Graph Regularized Autoencoder and its Application in Unsupervised Anomaly Detection

Dimensionality reduction is a crucial first step for many unsupervised learning tasks including anomaly detection and clustering. Autoencoder is a popular mechanism to accomplish dimensionality reduction. In order to make dimensionality reduction effective for high-dimensional data embedding nonline...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence Jg. 44; H. 8; S. 4110 - 4124
Hauptverfasser:	Ahmed, Imtiaz, Galoppo, Travis, Hu, Xia, Ding, Yu
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	United States IEEE 01.08.2022 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Algorithms Anomalies Anomaly detection Autoencoder Clustering Cognitive tasks Data points Datasets Decoding Dimensionality reduction Embedding Euclidean geometry Generative adversarial networks Graph theory Laplace equations Manifolds Measurement minimum spanning tree Neural networks nonlinear embedding Performance enhancement Reduction unsupervised learning
ISSN:	0162-8828, 1939-3539, 2160-9292, 1939-3539
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	Dimensionality reduction is a crucial first step for many unsupervised learning tasks including anomaly detection and clustering. Autoencoder is a popular mechanism to accomplish dimensionality reduction. In order to make dimensionality reduction effective for high-dimensional data embedding nonlinear low-dimensional manifold, it is understood that some sort of geodesic distance metric should be used to discriminate the data samples. Inspired by the success of geodesic distance approximators such as ISOMAP, we propose to use a minimum spanning tree (MST), a graph-based algorithm, to approximate the local neighborhood structure and generate structure-preserving distances among data points. We use this MST-based distance metric to replace the euclidean distance metric in the embedding function of autoencoders and develop a new graph regularized autoencoder, which outperforms a wide range of alternative methods over 20 benchmark anomaly detection datasets. We further incorporate the MST regularizer into two generative adversarial networks and find that using the MST regularizer improves the performance of anomaly detection substantially for both generative adversarial networks. We also test our MST regularized autoencoder on two datasets in a clustering application and witness its superior performance as well.
AbstractList	Dimensionality reduction is a crucial first step for many unsupervised learning tasks including anomaly detection and clustering. Autoencoder is a popular mechanism to accomplish dimensionality reduction. In order to make dimensionality reduction effective for high-dimensional data embedding nonlinear low-dimensional manifold, it is understood that some sort of geodesic distance metric should be used to discriminate the data samples. Inspired by the success of geodesic distance approximators such as ISOMAP, we propose to use a minimum spanning tree (MST), a graph-based algorithm, to approximate the local neighborhood structure and generate structure-preserving distances among data points. We use this MST-based distance metric to replace the euclidean distance metric in the embedding function of autoencoders and develop a new graph regularized autoencoder, which outperforms a wide range of alternative methods over 20 benchmark anomaly detection datasets. We further incorporate the MST regularizer into two generative adversarial networks and find that using the MST regularizer improves the performance of anomaly detection substantially for both generative adversarial networks. We also test our MST regularized autoencoder on two datasets in a clustering application and witness its superior performance as well. Dimensionality reduction is a crucial first step for many unsupervised learning tasks including anomaly detection and clustering. Autoencoder is a popular mechanism to accomplish dimensionality reduction. In order to make dimensionality reduction effective for high-dimensional data embedding nonlinear low-dimensional manifold, it is understood that some sort of geodesic distance metric should be used to discriminate the data samples. Inspired by the success of geodesic distance approximators such as ISOMAP, we propose to use a minimum spanning tree (MST), a graph-based algorithm, to approximate the local neighborhood structure and generate structure-preserving distances among data points. We use this MST-based distance metric to replace the euclidean distance metric in the embedding function of autoencoders and develop a new graph regularized autoencoder, which outperforms a wide range of alternative methods over 20 benchmark anomaly detection datasets. We further incorporate the MST regularizer into two generative adversarial networks and find that using the MST regularizer improves the performance of anomaly detection substantially for both generative adversarial networks. We also test our MST regularized autoencoder on two datasets in a clustering application and witness its superior performance as well.Dimensionality reduction is a crucial first step for many unsupervised learning tasks including anomaly detection and clustering. Autoencoder is a popular mechanism to accomplish dimensionality reduction. In order to make dimensionality reduction effective for high-dimensional data embedding nonlinear low-dimensional manifold, it is understood that some sort of geodesic distance metric should be used to discriminate the data samples. Inspired by the success of geodesic distance approximators such as ISOMAP, we propose to use a minimum spanning tree (MST), a graph-based algorithm, to approximate the local neighborhood structure and generate structure-preserving distances among data points. We use this MST-based distance metric to replace the euclidean distance metric in the embedding function of autoencoders and develop a new graph regularized autoencoder, which outperforms a wide range of alternative methods over 20 benchmark anomaly detection datasets. We further incorporate the MST regularizer into two generative adversarial networks and find that using the MST regularizer improves the performance of anomaly detection substantially for both generative adversarial networks. We also test our MST regularized autoencoder on two datasets in a clustering application and witness its superior performance as well.
Author	Galoppo, Travis Ahmed, Imtiaz Hu, Xia Ding, Yu
Author_xml	– sequence: 1 givenname: Imtiaz orcidid: 0000-0003-1577-7384 surname: Ahmed fullname: Ahmed, Imtiaz email: imtiazavi@tamu.edu organization: Department of Industrial & Systems Engineering, Texas A&M University, College Station, TX, USA – sequence: 2 givenname: Travis surname: Galoppo fullname: Galoppo, Travis email: travis.galoppo@baesystems.com organization: BAE Systems, Inc., Charlotte, NC, USA – sequence: 3 givenname: Xia orcidid: 0000-0003-2234-3226 surname: Hu fullname: Hu, Xia email: hu@cse.tamu.edu organization: Department of Computer Science & Engineering, Texas A&M University, College Station, TX, USA – sequence: 4 givenname: Yu orcidid: 0000-0001-6936-074X surname: Ding fullname: Ding, Yu email: yuding@tamu.edu organization: Department of Industrial & Systems Engineering, Texas A&M University, College Station, TX, USA
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/33729925$$D View this record in MEDLINE/PubMed
BookMark	eNp9kcFO3DAQhi0EKgv0BUBCkXrpJdsZe5PYxxWlgARqVeBsOd5Ja5S1UztBgqcnYRcOHHoaafR9v0bzH7BdHzwxdowwRwT17e7X8uZqzoHjXEBZIuIOm3EsIVdc8V02Ayx5LiWX--wgpQcAXBQgPrF9ISquFC9m7PYimu5v9pv-DK2J7plW2XLoA3kbVhQz41eZ61O27LrWWdO74DPns3ufho7io0sT78PatE_Zd-rJTsQR22tMm-jzdh6y-x_nd2eX-fXPi6uz5XVuhSr6vKpqgEJUpiRYNGiEbSqishC2qsXCCJRWjccLC00z7gpZy9oI0yBywLpuxCH7usntYvg3UOr12iVLbWs8hSFpXgCXUJVcjuiXD-hDGKIfr9O8lFyhkjBRp1tqqNe00l10axOf9Nu7RkBuABtDSpEabV3_-pU-GtdqBD01o1-b0VMzetvMqPIP6lv6f6WTjeSI6F1QQsJCFeIFoBuYiQ
CODEN	ITPIDJ
CitedBy_id	crossref_primary_10_1109_ACCESS_2025_3544260 crossref_primary_10_1109_TPAMI_2025_3528738 crossref_primary_10_1109_JIOT_2022_3181737 crossref_primary_10_3389_fenrg_2022_904622 crossref_primary_10_1109_TIFS_2024_3354412 crossref_primary_10_1080_0951192X_2024_2397821 crossref_primary_10_1109_TNNLS_2024_3465446 crossref_primary_10_1007_s12008_025_02407_2 crossref_primary_10_1080_24725854_2021_2024925 crossref_primary_10_1109_TIP_2024_3490894 crossref_primary_10_1109_TPAMI_2025_3566620 crossref_primary_10_1007_s10618_023_00952_6
Cites_doi	10.1002/aic.690370209 10.1109/CVPR.2013.17 10.1126/science.290.5500–2323 10.1109/ICPR.2014.272 10.1007/s10618-015-0444-8 10.1371/journal.pone.0146672 10.1109/SPW.2019.00014 10.1126/science.290.5500.2319 10.1145/2487575.2487629 10.1109/SMC.2015.513 10.1007/978-3-642-01307-2_86 10.1109/ICDM.2018.00088 10.1016/S0012-365X(00)00224-7 10.1145/342009.335388 10.1109/WACV.2012.6163005 10.1090/jams/852 10.1007/3-540-47887-6_53 10.1109/TPAMI.2010.231 10.7551/mitpress/7503.003.0147 10.1007/978-3-642-23783-6_41 10.1109/TSP.2004.831130 10.7551/mitpress/9780262033589.001.0001 10.7551/mitpress/1120.003.0080 10.1145/3097983.3098052 10.1109/ICDM.2008.17 10.1126/science.1127647 10.4135/9781412985130 10.1136/bmj.310.6973.170 10.1162/089976601750264965 10.1007/978-3-642-40994-3_14 10.1090/S0002-9939-1956-0078686-7 10.1002/j.1538-7305.1957.tb01515.x 10.1007/978-3-319-59050-9_12 10.1109/TASE.2018.2848198 10.1038/s41598-017-11873-y 10.1016/j.neucom.2015.02.023 10.1109/TIP.2016.2605010
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 ESBDL RIA RIE AAYXX CITATION NPM 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8
DOI	10.1109/TPAMI.2021.3066111
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE Xplore Open Access Journals IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef PubMed 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 MEDLINE - Academic
DatabaseTitle	CrossRef PubMed 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 MEDLINE - Academic
DatabaseTitleList	Technology Research Database PubMed MEDLINE - Academic
Database_xml	– sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE Xplore url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Computer Science
EISSN	2160-9292 1939-3539
EndPage	4124
ExternalDocumentID	33729925 10_1109_TPAMI_2021_3066111 9380495
Genre	orig-research Journal Article
GrantInformation_xml	– fundername: National Science Foundation grantid: IIS-1750074; IIS-1718840 funderid: 10.13039/501100008982 – fundername: ABB project grantid: M1801386 – fundername: National Science Foundation grantid: IIS-1849085 funderid: 10.13039/501100008982
GroupedDBID	--- -DZ -~X .DC 0R~ 29I 4.4 53G 5GY 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT AENEX AGQYO AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 E.L EBS EJD ESBDL F5P HZ~ IEDLZ IFIPE IPLJI JAVBF LAI M43 MS~ O9- OCL P2P PQQKQ RIA RIE RNS RXW TAE TN5 UHB ~02 5VS 9M8 AAYXX ABFSI ADRHT AETEA AETIX AGSQL AI. AIBXA ALLEH CITATION FA8 H~9 IBMZZ ICLAB IFJZH RNI RZB VH1 NPM 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8
ID	FETCH-LOGICAL-c395t-77b00537a6e04f1a3cf7ee653c7b34a318c98823c0ff3c758b8ba3af11201bbf3
IEDL.DBID	RIE
ISICitedReferencesCount	40
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000820521900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0162-8828 1939-3539
IngestDate	Sat Sep 27 19:24:08 EDT 2025 Sun Nov 30 04:28:29 EST 2025 Mon Jul 21 06:03:28 EDT 2025 Tue Nov 18 22:17:44 EST 2025 Sat Nov 29 05:16:00 EST 2025 Wed Aug 27 02:23:53 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	8
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c395t-77b00537a6e04f1a3cf7ee653c7b34a318c98823c0ff3c758b8ba3af11201bbf3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0001-6936-074X 0000-0003-2234-3226 0000-0003-1577-7384
OpenAccessLink	https://ieeexplore.ieee.org/document/9380495
PMID	33729925
PQID	2682919808
PQPubID	85458
PageCount	15
ParticipantIDs	ieee_primary_9380495 crossref_citationtrail_10_1109_TPAMI_2021_3066111 proquest_miscellaneous_2502807628 proquest_journals_2682919808 pubmed_primary_33729925 crossref_primary_10_1109_TPAMI_2021_3066111
PublicationCentury	2000
PublicationDate	2022-08-01
PublicationDateYYYYMMDD	2022-08-01
PublicationDate_xml	– month: 08 year: 2022 text: 2022-08-01 day: 01
PublicationDecade	2020
PublicationPlace	United States
PublicationPlace_xml	– name: United States – name: New York
PublicationTitle	IEEE transactions on pattern analysis and machine intelligence
PublicationTitleAbbrev	TPAMI
PublicationTitleAlternate	IEEE Trans Pattern Anal Mach Intell
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 ref12 Demšar (ref40) 2006; 7 Goodfellow (ref49) ref15 ref14 ref52 ref11 Ji (ref17) Levina (ref33) ref10 ref16 Kruskal (ref18) 1978 ref19 Ioffe (ref35) Rijsbergen (ref39) 1979 ref51 ref50 Srivastava (ref36) 2014; 15 ref48 ref47 ref44 ref43 ref8 ref7 Zong (ref45) ref9 ref4 Vincent (ref37) 2010; 11 ref6 ref34 ref31 Goodfellow (ref3) 2016 ref32 ref2 ref1 Conover (ref41) 1999 ref38 Zhai (ref46) Schreyer (ref5) 2017 ref24 ref23 ref26 ref25 Papernot (ref20) 2018 ref22 ref21 ref28 ref27 ref29 Ahmed (ref30) 2021; 22 Bland (ref42) 1995; 310
References_xml	– volume: 7 start-page: 1 year: 2006 ident: ref40 article-title: Statistical comparisons of classifiers over multiple data sets publication-title: J. Mach. Learn. Res. – ident: ref1 doi: 10.1002/aic.690370209 – start-page: 2672 volume-title: Proc. Int. Conf. Neural Inf. Process. Syst. ident: ref49 article-title: Generative adversarial nets – ident: ref23 doi: 10.1109/CVPR.2013.17 – volume: 15 start-page: 1929 issue: 1 year: 2014 ident: ref36 article-title: Dropout: A simple way to prevent neural networks from overfitting publication-title: J. Mach. Learn. Res. – start-page: 1 volume-title: Proc. Int. Conf. Learn. Representations ident: ref45 article-title: Deep autoencoding Gaussian mixture model for unsupervised anomaly detection – ident: ref6 doi: 10.1126/science.290.5500–2323 – start-page: 1100 ident: ref46 article-title: Deep structured energy based models for anomaly detection – ident: ref13 doi: 10.1109/ICPR.2014.272 – ident: ref38 doi: 10.1007/s10618-015-0444-8 – ident: ref16 doi: 10.1371/journal.pone.0146672 – ident: ref19 doi: 10.1109/SPW.2019.00014 – ident: ref7 doi: 10.1126/science.290.5500.2319 – volume: 11 start-page: 3371 year: 2010 ident: ref37 article-title: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion publication-title: J. Mach. Learn. Res. – ident: ref52 doi: 10.1145/2487575.2487629 – ident: ref14 doi: 10.1109/SMC.2015.513 – volume: 22 start-page: 1 issue: 34 year: 2021 ident: ref30 article-title: Neighborhood structure assisted non-negative matrix factorization and its application in unsupervised point-wise anomaly detection publication-title: J. Mach. Learn. Res. – ident: ref48 doi: 10.1007/978-3-642-01307-2_86 – ident: ref27 doi: 10.1109/ICDM.2018.00088 – ident: ref29 doi: 10.1016/S0012-365X(00)00224-7 – ident: ref43 doi: 10.1145/342009.335388 – ident: ref22 doi: 10.1109/WACV.2012.6163005 – ident: ref11 doi: 10.1090/jams/852 – start-page: 777 volume-title: Proc. Int. Conf. Neural Inf. Process. Syst. ident: ref33 article-title: Maximum likelihood estimation of intrinsic dimension – ident: ref32 doi: 10.1007/3-540-47887-6_53 – volume-title: Information Retrieval year: 1979 ident: ref39 – ident: ref9 doi: 10.1109/TPAMI.2010.231 – ident: ref50 doi: 10.7551/mitpress/7503.003.0147 – ident: ref51 doi: 10.1007/978-3-642-23783-6_41 – ident: ref25 doi: 10.1109/TSP.2004.831130 – volume-title: Deep Learning year: 2016 ident: ref3 – year: 2017 ident: ref5 article-title: Detection of anomalies in large scale accounting data using deep autoencoder networks – ident: ref10 doi: 10.7551/mitpress/9780262033589.001.0001 – ident: ref8 doi: 10.7551/mitpress/1120.003.0080 – start-page: 448 ident: ref35 article-title: Batch normalization: Accelerating deep network training by reducing internal covariate shift – ident: ref4 doi: 10.1145/3097983.3098052 – ident: ref47 doi: 10.1109/ICDM.2008.17 – start-page: 24 volume-title: Proc. Int. Conf. Neural Inf. Process. Syst. ident: ref17 article-title: Deep subspace clustering networks – volume-title: Practical Nonparametric Statistics year: 1999 ident: ref41 – ident: ref2 doi: 10.1126/science.1127647 – volume-title: Multidimensional Scaling year: 1978 ident: ref18 doi: 10.4135/9781412985130 – volume: 310 year: 1995 ident: ref42 article-title: Multiple significance tests: The Bonferroni method publication-title: Brit. Med. J. doi: 10.1136/bmj.310.6973.170 – ident: ref44 doi: 10.1162/089976601750264965 – ident: ref12 doi: 10.1007/978-3-642-40994-3_14 – ident: ref28 doi: 10.1090/S0002-9939-1956-0078686-7 – ident: ref24 doi: 10.1002/j.1538-7305.1957.tb01515.x – year: 2018 ident: ref20 article-title: Deep k-nearest neighbors: Towards confident, interpretable and robust deep learning – ident: ref26 doi: 10.1007/978-3-319-59050-9_12 – ident: ref31 doi: 10.1109/TASE.2018.2848198 – ident: ref34 doi: 10.1038/s41598-017-11873-y – ident: ref15 doi: 10.1016/j.neucom.2015.02.023 – ident: ref21 doi: 10.1109/TIP.2016.2605010
SSID	ssj0014503
Score	2.5809362
Snippet	Dimensionality reduction is a crucial first step for many unsupervised learning tasks including anomaly detection and clustering. Autoencoder is a popular...
SourceID	proquest pubmed crossref ieee
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	4110
SubjectTerms	Algorithms Anomalies Anomaly detection Autoencoder Clustering Cognitive tasks Data points Datasets Decoding Dimensionality reduction Embedding Euclidean geometry Generative adversarial networks Graph theory Laplace equations Manifolds Measurement minimum spanning tree Neural networks nonlinear embedding Performance enhancement Reduction unsupervised learning
Title	Graph Regularized Autoencoder and its Application in Unsupervised Anomaly Detection
URI	https://ieeexplore.ieee.org/document/9380495 https://www.ncbi.nlm.nih.gov/pubmed/33729925 https://www.proquest.com/docview/2682919808 https://www.proquest.com/docview/2502807628
Volume	44
WOSCitedRecordID	wos000820521900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Xplore customDbUrl: eissn: 2160-9292 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014503 issn: 0162-8828 databaseCode: RIE dateStart: 19790101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Nb9QwEB21FULtgUIL7ZZSGYkbbGtv4tg-roACB6oKWmlvkeMPaaXiVJukEvx6xt4k7QGQuEXJOIk88-KZjGcewBvPpaiYYVNhEeS5V3Sqq9jwklknjS4wKKGJbEJcXMjFQl1uwLuxFsY5lzafudN4mHL5tjZd_FV2pjKJDi3fhE0hxLpWa8wY5DyxIKMHgwjHMGIokKHq7Opy_vULhoIzdooOcoHo3obHWcxXqciQ_WA9SgQrf_c105pzvvt_b_sUnvS-JZmvjeEZbLiwB7sDbwPpYbwHOw-aEO7D90-xZzX5lkjpV8tfzpJ519axwaXFUTpYsmwbMr_PdJNlINeh6W7jd6aJ8qH-oW9-kg-uTTu7wnO4Pv949f7ztKdamJpM8RZ97ARHoQtHc890ZrxwruCZEVWWawS-UTirmaHe4zkuK1npTHv01iirKp-9gK1QB3cIBEE9k9LkhkmbW48RZE6d85a7QjjO-QTYMOGl6fuQRzqMmzLFI1SVSV9l1FfZ62sCb8cxt-suHP-U3o_aGCV7RUzgeNBr2QO1KWdojYopSeUEXo-XEWIxb6KDqzuU4TH_jKsGyhys7WG892BGR39-5kvYnsV6ibRj8Bi22lXnXsEjc9cum9UJ2vFCniQ7_g1umetR
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB6VgqAcKLQ8FgoYiRvdNo7jxD6ugNKKdlXBVuotcvyQVipOtUmQ4Ncz9iahB0DiFiXjJPLMF89kPPMBvHVcFBXVdFoYBHnmZDJVVWh4SY0VWuUYlCSRbKKYz8XlpTzfgP2xFsZaGzef2YNwGHP5ptZd-FV2KJlAh5bfgts8y1K6rtYacwYZjzzI6MMgxjGQGEpkEnm4OJ-dnWAwmNIDdJFzxPcW3GUhYyUDR_aNFSlSrPzd24yrztH2_73vQ3jQe5dktjaHR7Bh_Q5sD8wNpAfyDty_0YZwF75-Cl2ryZdIS79a_rSGzLq2Di0uDY5S3pBl25DZ71w3WXpy4ZvuOnxpmiDv62_q6gf5YNu4t8s_houjj4v3x9OebGGqmeQtetkRkIXKbZI5qph2hbU5Z7qoWKYQ-lrirDKdOIfnuKhEpZhy6K8ltKocewKbvvb2GRCEdSqEzjQVJjMOY8gssdYZbvPCcs4nQIcJL3XfiTwQYlyVMSJJZBn1VQZ9lb2-JvBuHHO97sPxT-ndoI1RslfEBPYGvZY9VJsyRXuUVIpETODNeBlBFjInytu6QxkeMtC4bqDM07U9jPcezOj5n5_5Gu4dL85Oy9OT-ecXsJWG6om4f3APNttVZ1_CHf29XTarV9GafwFF9e2w
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=Graph+Regularized+Autoencoder+and+its+Application+in+Unsupervised+Anomaly+Detection&rft.jtitle=IEEE+transactions+on+pattern+analysis+and+machine+intelligence&rft.au=Ahmed%2C+Imtiaz&rft.au=Galoppo%2C+Travis&rft.au=Hu%2C+Xia&rft.au=Ding%2C+Yu&rft.date=2022-08-01&rft.eissn=1939-3539&rft.volume=PP&rft_id=info:doi/10.1109%2FTPAMI.2021.3066111&rft_id=info%3Apmid%2F33729925&rft.externalDocID=33729925
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0162-8828&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0162-8828&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0162-8828&client=summon