Information Theoretic Learning-Enhanced Dual-Generative Adversarial Networks With Causal Representation for Robust OOD Generalization

Recently, machine/deep learning techniques are achieving remarkable success in a variety of intelligent control and management systems, promising to change the future of artificial intelligence (AI) scenarios. However, they still suffer from some intractable difficulty or limitations for model train...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transaction on neural networks and learning systems Jg. 36; H. 2; S. 2066 - 2079
Hauptverfasser:	Zhou, Xiaokang, Zheng, Xuzhe, Shu, Tian, Liang, Wei, Wang, Kevin I-Kai, Qi, Lianyong, Shimizu, Shohei, Jin, Qun
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	United States IEEE 01.02.2025
Schlagworte:	Autoencoder (AE) causal representation learning (CRL) Data models deep learning Feature extraction generative adversarial network (GAN) information theoretic learning (ITL) Object oriented modeling out-of-distribution (OOD) Predictive models Representation learning Task analysis Training
ISSN:	2162-237X, 2162-2388, 2162-2388
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	Recently, machine/deep learning techniques are achieving remarkable success in a variety of intelligent control and management systems, promising to change the future of artificial intelligence (AI) scenarios. However, they still suffer from some intractable difficulty or limitations for model training, such as the out-of-distribution (OOD) issue, in modern smart manufacturing or intelligent transportation systems (ITSs). In this study, we newly design and introduce a deep generative model framework, which seamlessly incorporates the information theoretic learning (ITL) and causal representation learning (CRL) in a dual-generative adversarial network (Dual-GAN) architecture, aiming to enhance the robust OOD generalization in modern machine learning (ML) paradigms. In particular, an ITL- and CRL-enhanced Dual-GAN (ITCRL-DGAN) model is presented, which includes an autoencoder with CRL (AE-CRL) structure to aid the dual-adversarial training with causality-inspired feature representations and a Dual-GAN structure to improve the data augmentation in both feature and data levels. Following a newly designed feature separation strategy, a causal graph is built and improved based on the information theory, which can enhance the causally related factors among the separated core features and further enrich the feature representation with the counterfactual features via interventions based on the refined causal relationships. The ITL is incorporated to improve the extraction of low-dimensional feature representations and learn the optimized causal representations based on the idea of "information flow." A dual-adversarial training mechanism is then developed, which not only enables the generator to expand the boundary of feature distribution in accordance with the optimized feature representation from AE-CRL, but also allows the discriminator to further verify and improve the quality of the augmented data for OOD generalization. Experiment and evaluation results based on an open-source dataset demonstrate the outstanding learning efficiency and classification performance of our proposed model for robust OOD generalization in modern smart applications compared with three baseline methods.
AbstractList	Recently, machine/deep learning techniques are achieving remarkable success in a variety of intelligent control and management systems, promising to change the future of artificial intelligence (AI) scenarios. However, they still suffer from some intractable difficulty or limitations for model training, such as the out-of-distribution (OOD) issue, in modern smart manufacturing or intelligent transportation systems (ITSs). In this study, we newly design and introduce a deep generative model framework, which seamlessly incorporates the information theoretic learning (ITL) and causal representation learning (CRL) in a dual-generative adversarial network (Dual-GAN) architecture, aiming to enhance the robust OOD generalization in modern machine learning (ML) paradigms. In particular, an ITL- and CRL-enhanced Dual-GAN (ITCRL-DGAN) model is presented, which includes an autoencoder with CRL (AE-CRL) structure to aid the dual-adversarial training with causality-inspired feature representations and a Dual-GAN structure to improve the data augmentation in both feature and data levels. Following a newly designed feature separation strategy, a causal graph is built and improved based on the information theory, which can enhance the causally related factors among the separated core features and further enrich the feature representation with the counterfactual features via interventions based on the refined causal relationships. The ITL is incorporated to improve the extraction of low-dimensional feature representations and learn the optimized causal representations based on the idea of "information flow." A dual-adversarial training mechanism is then developed, which not only enables the generator to expand the boundary of feature distribution in accordance with the optimized feature representation from AE-CRL, but also allows the discriminator to further verify and improve the quality of the augmented data for OOD generalization. Experiment and evaluation results based on an open-source dataset demonstrate the outstanding learning efficiency and classification performance of our proposed model for robust OOD generalization in modern smart applications compared with three baseline methods. Recently, machine/deep learning techniques are achieving remarkable success in a variety of intelligent control and management systems, promising to change the future of artificial intelligence (AI) scenarios. However, they still suffer from some intractable difficulty or limitations for model training, such as the out-of-distribution (OOD) issue, in modern smart manufacturing or intelligent transportation systems (ITSs). In this study, we newly design and introduce a deep generative model framework, which seamlessly incorporates the information theoretic learning (ITL) and causal representation learning (CRL) in a dual-generative adversarial network (Dual-GAN) architecture, aiming to enhance the robust OOD generalization in modern machine learning (ML) paradigms. In particular, an ITL- and CRL-enhanced Dual-GAN (ITCRL-DGAN) model is presented, which includes an autoencoder with CRL (AE-CRL) structure to aid the dual-adversarial training with causality-inspired feature representations and a Dual-GAN structure to improve the data augmentation in both feature and data levels. Following a newly designed feature separation strategy, a causal graph is built and improved based on the information theory, which can enhance the causally related factors among the separated core features and further enrich the feature representation with the counterfactual features via interventions based on the refined causal relationships. The ITL is incorporated to improve the extraction of low-dimensional feature representations and learn the optimized causal representations based on the idea of "information flow." A dual-adversarial training mechanism is then developed, which not only enables the generator to expand the boundary of feature distribution in accordance with the optimized feature representation from AE-CRL, but also allows the discriminator to further verify and improve the quality of the augmented data for OOD generalization. Experiment and evaluation results based on an open-source dataset demonstrate the outstanding learning efficiency and classification performance of our proposed model for robust OOD generalization in modern smart applications compared with three baseline methods.Recently, machine/deep learning techniques are achieving remarkable success in a variety of intelligent control and management systems, promising to change the future of artificial intelligence (AI) scenarios. However, they still suffer from some intractable difficulty or limitations for model training, such as the out-of-distribution (OOD) issue, in modern smart manufacturing or intelligent transportation systems (ITSs). In this study, we newly design and introduce a deep generative model framework, which seamlessly incorporates the information theoretic learning (ITL) and causal representation learning (CRL) in a dual-generative adversarial network (Dual-GAN) architecture, aiming to enhance the robust OOD generalization in modern machine learning (ML) paradigms. In particular, an ITL- and CRL-enhanced Dual-GAN (ITCRL-DGAN) model is presented, which includes an autoencoder with CRL (AE-CRL) structure to aid the dual-adversarial training with causality-inspired feature representations and a Dual-GAN structure to improve the data augmentation in both feature and data levels. Following a newly designed feature separation strategy, a causal graph is built and improved based on the information theory, which can enhance the causally related factors among the separated core features and further enrich the feature representation with the counterfactual features via interventions based on the refined causal relationships. The ITL is incorporated to improve the extraction of low-dimensional feature representations and learn the optimized causal representations based on the idea of "information flow." A dual-adversarial training mechanism is then developed, which not only enables the generator to expand the boundary of feature distribution in accordance with the optimized feature representation from AE-CRL, but also allows the discriminator to further verify and improve the quality of the augmented data for OOD generalization. Experiment and evaluation results based on an open-source dataset demonstrate the outstanding learning efficiency and classification performance of our proposed model for robust OOD generalization in modern smart applications compared with three baseline methods.
Author	Zhou, Xiaokang Qi, Lianyong Jin, Qun Zheng, Xuzhe Shu, Tian Liang, Wei Wang, Kevin I-Kai Shimizu, Shohei
Author_xml	– sequence: 1 givenname: Xiaokang orcidid: 0000-0003-3488-4679 surname: Zhou fullname: Zhou, Xiaokang email: zhou@biwako.shiga-u.ac.jp organization: Faculty of Data Science, Shiga University, Hikone, Japan – sequence: 2 givenname: Xuzhe orcidid: 0009-0001-5538-6890 surname: Zheng fullname: Zheng, Xuzhe email: xuzhezheng245@gmail.com organization: School of Frontier Crossover Studies, Hunan University of Technology and Business, Changsha, China – sequence: 3 givenname: Tian orcidid: 0000-0002-6743-7755 surname: Shu fullname: Shu, Tian email: wenbenst@gmail.com organization: Computer Science Institute, Hunan University of Technology and Business, Changsha, China – sequence: 4 givenname: Wei orcidid: 0000-0002-0689-256X surname: Liang fullname: Liang, Wei email: weiliang@csu.edu.cn organization: Changsha Social Laboratory of Artificial Intelligence, Hunan University of Technology and Business, Changsha, China – sequence: 5 givenname: Kevin I-Kai orcidid: 0000-0001-8450-2558 surname: Wang fullname: Wang, Kevin I-Kai email: kevin.wang@auckland.ac.nz organization: Department of Electrical, Computer, Software Engineering, University of Auckland, Auckland, New Zealand – sequence: 6 givenname: Lianyong orcidid: 0000-0001-7746-4901 surname: Qi fullname: Qi, Lianyong email: lianyongqi@upc.edu.cn organization: College of Computer Science and Technology, China University of Petroleum (East China), Qingdao, China – sequence: 7 givenname: Shohei orcidid: 0000-0002-1931-0733 surname: Shimizu fullname: Shimizu, Shohei email: shohei-shimizu@biwako.shiga-u.ac.jp organization: Faculty of Data Science, Shiga University, Hikone, Japan – sequence: 8 givenname: Qun orcidid: 0000-0002-1325-4275 surname: Jin fullname: Jin, Qun email: jin@waseda.jp organization: Faculty of Human Sciences, Waseda University, Tokorozawa, Japan
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/37976189$$D View this record in MEDLINE/PubMed
BookMark	eNp9kU1v1DAQhi1UREvbP4AQ8pFLtv5I_HGstqVUWu1KZSu4RY4zYQ1Ze2s7RXDnfzdtlgpxYC4ejZ_3HWne1-jABw8IvaFkRinRZ-vlcvFpxgjjM845UaJ8gY4YFaxgXKmD515-OUSnKX0jYwlSiVK_Qodcaimo0kfo97XvQtya7ILH6w2ECNlZvAATvfNfi0u_Md5Ciy8G0xdX4CGO7D3g8_YeYjLRmR4vIf8I8XvCn13e4LkZ0ji8gV2EBD5P3uMWfBOaIWW8Wl3gyal3v55-T9DLzvQJTvfvMbr9cLmefywWq6vr-fmisFyoXFDKRGeallJOZdOwknbAJCFAJQFhBJS26nhjNS1b1VTKSNJp1SluS6nbivJj9H7y3cVwN0DK9dYlC31vPIQh1UxpKitGFBvRd3t0aLbQ1rvotib-rP-cbgTYBNgYUorQPSOU1I8R1U8R1Y8R1fuIRpH6R2TddKAcjev_L307SR0A_LWLMyqZ5g9ccqCC
CODEN	ITNNAL
CitedBy_id	crossref_primary_10_1016_j_comcom_2023_12_024 crossref_primary_10_1109_TNNLS_2025_3563889 crossref_primary_10_1109_TCE_2025_3566725 crossref_primary_10_3390_electronics13071316 crossref_primary_10_1111_exsy_13685 crossref_primary_10_1109_TCE_2025_3566783 crossref_primary_10_3390_electronics14183569 crossref_primary_10_1039_D5MH00635J crossref_primary_10_1109_JIOT_2025_3584811 crossref_primary_10_1111_mice_70001 crossref_primary_10_1109_JIOT_2025_3577616 crossref_primary_10_1109_JIOT_2024_3364528 crossref_primary_10_1016_j_neunet_2025_107872 crossref_primary_10_1109_TCE_2023_3341227 crossref_primary_10_1109_TSC_2025_3539201
Cites_doi	10.1109/TNNLS.2021.3107375 10.1109/CVPR.2019.01022 10.1109/TNN.2004.828762 10.1109/TNNLS.2021.3116419 10.1145/3485447.3512251 10.1109/TNNLS.2021.3105227 10.48550/arXiv.1503.02531 10.1109/CVPR52688.2022.00047 10.1109/TSP.2013.2265221 10.1109/TIP.2016.2588330 10.1109/TCSVT.2021.3089491 10.1109/TCBB.2007.1056 10.1109/JSAIT.2020.2991561 10.1109/tnnls.2022.3183864 10.1142/S0219525908001465 10.1609/aaai.v31i1.10480 10.1109/TIFS.2022.3152361 10.1609/aaai.v36i7.20703 10.1145/3460231.3474263 10.1109/TBME.2019.2908099 10.1109/TNNLS.2022.3159538 10.1109/tpami.2022.3166765 10.1109/TCYB.2020.2986463 10.1109/TNNLS.2020.3015215 10.1109/TNNLS.2021.3082158 10.1109/TNNLS.2021.3111911 10.1609/aaai.v34i04.6024 10.1109/CVPR46437.2021.00947 10.1109/ACCESS.2020.3007266 10.1109/JSTSP.2008.923858 10.1109/ACCESS.2019.2958864 10.1109/ACCESS.2022.3160283 10.1109/TCYB.2013.2290775 10.1109/JIOT.2022.3188283 10.1109/TPAMI.2021.3099829 10.1109/TPAMI.2022.3170302 10.1109/TKDE.2022.3159802 10.1038/s41598-019-52737-x 10.1109/TKDE.2021.3119185 10.1109/TKDE.2021.3112591 10.1126/science.290.5500.2323
ContentType	Journal Article
DBID	97E ESBDL RIA RIE AAYXX CITATION NPM 7X8
DOI	10.1109/TNNLS.2023.3330864
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE Xplore Open Access Journals IEEE All-Society Periodicals Package (ASPP) 1998–Present IEL CrossRef PubMed MEDLINE - Academic
DatabaseTitle	CrossRef PubMed MEDLINE - Academic
DatabaseTitleList	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: IEL 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	Computer Science
EISSN	2162-2388
EndPage	2079
ExternalDocumentID	37976189 10_1109_TNNLS_2023_3330864 10321729
Genre	orig-research Journal Article
GrantInformation_xml	– fundername: Grants-in-Aid for Scientific Research (C) from Japan Society for the Promotion of Science (JSPS) grantid: 23K11064 – fundername: National Natural Science Foundation of China grantid: 62072171; 72091515 funderid: 10.13039/501100001809 – fundername: 2022 and 2023 Waseda University Grants for Special Research Projects grantid: 2022R-036; 2023C-216
GroupedDBID	0R~ 4.4 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACIWK ACPRK AENEX AFRAH AGQYO AGSQL AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD ESBDL IFIPE IPLJI JAVBF M43 MS~ O9- OCL PQQKQ RIA RIE RNS AAYXX CITATION NPM 7X8
ID	FETCH-LOGICAL-c368t-1126fabd11317bb241fe2700e170e6a6e4c5f3bc914d8b58a70f98f83c479d513
IEDL.DBID	RIE
ISICitedReferencesCount	80
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001123253500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2162-237X 2162-2388
IngestDate	Sun Sep 28 05:48:54 EDT 2025 Wed Dec 10 14:04:40 EST 2025 Tue Nov 18 21:01:01 EST 2025 Sat Nov 29 01:40:29 EST 2025 Wed Aug 27 01:52:59 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	false
IsScholarly	true
Issue	2
Language	English
License	https://creativecommons.org/licenses/by/4.0/legalcode
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c368t-1126fabd11317bb241fe2700e170e6a6e4c5f3bc914d8b58a70f98f83c479d513
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ORCID	0009-0001-5538-6890 0000-0001-8450-2558 0000-0001-7746-4901 0000-0002-1931-0733 0000-0002-6743-7755 0000-0002-0689-256X 0000-0003-3488-4679 0000-0002-1325-4275
OpenAccessLink	https://ieeexplore.ieee.org/document/10321729
PMID	37976189
PQID	2891752082
PQPubID	23479
PageCount	14
ParticipantIDs	crossref_primary_10_1109_TNNLS_2023_3330864 crossref_citationtrail_10_1109_TNNLS_2023_3330864 proquest_miscellaneous_2891752082 pubmed_primary_37976189 ieee_primary_10321729
PublicationCentury	2000
PublicationDate	2025-02-01
PublicationDateYYYYMMDD	2025-02-01
PublicationDate_xml	– month: 02 year: 2025 text: 2025-02-01 day: 01
PublicationDecade	2020
PublicationPlace	United States
PublicationPlace_xml	– name: United States
PublicationTitle	IEEE transaction on neural networks and learning systems
PublicationTitleAbbrev	TNNLS
PublicationTitleAlternate	IEEE Trans Neural Netw Learn Syst
PublicationYear	2025
Publisher	IEEE
Publisher_xml	– name: IEEE
References	ref13 ref12 Sricharan (ref10) ref15 ref14 ref11 ref17 ref16 ref19 ref18 Ye (ref5); 34 Recht (ref4) ref50 ref46 ref45 Yu (ref49) ref47 ref41 ref44 ref43 Lee (ref42) ref8 Vernekar (ref9) 2019 ref3 ref6 ref40 ref35 ref34 ref37 ref36 ref31 ref30 ref33 ref32 ref1 ref39 Liu (ref2) ref38 ref24 ref23 ref26 ref25 ref20 ref22 ref21 Pearl (ref48) 2016 ref28 ref27 Krueger (ref7) ref29
References_xml	– ident: ref23 doi: 10.1109/TNNLS.2021.3107375 – ident: ref43 doi: 10.1109/CVPR.2019.01022 – ident: ref13 doi: 10.1109/TNN.2004.828762 – ident: ref37 doi: 10.1109/TNNLS.2021.3116419 – volume-title: Causal Inference in Statistics: A Primer year: 2016 ident: ref48 – start-page: 5815 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref7 article-title: Out-of-distribution generalization via risk extrapolation – start-page: 1 volume-title: Proc. 3rd Workshop Bayesian Deep Learn. (NeurIPS) ident: ref10 article-title: Building robust classifiers through generation of confident out of distribution examples – ident: ref8 doi: 10.1145/3485447.3512251 – ident: ref40 doi: 10.1109/TNNLS.2021.3105227 – ident: ref46 doi: 10.48550/arXiv.1503.02531 – ident: ref50 doi: 10.1109/CVPR52688.2022.00047 – ident: ref16 doi: 10.1109/TSP.2013.2265221 – ident: ref18 doi: 10.1109/TIP.2016.2588330 – ident: ref25 doi: 10.1109/TCSVT.2021.3089491 – ident: ref17 doi: 10.1109/TCBB.2007.1056 – ident: ref15 doi: 10.1109/JSAIT.2020.2991561 – ident: ref27 doi: 10.1109/tnnls.2022.3183864 – start-page: 1 volume-title: Proc. ICLR ident: ref42 article-title: Training confidence-calibrated classifiers for detecting out-of-distribution samples – ident: ref47 doi: 10.1142/S0219525908001465 – ident: ref11 doi: 10.1609/aaai.v31i1.10480 – ident: ref20 doi: 10.1109/TIFS.2022.3152361 – ident: ref6 doi: 10.1609/aaai.v36i7.20703 – ident: ref12 doi: 10.1145/3460231.3474263 – ident: ref21 doi: 10.1109/TBME.2019.2908099 – ident: ref33 doi: 10.1109/TNNLS.2022.3159538 – ident: ref28 doi: 10.1109/tpami.2022.3166765 – ident: ref22 doi: 10.1109/TCYB.2020.2986463 – volume: 34 start-page: 23519 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref5 article-title: Towards a theoretical framework of out-of-distribution generalization – ident: ref14 doi: 10.1109/TNNLS.2020.3015215 – ident: ref39 doi: 10.1109/TNNLS.2021.3082158 – ident: ref35 doi: 10.1109/TNNLS.2021.3111911 – year: 2019 ident: ref9 article-title: Out-of-distribution detection in classifiers via generation publication-title: arXiv:1910.04241 – ident: ref3 doi: 10.1609/aaai.v34i04.6024 – ident: ref44 doi: 10.1109/CVPR46437.2021.00947 – ident: ref38 doi: 10.1109/ACCESS.2020.3007266 – start-page: 6804 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref2 article-title: Heterogeneous risk minimization – ident: ref19 doi: 10.1109/JSTSP.2008.923858 – ident: ref34 doi: 10.1109/ACCESS.2019.2958864 – ident: ref36 doi: 10.1109/ACCESS.2022.3160283 – ident: ref29 doi: 10.1109/TCYB.2013.2290775 – ident: ref31 doi: 10.1109/JIOT.2022.3188283 – ident: ref41 doi: 10.1109/TPAMI.2021.3099829 – ident: ref30 doi: 10.1109/TPAMI.2022.3170302 – ident: ref24 doi: 10.1109/TKDE.2022.3159802 – ident: ref1 doi: 10.1038/s41598-019-52737-x – ident: ref26 doi: 10.1109/TKDE.2021.3119185 – ident: ref32 doi: 10.1109/TKDE.2021.3112591 – ident: ref45 doi: 10.1126/science.290.5500.2323 – start-page: 7154 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref49 article-title: DAG-GNN: DAG structure learning with graph neural networks – start-page: 5389 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref4 article-title: Do ImageNet classifiers generalize to ImageNet?
SSID	ssj0000605649
Score	2.6631107
Snippet	Recently, machine/deep learning techniques are achieving remarkable success in a variety of intelligent control and management systems, promising to change the...
SourceID	proquest pubmed crossref ieee
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	2066
SubjectTerms	Autoencoder (AE) causal representation learning (CRL) Data models deep learning Feature extraction generative adversarial network (GAN) information theoretic learning (ITL) Object oriented modeling out-of-distribution (OOD) Predictive models Representation learning Task analysis Training
Title	Information Theoretic Learning-Enhanced Dual-Generative Adversarial Networks With Causal Representation for Robust OOD Generalization
URI	https://ieeexplore.ieee.org/document/10321729 https://www.ncbi.nlm.nih.gov/pubmed/37976189 https://www.proquest.com/docview/2891752082
Volume	36
WOSCitedRecordID	wos001123253500001&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: IEL customDbUrl: eissn: 2162-2388 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000605649 issn: 2162-237X databaseCode: RIE dateStart: 20120101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NT9wwEB0V1EMvhQItCxS5Um_ISxxn_XFEfIgDChVdxN4i27ELEspWJOk_4H9jO86KC5W4RZGdRHrjzIw9bx7Az6LIrDNuhh3RHBeMKb-kmMDOZVL7fMIJG5G-4mUpFgv5K5HVIxfGWhuLz-w0XMaz_Hpp-rBVdhyav3mHK9dgjXM2kLVWGyqZD8xZDHdzwnKcU74YSTKZPJ6X5dXvadAKn1KfwgsWBHko986YBIX3Vz4piqy8HW9Gv3Ox8c4v3oTPKcBEJ4NFfIEPttmCjVG8AaW1vA3PiYgUgEHzkc6IUr_VP_i8uY_FAeisV4946E4dfo0oSji3KhguKoci8hbdPXT36FT1rb95E4trE6epQf4t6Gap-7ZD19dnKPW5TvTPHbi9OJ-fXuKkyYANZaLDgXHklK4J8YGH1t7_OxvOri3hmWWK2cLMHNVGkqIWeiYUz5wUTlBTcFnPCP0K682ysbuAMkeJylluuOWFE8xHkrRWWrpak9pINgEyolKZ1LA86GY8VjFxyWQVQa0CqFUCdQJHqzl_h3Yd_x29EyB7NXJAawI_RvQrv9rCEYpq7LJvK5-e-ngr93HTBL4NZrGaPVrT3htP3YdPeRAPjiXfB7DePfX2O3w0_7qH9unQm_RCHEaTfgG81fGV
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3LbtQwFL0qBQk2lEcLU15GYoc8jeOMH8uqD7ViSFEZ1NlFtmO3laoMahL-gP_GdpxRN63ELorsJNK5jo_te-4B-FIUmXXGzbAjmuOCMeWHFBPYuUxqv55wwkak57wsxXIpfySxetTCWGtj8pmdhst4ll-vTB-2yvZC8Tc_4cpH8DhYZyW51npLJfPUnEXCmxOW45zy5SiTyeTeoiznP6fBLXxK_SJesGDJQ7mfjknweL8zK0WblfsZZ5x5jrf-85tfwPNEMdH-EBMvYcM2r2BrtG9AaTS_hr9JihSgQYtR0IhSxdVLfNRcxfQAdNirGzzUpw4_RxRNnFsVQheVQxp5iy6uuyt0oPrW3zyP6bVJ1dQg_xZ0vtJ926Gzs0OUKl0nAeg2_Do-Whyc4OTKgA1losNBc-SUrgnx1ENrzwCcDafXlvDMMsVsYWaOaiNJUQs9E4pnTgonqCm4rGeE7sBms2rsW0CZo0TlLDfc8sIJ5rkkrZWWrtakNpJNgIyoVCaVLA_OGTdVXLpksoqgVgHUKoE6ga_rPr-Hgh0Ptt4OkN1pOaA1gc8j-pUfb-EQRTV21beVX6B6xpV75jSBN0NYrHuP0bR7z1M_wdOTxfd5NT8tv72DZ3mwEo4J4O9hs7vt7Qd4Yv501-3txxjY_wDEmfP2
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=Information+Theoretic+Learning-Enhanced+Dual-Generative+Adversarial+Networks+With+Causal+Representation+for+Robust+OOD+Generalization&rft.jtitle=IEEE+transaction+on+neural+networks+and+learning+systems&rft.au=Zhou%2C+Xiaokang&rft.au=Zheng%2C+Xuzhe&rft.au=Shu%2C+Tian&rft.au=Liang%2C+Wei&rft.date=2025-02-01&rft.pub=IEEE&rft.issn=2162-237X&rft.volume=36&rft.issue=2&rft.spage=2066&rft.epage=2079&rft_id=info:doi/10.1109%2FTNNLS.2023.3330864&rft_id=info%3Apmid%2F37976189&rft.externalDocID=10321729
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2162-237X&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2162-237X&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2162-237X&client=summon