adVAE: A self-adversarial variational autoencoder with Gaussian anomaly prior knowledge for anomaly detection
Recently, deep generative models have become increasingly popular in unsupervised anomaly detection. However, deep generative models aim at recovering the data distribution rather than detecting anomalies. Moreover, deep generative models have the risk of overfitting training samples, which has disa...
Saved in:
| Published in: | Knowledge-based systems Vol. 190; p. 105187 |
|---|---|
| Main Authors: | , , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Amsterdam
Elsevier B.V
29.02.2020
Elsevier Science Ltd |
| Subjects: | |
| ISSN: | 0950-7051, 1872-7409 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Recently, deep generative models have become increasingly popular in unsupervised anomaly detection. However, deep generative models aim at recovering the data distribution rather than detecting anomalies. Moreover, deep generative models have the risk of overfitting training samples, which has disastrous effects on anomaly detection performance. To solve the above two problems, we propose a self-adversarial variational autoencoder (adVAE) with a Gaussian anomaly prior assumption. We assume that both the anomalous and the normal prior distribution are Gaussian and have overlaps in the latent space. Therefore, a Gaussian transformer net T is trained to synthesize anomalous but near-normal latent variables. Keeping the original training objective of a variational autoencoder, a generator G tries to distinguish between the normal latent variables encoded by E and the anomalous latent variables synthesized by T, and the encoder E is trained to discriminate whether the output of G is real. These new objectives we added not only give both G and E the ability to discriminate, but also become an additional regularization mechanism to prevent overfitting. Compared with other competitive methods, the proposed model achieves significant improvements in extensive experiments. The employed datasets and our model are available in a Github repository. |
|---|---|
| AbstractList | Recently, deep generative models have become increasingly popular in unsupervised anomaly detection. However, deep generative models aim at recovering the data distribution rather than detecting anomalies. Moreover, deep generative models have the risk of overfitting training samples, which has disastrous effects on anomaly detection performance. To solve the above two problems, we propose a self-adversarial variational autoencoder (adVAE) with a Gaussian anomaly prior assumption. We assume that both the anomalous and the normal prior distribution are Gaussian and have overlaps in the latent space. Therefore, a Gaussian transformer net T is trained to synthesize anomalous but near-normal latent variables. Keeping the original training objective of a variational autoencoder, a generator G tries to distinguish between the normal latent variables encoded by E and the anomalous latent variables synthesized by T, and the encoder E is trained to discriminate whether the output of G is real. These new objectives we added not only give both G and E the ability to discriminate, but also become an additional regularization mechanism to prevent overfitting. Compared with other competitive methods, the proposed model achieves significant improvements in extensive experiments. The employed datasets and our model are available in a Github repository. |
| ArticleNumber | 105187 |
| Author | Wang, Xuhong Lin, Shijie Cui, Ping Shen, Yuntian Du, Ying Yang, Yupu |
| Author_xml | – sequence: 1 givenname: Xuhong surname: Wang fullname: Wang, Xuhong email: wang_xuhong@sjtu.edu.cn organization: Shanghai Jiao Tong University, Shanghai, China – sequence: 2 givenname: Ying surname: Du fullname: Du, Ying email: duying@sjtu.edu.cn organization: Shanghai Jiao Tong University, Shanghai, China – sequence: 3 givenname: Shijie surname: Lin fullname: Lin, Shijie email: linshijie@whu.edu.cn organization: Wuhan University, Wuhan, China – sequence: 4 givenname: Ping surname: Cui fullname: Cui, Ping email: cuiping@sjtu.edu.cn organization: Shanghai Jiao Tong University, Shanghai, China – sequence: 5 givenname: Yuntian surname: Shen fullname: Shen, Yuntian email: ytshen@ucdavis.edu organization: University of California, Davis, USA – sequence: 6 givenname: Yupu surname: Yang fullname: Yang, Yupu email: ypyang@sjtu.edu.cn organization: Shanghai Jiao Tong University, Shanghai, China |
| BookMark | eNqFkE1PAyEQhonRxPrxDzyQeN7Kx24pHkwao9XExIt6JRMYlLpdFLY1_fdSVy8e9MIwzLxveJ8DstvFDgk54WzMGZ-cLcavXcybPBaM6_LU8KnaIaNyikrVTO-SEdMNq1SZ7JODnBeMMSH4dESW4J5mV-d0RjO2vgK3xpQhBWjpelv6ELtyh1UfsbPRYaIfoX-hc1jlHKCj0MUltBv6lkJMtPzjo0X3jNSX7mfmsEe7dToiex7ajMff9ZA8Xl89XN5Ud_fz28vZXWWlrPsKa-eUdwrlVGmQKIWWWlrgyLmbMm31xHnfKNUwKaD2wkrhYVJ7UMhEg_KQnA6-bym-rzD3ZhFXqQTJRkg10XVTC1m26mHLpphzQm9KiCWkjeHMbMGahRnAmi1YM4AtsvNfMhv6L1B9gtD-J74YxFjirwMmk20oZNGFVBgZF8PfBp8qvprI |
| CitedBy_id | crossref_primary_10_1007_s10115_023_02012_3 crossref_primary_10_1016_j_ymeth_2023_04_007 crossref_primary_10_1109_TNNLS_2021_3116269 crossref_primary_10_1088_1361_6501_abe5e3 crossref_primary_10_1016_j_knosys_2023_110611 crossref_primary_10_1007_s10489_020_01944_5 crossref_primary_10_1016_j_media_2024_103229 crossref_primary_10_1016_j_neucom_2021_06_030 crossref_primary_10_1007_s10489_024_05395_0 crossref_primary_10_1007_s40815_023_01496_z crossref_primary_10_1016_j_ins_2025_122227 crossref_primary_10_1094_PHYTO_05_20_0185_R crossref_primary_10_1016_j_knosys_2023_111196 crossref_primary_10_1109_TAI_2024_3394795 crossref_primary_10_1016_j_knosys_2022_108846 crossref_primary_10_1109_TSG_2020_3019263 crossref_primary_10_3390_computers14030079 crossref_primary_10_1109_TNNLS_2021_3122179 crossref_primary_10_1109_ACCESS_2022_3178592 crossref_primary_10_1016_j_knosys_2022_108241 crossref_primary_10_3389_fphys_2022_961724 crossref_primary_10_1140_epjc_s10052_023_12169_4 crossref_primary_10_32604_cmes_2021_016264 crossref_primary_10_3390_s23239360 crossref_primary_10_1109_TGRS_2022_3198130 crossref_primary_10_3390_sym13112104 crossref_primary_10_1109_TMM_2022_3175611 crossref_primary_10_1016_j_knosys_2024_111842 crossref_primary_10_1080_0951192X_2024_2397821 crossref_primary_10_1007_s10845_020_01716_5 crossref_primary_10_1049_cit2_12007 crossref_primary_10_1016_j_knosys_2024_111640 crossref_primary_10_1016_j_eswa_2025_129166 crossref_primary_10_1007_s10845_024_02511_2 crossref_primary_10_1007_s11063_024_11681_2 crossref_primary_10_1016_j_jobe_2023_106099 crossref_primary_10_1088_2632_2153_ace756 crossref_primary_10_1109_TBDATA_2024_3350539 crossref_primary_10_1007_s00521_021_05924_9 crossref_primary_10_1109_TMM_2020_3046884 crossref_primary_10_1007_s11276_023_03353_1 crossref_primary_10_1029_2023SW003516 crossref_primary_10_3390_app112110307 crossref_primary_10_1109_TNNLS_2021_3130074 crossref_primary_10_1016_j_eswa_2021_116429 crossref_primary_10_1016_j_neunet_2023_12_023 crossref_primary_10_1016_j_chemolab_2025_105491 crossref_primary_10_1016_j_jmapro_2023_03_043 crossref_primary_10_1109_TIM_2023_3303498 crossref_primary_10_3389_frobt_2025_1554196 crossref_primary_10_1016_j_engappai_2023_106312 crossref_primary_10_1016_j_jik_2025_100782 crossref_primary_10_3390_aerospace7080115 crossref_primary_10_1016_j_eswa_2025_128978 crossref_primary_10_1109_ACCESS_2023_3313448 crossref_primary_10_1016_j_jnca_2022_103513 crossref_primary_10_1016_j_knosys_2023_110829 crossref_primary_10_1109_ACCESS_2021_3072126 crossref_primary_10_1016_j_engappai_2025_111585 crossref_primary_10_1016_j_asoc_2024_111896 crossref_primary_10_1016_j_sysarc_2023_102861 crossref_primary_10_1016_j_neucom_2021_04_089 crossref_primary_10_1109_ACCESS_2024_3452168 crossref_primary_10_1007_s00521_024_10291_2 crossref_primary_10_1002_tee_23672 |
| Cites_doi | 10.1016/j.csda.2016.09.001 10.1016/j.jnca.2016.04.007 10.1016/j.cie.2015.06.020 10.1109/TNN.2004.828762 10.1145/2830544.2830549 10.1145/2890508 10.1609/aaai.v31i1.10983 10.1109/LRA.2018.2801475 10.1016/j.cherd.2018.12.028 10.1016/j.knosys.2018.04.020 10.1016/j.sigpro.2013.12.026 10.1109/TKDE.2019.2905606 10.1162/089976601750264965 10.1016/j.knosys.2019.03.001 10.1016/j.neucom.2017.02.039 10.1016/j.jocs.2015.11.005 |
| ContentType | Journal Article |
| Copyright | 2019 Elsevier B.V. Copyright Elsevier Science Ltd. Feb 29, 2020 |
| Copyright_xml | – notice: 2019 Elsevier B.V. – notice: Copyright Elsevier Science Ltd. Feb 29, 2020 |
| DBID | AAYXX CITATION 7SC 8FD E3H F2A JQ2 L7M L~C L~D |
| DOI | 10.1016/j.knosys.2019.105187 |
| DatabaseName | CrossRef Computer and Information Systems Abstracts Technology Research Database Library & Information Sciences Abstracts (LISA) Library & Information Science Abstracts (LISA) 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 Library and Information Science Abstracts (LISA) ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional |
| DatabaseTitleList | Technology Research Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1872-7409 |
| ExternalDocumentID | 10_1016_j_knosys_2019_105187 S0950705119305283 |
| GroupedDBID | --K --M .DC .~1 0R~ 1B1 1~. 1~5 4.4 457 4G. 5VS 7-5 71M 77K 8P~ 9JN AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAXUO AAYFN ABAOU ABBOA ABIVO ABJNI ABMAC ABYKQ ACAZW ACDAQ ACGFS ACRLP ACZNC ADBBV ADEZE ADGUI ADTZH AEBSH AECPX AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ARUGR AXJTR BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EO8 EO9 EP2 EP3 FDB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ IHE J1W JJJVA KOM LG9 LY7 M41 MHUIS MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. PQQKQ Q38 ROL RPZ SDF SDG SDP SES SPC SPCBC SST SSV SSW SSZ T5K WH7 XPP ZMT ~02 ~G- 29L 77I 9DU AAQXK AATTM AAXKI AAYWO AAYXX ABDPE ABWVN ABXDB ACLOT ACNNM ACRPL ACVFH ADCNI ADJOM ADMUD ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP ASPBG AVWKF AZFZN CITATION EFKBS EJD FEDTE FGOYB G-2 HLZ HVGLF HZ~ R2- SBC SET SEW UHS WUQ ~HD 7SC 8FD E3H F2A JQ2 L7M L~C L~D |
| ID | FETCH-LOGICAL-c334t-e4dd7fd7e3879a3e329393ca1e11d809c96dff5775032a4f2c32fa64fa7e025e3 |
| ISICitedReferencesCount | 82 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000518492400009&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0950-7051 |
| IngestDate | Fri Nov 14 18:45:03 EST 2025 Sat Nov 29 07:07:33 EST 2025 Tue Nov 18 20:59:31 EST 2025 Fri Feb 23 02:49:30 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Variational autoencoder Outlier detection Deep generative model Anomaly detection Novelty detection |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c334t-e4dd7fd7e3879a3e329393ca1e11d809c96dff5775032a4f2c32fa64fa7e025e3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| PQID | 2376945423 |
| PQPubID | 2035257 |
| ParticipantIDs | proquest_journals_2376945423 crossref_primary_10_1016_j_knosys_2019_105187 crossref_citationtrail_10_1016_j_knosys_2019_105187 elsevier_sciencedirect_doi_10_1016_j_knosys_2019_105187 |
| PublicationCentury | 2000 |
| PublicationDate | 2020-02-29 |
| PublicationDateYYYYMMDD | 2020-02-29 |
| PublicationDate_xml | – month: 02 year: 2020 text: 2020-02-29 day: 29 |
| PublicationDecade | 2020 |
| PublicationPlace | Amsterdam |
| PublicationPlace_xml | – name: Amsterdam |
| PublicationTitle | Knowledge-based systems |
| PublicationYear | 2020 |
| Publisher | Elsevier B.V Elsevier Science Ltd |
| Publisher_xml | – name: Elsevier B.V – name: Elsevier Science Ltd |
| References | Park, Hoshi, Kemp (b14) 2018; 3 Pimentel, Clifton, Clifton, Tarassenko (b9) 2014; 99 Huang, Li, He, Sun, Tan (b26) 2018 Aggarwal, Sathe (b43) 2015; 17 Gramacki, Gramacki (b37) 2017; 106 Zhang, Bi, Xu, Ramentol, Fan, Qiao, Fujita (b6) 2019; 174 Goodfellow, Pouget-Abadie, Mirza, Xu, Warde-Farley, Ozair, Courville, Bengio (b12) 2014 Harrou, Kadri, Chaabane, Tahon, Sun (b34) 2015; 88 Keller, Müller, Böhm (b44) 2012 Liu, Ting, Zhou (b46) 2008 Goldstein, Dengel (b49) 2012 Silverman (b39) 2018 Davis, Goadrich (b45) 2006 Abdallah, Maarof, Zainal (b2) 2016; 68 Liu, Li, Zhou, Jiang, Sun, Wang, He (b24) 2019 Chalapathy, Chawla (b10) 2019 Ravanbakhsh, Nabi, Sangineto, Marcenaro, Regazzoni, Sebe (b19) 2017 An, Cho (b13) 2015 B. Zong, Q. Song, M.R. Min, W. Cheng, C. Lumezanu, D. Cho, H. Chen, Deep autoencoding Gaussian mixture model for unsupervised anomaly detection, in: International Conference on Learning Representations, ICLR, 2018. Breunig, Kriegel, Ng, Sander (b29) 2000 Xu, Chen, Zhao, Li, Bu, Li, Liu, Zhao, Pei, Feng, Chen, Wang, Qiao (b16) 2018 Ilonen, Paalanen, Kamarainen, Kälviäinen (b27) 2006 Cui, Zhan, Yang (b3) 2019; 142 Kawachi, Koizumi, Harada (b25) 2018 I. Gulrajani, F. Ahmed, M. Arjovsky, V. Dumoulin, A.C. Courville, Improved training of Wasserstein GANs, in: Annual Conference on Neural Information Processing Systems, NeurIPS, 2017, pp. 5767–5777. Kriegel, Schubert, Zimek (b47) 2008 I.V. Serban, A. Sordoni, R. Lowe, L. Charlin, J. Pineau, A.C. Courville, Y. Bengio, A hierarchical latent variable encoder-decoder model for generating dialogues, in: AAAI Conference on Artificial Intelligence, AAAI, 2017, pp. 3295–3301. Honkela, Valpola (b23) 2004; 15 A. Makhzani, J. Shlens, N. Jaitly, I. Goodfellow, Adversarial autoencoders, in: International Conference on Learning Representations, ICLR, 2016. Tang, He (b30) 2017; 241 Osada, Omote, Nishide (b1) 2017 Yeung, Chow (b28) 2002 Olive (b33) 2017 X. Chen, D.P. Kingma, T. Salimans, Y. Duan, P. Dhariwal, J. Schulman, I. Sutskever, P. Abbeel, Variational lossy autoencoder, in: International Conference on Learning Representations, ICLR, 2017. Sathe, Aggarwal (b41) 2016 Pidhorskyi, Almohsen, Doretto (b18) 2018 Kriegel, Kröger, Schubert, Zimek (b48) 2009; vol. 5476 Schölkopf, Platt, Shawe-Taylor, Smola, Williamson (b31) 2001; 13 M. Fraccaro, S.K. Sønderby, U. Paquet, O. Winther, Sequential neural models with stochastic layers, in: Annual Conference on Neural Information Processing Systems NeurIPS, 2016, pp. 2199–2207. Yin, Wang, Fan (b32) 2018; 153 Zhou, Yang, Fujita, Chen, Wen (b7) 2019 Rayana, Akoglu (b40) 2016; 10 Baklouti, Mansouri, Nounou, Nounou, Hamida (b35) 2016; 15 Liu, Ting, Zhou (b42) 2008 D.P. Kingma, M. Welling, Auto-encoding variational Bayes, in: International Conference on Learning Representations, ICLR, 2014. Suh, Chae, Kang, Choi (b15) 2016 Schlegl, Seeböck, Waldstein, Schmidt-Erfurth, Langs (b4) 2017 Lemaître, Nogueira, Aridas (b8) 2017; 18 Zhao, Nasrullah, Li (b50) 2019; 20 He, Bai, Garcia, Li (b51) 2008 Akcay, Abarghouei, Breckon (b5) 2018 Schlegl (10.1016/j.knosys.2019.105187_b4) 2017 Cui (10.1016/j.knosys.2019.105187_b3) 2019; 142 Akcay (10.1016/j.knosys.2019.105187_b5) 2018 Liu (10.1016/j.knosys.2019.105187_b24) 2019 Olive (10.1016/j.knosys.2019.105187_b33) 2017 Kriegel (10.1016/j.knosys.2019.105187_b47) 2008 Park (10.1016/j.knosys.2019.105187_b14) 2018; 3 Zhao (10.1016/j.knosys.2019.105187_b50) 2019; 20 Chalapathy (10.1016/j.knosys.2019.105187_b10) 2019 Baklouti (10.1016/j.knosys.2019.105187_b35) 2016; 15 Rayana (10.1016/j.knosys.2019.105187_b40) 2016; 10 Abdallah (10.1016/j.knosys.2019.105187_b2) 2016; 68 Ravanbakhsh (10.1016/j.knosys.2019.105187_b19) 2017 Goldstein (10.1016/j.knosys.2019.105187_b49) 2012 Liu (10.1016/j.knosys.2019.105187_b46) 2008 Honkela (10.1016/j.knosys.2019.105187_b23) 2004; 15 Schölkopf (10.1016/j.knosys.2019.105187_b31) 2001; 13 10.1016/j.knosys.2019.105187_b36 Harrou (10.1016/j.knosys.2019.105187_b34) 2015; 88 He (10.1016/j.knosys.2019.105187_b51) 2008 10.1016/j.knosys.2019.105187_b38 Lemaître (10.1016/j.knosys.2019.105187_b8) 2017; 18 Huang (10.1016/j.knosys.2019.105187_b26) 2018 Breunig (10.1016/j.knosys.2019.105187_b29) 2000 Sathe (10.1016/j.knosys.2019.105187_b41) 2016 Zhang (10.1016/j.knosys.2019.105187_b6) 2019; 174 An (10.1016/j.knosys.2019.105187_b13) 2015 Gramacki (10.1016/j.knosys.2019.105187_b37) 2017; 106 Osada (10.1016/j.knosys.2019.105187_b1) 2017 Yin (10.1016/j.knosys.2019.105187_b32) 2018; 153 10.1016/j.knosys.2019.105187_b22 10.1016/j.knosys.2019.105187_b21 10.1016/j.knosys.2019.105187_b20 Aggarwal (10.1016/j.knosys.2019.105187_b43) 2015; 17 Davis (10.1016/j.knosys.2019.105187_b45) 2006 Kriegel (10.1016/j.knosys.2019.105187_b48) 2009; vol. 5476 Pidhorskyi (10.1016/j.knosys.2019.105187_b18) 2018 Tang (10.1016/j.knosys.2019.105187_b30) 2017; 241 10.1016/j.knosys.2019.105187_b11 10.1016/j.knosys.2019.105187_b17 Liu (10.1016/j.knosys.2019.105187_b42) 2008 Kawachi (10.1016/j.knosys.2019.105187_b25) 2018 Pimentel (10.1016/j.knosys.2019.105187_b9) 2014; 99 Goodfellow (10.1016/j.knosys.2019.105187_b12) 2014 Yeung (10.1016/j.knosys.2019.105187_b28) 2002 Suh (10.1016/j.knosys.2019.105187_b15) 2016 Ilonen (10.1016/j.knosys.2019.105187_b27) 2006 Keller (10.1016/j.knosys.2019.105187_b44) 2012 Zhou (10.1016/j.knosys.2019.105187_b7) 2019 Silverman (10.1016/j.knosys.2019.105187_b39) 2018 Xu (10.1016/j.knosys.2019.105187_b16) 2018 |
| References_xml | – start-page: 93 year: 2000 end-page: 104 ident: b29 article-title: LOF: identifying density-based local outliers publication-title: ACM SIGMOD International Conference on Management of Data, SIGMOD – volume: 88 start-page: 63 year: 2015 end-page: 77 ident: b34 article-title: Improved principal component analysis for anomaly detection: application to an emergency department publication-title: Comput. Ind. Eng. – start-page: 1037 year: 2012 end-page: 1048 ident: b44 article-title: Hics: High contrast subspaces for density-based outlier ranking publication-title: International Conference on Data Engineering, ICDE – volume: 10 start-page: 42:1 year: 2016 end-page: 42:33 ident: b40 article-title: Less is more: building selective anomaly ensembles publication-title: ACM Trans. Knowl. Discov. Data – start-page: 1577 year: 2017 end-page: 1581 ident: b19 article-title: Abnormal event detection in videos using generative adversarial nets publication-title: International Conference on Image Processing, ICIP – start-page: 1015 year: 2016 end-page: 1022 ident: b15 article-title: Echo-state conditional variational autoencoder for anomaly detection publication-title: International Joint Conference on Neural Networks, IJCNN – start-page: 233 year: 2006 end-page: 240 ident: b45 article-title: The relationship between precision-recall and ROC curves publication-title: International Conference on Machine Learning, ICML – start-page: 413 year: 2008 end-page: 422 ident: b46 article-title: Isolation forest publication-title: International Conference on Data Mining, ICDM – start-page: 2366 year: 2018 end-page: 2370 ident: b25 article-title: Complementary set variational autoencoder for supervised anomaly detection publication-title: International Conference on Acoustics, Speech and Signal Processing, ICASSP – start-page: 622 year: 2018 end-page: 637 ident: b5 article-title: Ganomaly: semi-supervised anomaly detection via adversarial training publication-title: Asian Conference on Computer Vision, ACCV – volume: 15 start-page: 34 year: 2016 end-page: 49 ident: b35 article-title: Iterated robust kernel fuzzy principal component analysis and application to fault detection publication-title: J. Comput. Sci. – reference: B. Zong, Q. Song, M.R. Min, W. Cheng, C. Lumezanu, D. Cho, H. Chen, Deep autoencoding Gaussian mixture model for unsupervised anomaly detection, in: International Conference on Learning Representations, ICLR, 2018. – volume: 18 start-page: 1 year: 2017 end-page: 5 ident: b8 article-title: Imbalanced-learn: a python toolbox to tackle the curse of imbalanced datasets in machine learning publication-title: J. Mach. Learn. Res. – year: 2018 ident: b39 article-title: Density Estimation for Statistics and Data Analysis – reference: I.V. Serban, A. Sordoni, R. Lowe, L. Charlin, J. Pineau, A.C. Courville, Y. Bengio, A hierarchical latent variable encoder-decoder model for generating dialogues, in: AAAI Conference on Artificial Intelligence, AAAI, 2017, pp. 3295–3301. – volume: 3 start-page: 1544 year: 2018 end-page: 1551 ident: b14 article-title: A multimodal anomaly detector for robot-assisted feeding using an LSTM-based variational autoencoder publication-title: IEEE Robot. Autom. Lett. – start-page: 171 year: 2016 end-page: 179 ident: b41 article-title: LODES: local density meets spectral outlier detection publication-title: SIAM International Conference on Data Mining, SDM – start-page: 577 year: 2006 end-page: 580 ident: b27 article-title: Gaussian mixture pdf in one-class classification: computing and utilizing confidence values publication-title: International Conference on Pattern Recognition, ICPR – volume: 13 start-page: 1443 year: 2001 end-page: 1471 ident: b31 article-title: Estimating the support of a high-dimensional distribution publication-title: Neural Comput. – start-page: 344 year: 2017 end-page: 361 ident: b1 article-title: Network intrusion detection based on semi-supervised variational auto-encoder publication-title: European Symposium on Research in Computer Security, ESORICS – volume: 99 start-page: 215 year: 2014 end-page: 249 ident: b9 article-title: A review of novelty detection publication-title: Signal Process. – start-page: 2672 year: 2014 end-page: 2680 ident: b12 article-title: Generative adversarial nets publication-title: Annual Conference on Neural Information Processing Systems, NeurIPS – reference: I. Gulrajani, F. Ahmed, M. Arjovsky, V. Dumoulin, A.C. Courville, Improved training of Wasserstein GANs, in: Annual Conference on Neural Information Processing Systems, NeurIPS, 2017, pp. 5767–5777. – start-page: 187 year: 2018 end-page: 196 ident: b16 article-title: Unsupervised anomaly detection via variational auto-encoder for seasonal KPIs in web applications publication-title: International World Wide Web Conference, WWW – start-page: 6823 year: 2018 end-page: 6834 ident: b18 article-title: Generative probabilistic novelty detection with adversarial autoencoders publication-title: Annual Conference on Neural Information Processing Systems, NeurIPS – volume: 142 start-page: 355 year: 2019 end-page: 368 ident: b3 article-title: Improved nonlinear process monitoring based on ensemble KPCA with local structure analysis publication-title: Chem. Eng. Res. Des. – reference: D.P. Kingma, M. Welling, Auto-encoding variational Bayes, in: International Conference on Learning Representations, ICLR, 2014. – start-page: 52 year: 2018 end-page: 63 ident: b26 article-title: IntroVAE: introspective variational autoencoders for photographic image synthesis publication-title: Annual Conference on Neural Information Processing Systems, NeurIPS – start-page: 1322 year: 2008 end-page: 1328 ident: b51 article-title: ADASYN: adaptive synthetic sampling approach for imbalanced learning publication-title: International Joint Conference on Neural Networks, IJCNN – volume: 15 start-page: 800 year: 2004 end-page: 810 ident: b23 article-title: Variational learning and bits-back coding: an information-theoretic view to Bayesian learning publication-title: IEEE Trans. Neural Netw. – reference: A. Makhzani, J. Shlens, N. Jaitly, I. Goodfellow, Adversarial autoencoders, in: International Conference on Learning Representations, ICLR, 2016. – volume: 20 start-page: 1 year: 2019 end-page: 7 ident: b50 article-title: PyOD: A Python toolbox for scalable outlier detection publication-title: J. Mach. Learn. Res. – start-page: 146 year: 2017 end-page: 157 ident: b4 article-title: Unsupervised anomaly detection with generative adversarial networks to guide marker discovery publication-title: International Conference on Information Processing in Medical Imaging, IPMI – volume: 17 start-page: 24 year: 2015 end-page: 47 ident: b43 article-title: Theoretical foundations and algorithms for outlier ensembles publication-title: SIGKDD Explor. Newsl. – year: 2019 ident: b24 article-title: Generative adversarial active learning for unsupervised outlier detection publication-title: IEEE Trans. Knowl. Data Eng. – volume: 153 start-page: 40 year: 2018 end-page: 52 ident: b32 article-title: Active learning based support vector data description method for robust novelty detection publication-title: Knowl.-Based Syst. – start-page: 444 year: 2008 end-page: 452 ident: b47 article-title: Angle-based outlier detection in high-dimensional data publication-title: ACM Knowledge Discovery and Data Mining, KDD – volume: vol. 5476 start-page: 831 year: 2009 end-page: 838 ident: b48 article-title: Outlier detection in axis-parallel subspaces of high dimensional data publication-title: Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD – volume: 174 start-page: 137 year: 2019 end-page: 143 ident: b6 article-title: Multi-imbalance: An open-source software for multi-class imbalance learning publication-title: Knowl.-Based Syst. – reference: X. Chen, D.P. Kingma, T. Salimans, Y. Duan, P. Dhariwal, J. Schulman, I. Sutskever, P. Abbeel, Variational lossy autoencoder, in: International Conference on Learning Representations, ICLR, 2017. – start-page: 385 year: 2002 end-page: 388 ident: b28 article-title: Parzen-window network intrusion detectors publication-title: International Conference on Pattern Recognition, ICPR – year: 2019 ident: b10 article-title: Deep learning for anomaly detection: a survey – start-page: 413 year: 2008 end-page: 422 ident: b42 article-title: Isolation forest publication-title: International Conference on Data Mining, ICDM – volume: 241 start-page: 171 year: 2017 end-page: 180 ident: b30 article-title: A local density-based approach for outlier detection publication-title: Neurocomputing – start-page: 189 year: 2017 end-page: 217 ident: b33 article-title: Principal component analysis publication-title: Robust Multivariate Analysis – start-page: 59 year: 2012 end-page: 63 ident: b49 article-title: Histogram-based outlier score (hbos): A fast unsupervised anomaly detection algorithm publication-title: German Conference on Artificial Intelligence (KI-2012): Poster and Demo Track – year: 2015 ident: b13 article-title: Variational autoencoder based anomaly detection using reconstruction probability – reference: M. Fraccaro, S.K. Sønderby, U. Paquet, O. Winther, Sequential neural models with stochastic layers, in: Annual Conference on Neural Information Processing Systems NeurIPS, 2016, pp. 2199–2207. – year: 2019 ident: b7 article-title: Deep learning fault diagnosis method based on global optimization gan for unbalanced data publication-title: Knowl.-Based Syst. – volume: 68 start-page: 90 year: 2016 end-page: 113 ident: b2 article-title: Fraud detection system: A survey publication-title: J. Netw. Comput. Appl. – volume: 106 start-page: 27 year: 2017 end-page: 45 ident: b37 article-title: FFT-Based fast bandwidth selector for multivariate kernel density estimation publication-title: Comput. Stat. Data Anal. – year: 2019 ident: 10.1016/j.knosys.2019.105187_b10 – ident: 10.1016/j.knosys.2019.105187_b11 – volume: 106 start-page: 27 year: 2017 ident: 10.1016/j.knosys.2019.105187_b37 article-title: FFT-Based fast bandwidth selector for multivariate kernel density estimation publication-title: Comput. Stat. Data Anal. doi: 10.1016/j.csda.2016.09.001 – year: 2015 ident: 10.1016/j.knosys.2019.105187_b13 – ident: 10.1016/j.knosys.2019.105187_b38 – volume: 68 start-page: 90 year: 2016 ident: 10.1016/j.knosys.2019.105187_b2 article-title: Fraud detection system: A survey publication-title: J. Netw. Comput. Appl. doi: 10.1016/j.jnca.2016.04.007 – start-page: 1577 year: 2017 ident: 10.1016/j.knosys.2019.105187_b19 article-title: Abnormal event detection in videos using generative adversarial nets – year: 2018 ident: 10.1016/j.knosys.2019.105187_b39 – ident: 10.1016/j.knosys.2019.105187_b20 – volume: 88 start-page: 63 year: 2015 ident: 10.1016/j.knosys.2019.105187_b34 article-title: Improved principal component analysis for anomaly detection: application to an emergency department publication-title: Comput. Ind. Eng. doi: 10.1016/j.cie.2015.06.020 – start-page: 2366 year: 2018 ident: 10.1016/j.knosys.2019.105187_b25 article-title: Complementary set variational autoencoder for supervised anomaly detection – start-page: 233 year: 2006 ident: 10.1016/j.knosys.2019.105187_b45 article-title: The relationship between precision-recall and ROC curves – start-page: 622 year: 2018 ident: 10.1016/j.knosys.2019.105187_b5 article-title: Ganomaly: semi-supervised anomaly detection via adversarial training – start-page: 1037 year: 2012 ident: 10.1016/j.knosys.2019.105187_b44 article-title: Hics: High contrast subspaces for density-based outlier ranking – start-page: 444 year: 2008 ident: 10.1016/j.knosys.2019.105187_b47 article-title: Angle-based outlier detection in high-dimensional data – volume: 15 start-page: 800 issue: 4 year: 2004 ident: 10.1016/j.knosys.2019.105187_b23 article-title: Variational learning and bits-back coding: an information-theoretic view to Bayesian learning publication-title: IEEE Trans. Neural Netw. doi: 10.1109/TNN.2004.828762 – volume: 17 start-page: 24 issue: 1 year: 2015 ident: 10.1016/j.knosys.2019.105187_b43 article-title: Theoretical foundations and algorithms for outlier ensembles publication-title: SIGKDD Explor. Newsl. doi: 10.1145/2830544.2830549 – start-page: 413 year: 2008 ident: 10.1016/j.knosys.2019.105187_b42 article-title: Isolation forest – start-page: 93 year: 2000 ident: 10.1016/j.knosys.2019.105187_b29 article-title: LOF: identifying density-based local outliers – start-page: 1322 year: 2008 ident: 10.1016/j.knosys.2019.105187_b51 article-title: ADASYN: adaptive synthetic sampling approach for imbalanced learning – volume: 10 start-page: 42:1 issue: 4 year: 2016 ident: 10.1016/j.knosys.2019.105187_b40 article-title: Less is more: building selective anomaly ensembles publication-title: ACM Trans. Knowl. Discov. Data doi: 10.1145/2890508 – start-page: 146 year: 2017 ident: 10.1016/j.knosys.2019.105187_b4 article-title: Unsupervised anomaly detection with generative adversarial networks to guide marker discovery – start-page: 344 year: 2017 ident: 10.1016/j.knosys.2019.105187_b1 article-title: Network intrusion detection based on semi-supervised variational auto-encoder – ident: 10.1016/j.knosys.2019.105187_b22 doi: 10.1609/aaai.v31i1.10983 – start-page: 6823 year: 2018 ident: 10.1016/j.knosys.2019.105187_b18 article-title: Generative probabilistic novelty detection with adversarial autoencoders – ident: 10.1016/j.knosys.2019.105187_b21 – start-page: 187 year: 2018 ident: 10.1016/j.knosys.2019.105187_b16 article-title: Unsupervised anomaly detection via variational auto-encoder for seasonal KPIs in web applications – start-page: 171 year: 2016 ident: 10.1016/j.knosys.2019.105187_b41 article-title: LODES: local density meets spectral outlier detection – volume: vol. 5476 start-page: 831 year: 2009 ident: 10.1016/j.knosys.2019.105187_b48 article-title: Outlier detection in axis-parallel subspaces of high dimensional data – start-page: 2672 year: 2014 ident: 10.1016/j.knosys.2019.105187_b12 article-title: Generative adversarial nets – start-page: 385 year: 2002 ident: 10.1016/j.knosys.2019.105187_b28 article-title: Parzen-window network intrusion detectors – start-page: 413 year: 2008 ident: 10.1016/j.knosys.2019.105187_b46 article-title: Isolation forest – ident: 10.1016/j.knosys.2019.105187_b36 – volume: 3 start-page: 1544 issue: 3 year: 2018 ident: 10.1016/j.knosys.2019.105187_b14 article-title: A multimodal anomaly detector for robot-assisted feeding using an LSTM-based variational autoencoder publication-title: IEEE Robot. Autom. Lett. doi: 10.1109/LRA.2018.2801475 – start-page: 59 year: 2012 ident: 10.1016/j.knosys.2019.105187_b49 article-title: Histogram-based outlier score (hbos): A fast unsupervised anomaly detection algorithm publication-title: German Conference on Artificial Intelligence (KI-2012): Poster and Demo Track – volume: 142 start-page: 355 year: 2019 ident: 10.1016/j.knosys.2019.105187_b3 article-title: Improved nonlinear process monitoring based on ensemble KPCA with local structure analysis publication-title: Chem. Eng. Res. Des. doi: 10.1016/j.cherd.2018.12.028 – volume: 153 start-page: 40 year: 2018 ident: 10.1016/j.knosys.2019.105187_b32 article-title: Active learning based support vector data description method for robust novelty detection publication-title: Knowl.-Based Syst. doi: 10.1016/j.knosys.2018.04.020 – volume: 99 start-page: 215 year: 2014 ident: 10.1016/j.knosys.2019.105187_b9 article-title: A review of novelty detection publication-title: Signal Process. doi: 10.1016/j.sigpro.2013.12.026 – issn: 1041-4347 year: 2019 ident: 10.1016/j.knosys.2019.105187_b24 article-title: Generative adversarial active learning for unsupervised outlier detection publication-title: IEEE Trans. Knowl. Data Eng. doi: 10.1109/TKDE.2019.2905606 – volume: 13 start-page: 1443 issue: 7 year: 2001 ident: 10.1016/j.knosys.2019.105187_b31 article-title: Estimating the support of a high-dimensional distribution publication-title: Neural Comput. doi: 10.1162/089976601750264965 – start-page: 1015 year: 2016 ident: 10.1016/j.knosys.2019.105187_b15 article-title: Echo-state conditional variational autoencoder for anomaly detection – start-page: 189 year: 2017 ident: 10.1016/j.knosys.2019.105187_b33 article-title: Principal component analysis – ident: 10.1016/j.knosys.2019.105187_b17 – volume: 20 start-page: 1 issue: 96 year: 2019 ident: 10.1016/j.knosys.2019.105187_b50 article-title: PyOD: A Python toolbox for scalable outlier detection publication-title: J. Mach. Learn. Res. – start-page: 52 year: 2018 ident: 10.1016/j.knosys.2019.105187_b26 article-title: IntroVAE: introspective variational autoencoders for photographic image synthesis – volume: 174 start-page: 137 year: 2019 ident: 10.1016/j.knosys.2019.105187_b6 article-title: Multi-imbalance: An open-source software for multi-class imbalance learning publication-title: Knowl.-Based Syst. doi: 10.1016/j.knosys.2019.03.001 – year: 2019 ident: 10.1016/j.knosys.2019.105187_b7 article-title: Deep learning fault diagnosis method based on global optimization gan for unbalanced data publication-title: Knowl.-Based Syst. – volume: 241 start-page: 171 year: 2017 ident: 10.1016/j.knosys.2019.105187_b30 article-title: A local density-based approach for outlier detection publication-title: Neurocomputing doi: 10.1016/j.neucom.2017.02.039 – volume: 15 start-page: 34 year: 2016 ident: 10.1016/j.knosys.2019.105187_b35 article-title: Iterated robust kernel fuzzy principal component analysis and application to fault detection publication-title: J. Comput. Sci. doi: 10.1016/j.jocs.2015.11.005 – start-page: 577 year: 2006 ident: 10.1016/j.knosys.2019.105187_b27 article-title: Gaussian mixture pdf in one-class classification: computing and utilizing confidence values – volume: 18 start-page: 1 issue: 17 year: 2017 ident: 10.1016/j.knosys.2019.105187_b8 article-title: Imbalanced-learn: a python toolbox to tackle the curse of imbalanced datasets in machine learning publication-title: J. Mach. Learn. Res. |
| SSID | ssj0002218 |
| Score | 2.5420249 |
| Snippet | Recently, deep generative models have become increasingly popular in unsupervised anomaly detection. However, deep generative models aim at recovering the data... |
| SourceID | proquest crossref elsevier |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 105187 |
| SubjectTerms | Anomalies Anomaly detection Coders Deep generative model Experiments Normal distribution Novelty detection Outlier detection Prior knowledge Regularization Synthesis Training Variables Variational autoencoder |
| Title | adVAE: A self-adversarial variational autoencoder with Gaussian anomaly prior knowledge for anomaly detection |
| URI | https://dx.doi.org/10.1016/j.knosys.2019.105187 https://www.proquest.com/docview/2376945423 |
| Volume | 190 |
| WOSCitedRecordID | wos000518492400009&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: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1872-7409 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002218 issn: 0950-7051 databaseCode: AIEXJ dateStart: 19950201 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1LbxMxELZCyoELb0RpQT4gLmjR7noTr3uLqpRXFCqRQm4rZ22rG6WbkGyi_hX-LeNn0vIoHLhsItubx8znmfHsPBB6OaHdrshVGU3gfBWBRUxgz8G-ymBQlDRRiTDV9Qd0OMzHY3baan33uTCbGa3r_PKSLf4rq2EMmK1TZ_-B3eFDYQDeA9PhCmyH618xnosvvb5NOF_JmYq4brm84qY7x0a_OO8fXzdzXcVSF5Mw3ti3fL0yKZW8nl9w7fVYVvPl6-B1cwGXdk7IxgRx1bvW7Ue_NNLKUbgy0cFq_-p80-P1-dwpTGNCGzVQbUcGtq7B5_NqWgXcHa9N3MGpX-c8FXAs1ZnfW3kYUmi81NrGLVl_ZBzR2FWflVYa5xTM_yxmV8S1bS_qBG7ySzVgPRLTN0Ah-Kc6gI_phsaJ0-1Xqm4PPxUnZ4NBMeqPR68W3yLdkEw_uHfdWW6hvZR2WN5Ge733_fGHoObT1DiPw-_2eZkmePDnL_6d3XPNAjBmzeg-uuvOI7hncfQAtWT9EN3zvT6wI-IjdGFgdYR7-Dqo8A6o8A6osAYV9qDCDjjYgAoHUGEAVZgLoHqMzk76o-N3kWvVEZWEZE0kMyGoElSSnDJOJAErkpGSJzJJRB6zknWFUh2qn5qnPFNpSVLFu5niVILVLckT1K7ntXyKcDfX0a75JBEiz-Ks5GUnjUGiMEWZitPJPiKekEXp6tjrdiqzwgcsTgtL_kKTv7Dk30dRuGth67jcsJ56HhXOFrU2ZgEYu-HOQ8_SwokFmAc9zrIOnF2e_Xn6AN3Zbp1D1G6Wa_kc3S43TbVavnAY_AHOerc1 |
| linkProvider | Elsevier |
| 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=adVAE%3A+A+self-adversarial+variational+autoencoder+with+Gaussian+anomaly+prior+knowledge+for+anomaly+detection&rft.jtitle=Knowledge-based+systems&rft.au=Wang%2C+Xuhong&rft.au=Du%2C+Ying&rft.au=Lin%2C+Shijie&rft.au=Cui%2C+Ping&rft.date=2020-02-29&rft.pub=Elsevier+Science+Ltd&rft.issn=0950-7051&rft.eissn=1872-7409&rft.volume=190&rft.spage=1&rft_id=info:doi/10.1016%2Fj.knosys.2019.105187&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0950-7051&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0950-7051&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0950-7051&client=summon |