+processing&rft.au=Kroizer%2C+Ariel&rft.au=Routtenberg%2C+Tirza&rft.au=Eldar%2C+Yonina+C.&rft.date=2022&rft.issn=1053-587X&rft.eissn=1941-0476&rft.volume=70&rft.spage=2207&rft.epage=2223&rft_id=info:doi/10.1109%2FTSP.2022.3159393&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TSP_2022_3159393
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1053-587X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1053-587X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1053-587X&client=summon