Cloud-VAE: Variational autoencoder with concepts embedded
•The initial concepts in latent space are described as prior distribution obtained by the proposed cloud model-based clustering algorithm.•Variational lower bound of Cloud-VAE is derived to guide training process and re-construct concepts of latent space, so that the mutual mapping between latent sp...
Uložené v:
| Vydané v: | Pattern recognition Ročník 140; s. 109530 |
|---|---|
| Hlavní autori: | , , , , , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
Elsevier Ltd
01.08.2023
|
| Predmet: | |
| ISSN: | 0031-3203, 1873-5142 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | •The initial concepts in latent space are described as prior distribution obtained by the proposed cloud model-based clustering algorithm.•Variational lower bound of Cloud-VAE is derived to guide training process and re-construct concepts of latent space, so that the mutual mapping between latent space and concept space is established.•Reparameterization trick based forward cloud transformation algorithm is designed to constrain the representations range of latent space by increasing the randomness of latent variables.•The experimental results on six benchmark datasets show that Cloud-VAE has good clustering and reconstruction performance. Compared with the deep clustering methods VaDE and GMVAE, Cloud-VAE improved the NMI by 22.9% and 19.9% respectively.•Cloud-VAE can explicitly explain the aggregation process of the model, and other interpretable latent representations are found on top of the existed.
Variational Autoencoder (VAE) has been widely and successfully used in learning coherent latent representation of data. However, the lack of interpretability in the latent space constructed by the VAE under the prior distribution is still an urgent problem. This paper proposes a VAE with understandable concept embedding named Cloud-VAE, which constructs interpretable latent space by disentangling the latent variables and considering their uncertainty based on cloud model. Firstly, cloud model-based clustering algorithm cast initial constraint of latent space into a prior distribution of concept which can be embedded into the latent space of the VAE to disentangle the latent variables. Secondly, reparameterization trick based on forward cloud transformation algorithm is designed to estimate the latent space concept by increasing the randomness of latent variables. Furthermore, variational lower bound of Cloud-VAE is derived to guide the training process to construct concepts of latent space, realizing the mutual mapping between latent space and concept space. Finally, experimental results on 6 benchmark datasets show that Cloud-VAE has good clustering and reconstruction performance, which can explicitly explain the aggregation process of the model and discover more interpretable disentangled representations. |
|---|---|
| AbstractList | •The initial concepts in latent space are described as prior distribution obtained by the proposed cloud model-based clustering algorithm.•Variational lower bound of Cloud-VAE is derived to guide training process and re-construct concepts of latent space, so that the mutual mapping between latent space and concept space is established.•Reparameterization trick based forward cloud transformation algorithm is designed to constrain the representations range of latent space by increasing the randomness of latent variables.•The experimental results on six benchmark datasets show that Cloud-VAE has good clustering and reconstruction performance. Compared with the deep clustering methods VaDE and GMVAE, Cloud-VAE improved the NMI by 22.9% and 19.9% respectively.•Cloud-VAE can explicitly explain the aggregation process of the model, and other interpretable latent representations are found on top of the existed.
Variational Autoencoder (VAE) has been widely and successfully used in learning coherent latent representation of data. However, the lack of interpretability in the latent space constructed by the VAE under the prior distribution is still an urgent problem. This paper proposes a VAE with understandable concept embedding named Cloud-VAE, which constructs interpretable latent space by disentangling the latent variables and considering their uncertainty based on cloud model. Firstly, cloud model-based clustering algorithm cast initial constraint of latent space into a prior distribution of concept which can be embedded into the latent space of the VAE to disentangle the latent variables. Secondly, reparameterization trick based on forward cloud transformation algorithm is designed to estimate the latent space concept by increasing the randomness of latent variables. Furthermore, variational lower bound of Cloud-VAE is derived to guide the training process to construct concepts of latent space, realizing the mutual mapping between latent space and concept space. Finally, experimental results on 6 benchmark datasets show that Cloud-VAE has good clustering and reconstruction performance, which can explicitly explain the aggregation process of the model and discover more interpretable disentangled representations. |
| ArticleNumber | 109530 |
| Author | Wang, Guoyin Liu, Zitu Liu, Qun Guo, Yike Liu, Yue Li, Shuang Yu, Zhenyao |
| Author_xml | – sequence: 1 givenname: Yue surname: Liu fullname: Liu, Yue organization: School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China – sequence: 2 givenname: Zitu surname: Liu fullname: Liu, Zitu organization: School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China – sequence: 3 givenname: Shuang surname: Li fullname: Li, Shuang organization: School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China – sequence: 4 givenname: Zhenyao surname: Yu fullname: Yu, Zhenyao organization: School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China – sequence: 5 givenname: Yike surname: Guo fullname: Guo, Yike organization: The Department of Computing, Imperial College, London SW7 2AZ, U.K – sequence: 6 givenname: Qun surname: Liu fullname: Liu, Qun organization: The Chongqing Key Laboratory of Computational Intelligence, Chongqing University of Posts and Telecommunications, Chongqing 400065, China – sequence: 7 givenname: Guoyin surname: Wang fullname: Wang, Guoyin organization: The Chongqing Key Laboratory of Computational Intelligence, Chongqing University of Posts and Telecommunications, Chongqing 400065, China |
| BookMark | eNqFkMtOwzAQRS1UJNrCH7DID6SMH62bLpCqqDykSmygW8uxJ-AojSvbBfH3pIQVC1iNdEfnauZMyKjzHRJyTWFGgS5umtlBJ-NfZwwY76NizuGMjOlS8nxOBRuRMQCnOWfAL8gkxgaAyn4xJkXZ-qPNd-vNKtvp4HRyvtNtpo_JY2e8xZB9uPSWGd8ZPKSY4b5Ca9FekvNatxGvfuaUvNxtnsuHfPt0_1iut7lhjKYckS7tghf1XCKvhBEgEDlHjYAM5KIqGDeWSoFSWltRUSCrZA0omBC1LPiUrIZeE3yMAWtlXPo-MwXtWkVBnSSoRg0S1EmCGiT0sPgFH4Lb6_D5H3Y7YNg_9u4wqGhcrwOtC2iSst79XfAFFjR6Lg |
| CitedBy_id | crossref_primary_10_1049_gtd2_70068 crossref_primary_10_1007_s10489_024_05791_6 crossref_primary_10_1016_j_apenergy_2024_124385 crossref_primary_10_3390_e27030283 crossref_primary_10_3390_rs16111963 crossref_primary_10_1016_j_microc_2025_114814 crossref_primary_10_3390_jtaer20030220 crossref_primary_10_1016_j_ins_2024_120273 crossref_primary_10_1016_j_neucom_2024_127761 crossref_primary_10_1016_j_neucom_2025_130752 crossref_primary_10_1007_s11431_024_2732_9 crossref_primary_10_1016_j_eswa_2025_128578 crossref_primary_10_1016_j_neucom_2025_130129 |
| Cites_doi | 10.3390/land11010060 10.1007/s11004-021-09979-1 10.1016/j.patcog.2017.11.019 10.1109/TPAMI.2020.3026079 10.1016/j.ins.2018.05.053 10.1016/j.patcog.2020.107514 10.1016/j.patcog.2021.108191 10.1016/j.patcog.2018.04.007 10.1109/ACCESS.2020.2977671 10.1080/00207543.2019.1662133 10.1016/j.patcog.2021.108334 10.1016/j.patcog.2019.107166 10.1016/j.knosys.2023.110261 |
| ContentType | Journal Article |
| Copyright | 2023 Elsevier Ltd |
| Copyright_xml | – notice: 2023 Elsevier Ltd |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.patcog.2023.109530 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1873-5142 |
| ExternalDocumentID | 10_1016_j_patcog_2023_109530 S0031320323002303 |
| GroupedDBID | --K --M -D8 -DT -~X .DC .~1 0R~ 123 1B1 1RT 1~. 1~5 29O 4.4 457 4G. 53G 5VS 7-5 71M 8P~ 9JN AABNK AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABEFU ABFNM ABFRF ABHFT ABJNI ABMAC ABTAH ABXDB ABYKQ ACBEA ACDAQ ACGFO ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADJOM ADMUD ADMXK ADTZH AEBSH AECPX AEFWE AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F0J F5P FD6 FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q G8K GBLVA GBOLZ HLZ HVGLF HZ~ H~9 IHE J1W JJJVA KOM KZ1 LG9 LMP LY1 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG RNS ROL RPZ SBC SDF SDG SDP SDS SES SEW SPC SPCBC SST SSV SSZ T5K TN5 UNMZH VOH WUQ XJE XPP ZMT ZY4 ~G- 9DU AATTM AAXKI AAYWO AAYXX ABDPE ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD |
| ID | FETCH-LOGICAL-c221t-ee18d639f57e3b4c404ee33eae0e2076b923cd174e77ddb149e2b7f0e4244f793 |
| ISSN | 0031-3203 |
| IngestDate | Sat Nov 29 07:30:33 EST 2025 Tue Nov 18 22:35:41 EST 2025 Fri Feb 23 02:35:21 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Variational autoencoder Cloud Model Concept embedded Deep Learning Interpretability Disentangled representation |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c221t-ee18d639f57e3b4c404ee33eae0e2076b923cd174e77ddb149e2b7f0e4244f793 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_patcog_2023_109530 crossref_primary_10_1016_j_patcog_2023_109530 elsevier_sciencedirect_doi_10_1016_j_patcog_2023_109530 |
| PublicationCentury | 2000 |
| PublicationDate | August 2023 2023-08-00 |
| PublicationDateYYYYMMDD | 2023-08-01 |
| PublicationDate_xml | – month: 08 year: 2023 text: August 2023 |
| PublicationDecade | 2020 |
| PublicationTitle | Pattern recognition |
| PublicationYear | 2023 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Gulrajani, Kumar, Ahmed (bib0011) 2017 Jiang, Zheng, Tan (bib0024) 2017 Xie, Girshick, Farhadi (bib0029) 2016 Joo, Lee, Park (bib0019) 2020; 107 Liu, Liu, Zhao (bib0020) 2020; 100 Atanov, Struminsky, Welling (bib0021) 2019 Li, Zhou, Xun (bib0036) 2022; 11 Dupont (bib0035) 2018 Yang, Deng, Liu (bib0033) 2020; 44 Liu, Ng, Zeng (bib0008) 2018; 76 Chen, Kingma, Salimans (bib0009) 2017 Zhou, Lai, Miao (bib0022) 2020; 507 Zhu, Min, Kadav (bib0005) 2020 Kusiak (bib0002) 2020; 58 Xiong, Zuo, Luo (bib0004) 2022; 54 Kipf, Welling (bib0015) 2016 Yang, Deng, Zheng (bib0031) 2019 Cai, Gao, Ji (bib0014) 2019 Dilokthanakul, Mediano, Garnelo (bib0025) 2017 Guo, Gao, Liu (bib0030) 2017 Kingma, Welling (bib0001) 2014 Ding, Xu, Xu (bib0028) 2020 Greco, Guzzo, Nardiello (bib0006) 2020 Zhang, Gao (bib0007) 2021 Demšar (bib0038) 2006; 7 He, Xu, Huang (bib0017) 2022; 121 Tran, Vu, Vo (bib0003) 2022 Sabathé, Coutinho, Schuller (bib0018) 2017 Yang, Deng, Wei (bib0032) 2020; 33 Burda, Grosse, Salakhutdinov (bib0016) 2016 Guo, Dai (bib0012) 2022; 122 Liu, Liu, Li (bib0037) 2023; 263 Nguyen, Nguyen, Liew (bib0010) 2018; 81 Guo, Zhou, Chen (bib0023) 2020; 8 Burgess, Higgins, Pal (bib0026) 2017 Louizos, Swersky, Li (bib0013) 2016 Kim, Mnih (bib0034) 2018 Chen, Li, Grosse (bib0027) 2018 Zhang (10.1016/j.patcog.2023.109530_bib0007) 2021 Greco (10.1016/j.patcog.2023.109530_bib0006) 2020 Nguyen (10.1016/j.patcog.2023.109530_bib0010) 2018; 81 Kim (10.1016/j.patcog.2023.109530_bib0034) 2018 Liu (10.1016/j.patcog.2023.109530_bib0008) 2018; 76 Guo (10.1016/j.patcog.2023.109530_bib0030) 2017 Yang (10.1016/j.patcog.2023.109530_bib0033) 2020; 44 Burda (10.1016/j.patcog.2023.109530_bib0016) 2016 Sabathé (10.1016/j.patcog.2023.109530_bib0018) 2017 Jiang (10.1016/j.patcog.2023.109530_bib0024) 2017 Xiong (10.1016/j.patcog.2023.109530_bib0004) 2022; 54 Atanov (10.1016/j.patcog.2023.109530_bib0021) 2019 Guo (10.1016/j.patcog.2023.109530_bib0012) 2022; 122 Guo (10.1016/j.patcog.2023.109530_bib0023) 2020; 8 Chen (10.1016/j.patcog.2023.109530_bib0027) 2018 Dilokthanakul (10.1016/j.patcog.2023.109530_bib0025) 2017 Ding (10.1016/j.patcog.2023.109530_bib0028) 2020 Louizos (10.1016/j.patcog.2023.109530_bib0013) 2016 Tran (10.1016/j.patcog.2023.109530_bib0003) 2022 Demšar (10.1016/j.patcog.2023.109530_bib0038) 2006; 7 Zhou (10.1016/j.patcog.2023.109530_bib0022) 2020; 507 Chen (10.1016/j.patcog.2023.109530_bib0009) 2017 Dupont (10.1016/j.patcog.2023.109530_bib0035) 2018 Yang (10.1016/j.patcog.2023.109530_bib0031) 2019 Joo (10.1016/j.patcog.2023.109530_bib0019) 2020; 107 Kingma (10.1016/j.patcog.2023.109530_bib0001) 2014 Burgess (10.1016/j.patcog.2023.109530_bib0026) 2017 Liu (10.1016/j.patcog.2023.109530_bib0020) 2020; 100 Yang (10.1016/j.patcog.2023.109530_bib0032) 2020; 33 Cai (10.1016/j.patcog.2023.109530_bib0014) 2019 Zhu (10.1016/j.patcog.2023.109530_bib0005) 2020 He (10.1016/j.patcog.2023.109530_bib0017) 2022; 121 Kusiak (10.1016/j.patcog.2023.109530_bib0002) 2020; 58 Xie (10.1016/j.patcog.2023.109530_bib0029) 2016 Li (10.1016/j.patcog.2023.109530_bib0036) 2022; 11 Gulrajani (10.1016/j.patcog.2023.109530_bib0011) 2017 Kipf (10.1016/j.patcog.2023.109530_bib0015) 2016 Liu (10.1016/j.patcog.2023.109530_bib0037) 2023; 263 |
| References_xml | – start-page: 7920 year: 2020 end-page: 7929 ident: bib0028 article-title: Guided variational autoencoder for disentanglement learning publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition – year: 2014 ident: bib0001 article-title: Auto-encoding variational bayes publication-title: Proceedings of the International Conference on Learning Representations – volume: 107 year: 2020 ident: bib0019 article-title: Dirichlet variational autoencoder publication-title: Pattern Recognit. – volume: 44 start-page: 1992 year: 2020 end-page: 2003 ident: bib0033 article-title: Heterogeneous graph attention network for unsupervised multiple-target domain adaptation publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 100 start-page: 107166 year: 2020 ident: bib0020 article-title: Discovering influential factors in variational autoencoders publication-title: Pattern Recognit. – year: 2019 ident: bib0021 article-title: The deep weight prior publication-title: Proceedings of the International Conference on Learning Representations – start-page: 1965 year: 2017 end-page: 1972 ident: bib0024 article-title: Variational deep embedding: an unsupervised and generative approach to clustering publication-title: Proceedings of the 26th International Joint Conference on Artificial Intelligence – start-page: 2649 year: 2018 end-page: 2658 ident: bib0034 article-title: Disentangling by factorising publication-title: Proceedings of the International Conference on Machine Learning – start-page: 1 year: 2016 end-page: 14 ident: bib0016 article-title: Importance weighted autoencoders publication-title: Proceedings of the International Conference on Learning Representations – volume: 507 start-page: 553 year: 2020 end-page: 573 ident: bib0022 article-title: Multigranulation rough-fuzzy clustering based on shadowed sets publication-title: Inf. Sci. – year: 2017 ident: bib0011 article-title: Pixelvae: a latent variable model for natural images publication-title: Proceedings of the International Conference on Learning Representations – volume: 7 start-page: 1 year: 2006 end-page: 30 ident: bib0038 article-title: Statistical comparisons of classifiers over multiple data sets publication-title: J. Mach. Learn. Res. – year: 2017 ident: bib0009 article-title: Variational lossy autoencoder publication-title: Proceedings of the International Conference on Learning Representations – start-page: 2615 year: 2018 end-page: 2625 ident: bib0027 article-title: Isolating sources of disentanglement in VAEs publication-title: Proceedings of the 32nd International Conference on Neural Information Processing Systems – start-page: 630 year: 2019 end-page: 638 ident: bib0014 article-title: Multi-stage variational autoencoders for coarse-to-fine image generation publication-title: Proceedings of the SIAM International Conference on Data Mining, Society for Industrial and Applied Mathematics – start-page: 708 year: 2018 end-page: 718 ident: bib0035 article-title: Learning disentangled joint continuous and discrete representations publication-title: Proceedings of the 32nd International Conference on Neural Information Processing Systems – start-page: 1 year: 2017 end-page: 11 ident: bib0026 article-title: Understanding disentangling in β-VAE publication-title: Workshop on Learning Disentangled Representations at the 31st Conference on Neural Information Processing Systems – volume: 76 start-page: 367 year: 2018 end-page: 379 ident: bib0008 article-title: Weighted variational model for selective image segmentation with application to medical images publication-title: Pattern Recognit. – volume: 121 year: 2022 ident: bib0017 article-title: Creating synthetic minority class samples based on autoencoder extreme learning machine publication-title: Pattern Recognit. – start-page: 1 year: 2016 end-page: 3 ident: bib0015 article-title: Variational graph autoencoders publication-title: NIPS Workshop on Bayesian Deep Learning – volume: 81 start-page: 280 year: 2018 end-page: 293 ident: bib0010 article-title: Variational inference based bayes online classifiers with concept drift adaptation publication-title: Pattern Recognit. – volume: 8 start-page: 43992 year: 2020 end-page: 44400 ident: bib0023 article-title: Variational autoencoder with optimizing gaussian mixture model priors publication-title: IEEE Access – start-page: 188 year: 2020 end-page: 197 ident: bib0006 article-title: FD-VAE: a feature driven VAE architecture for flexible synthetic data generation publication-title: Proceedings of the International Conference on Database and Expert Systems Applications – volume: 54 start-page: 783 year: 2022 end-page: 806 ident: bib0004 article-title: A physically constrained variational autoencoder for geochemical pattern recognition publication-title: Math. Geosci. – volume: 33 start-page: 9098 year: 2020 end-page: 9108 ident: bib0032 article-title: Adversarial learning for robust deep clustering publication-title: Adv. Neural Inf. Process. Syst. – start-page: 478 year: 2016 end-page: 487 ident: bib0029 article-title: Unsupervised deep embedding for clustering analysis publication-title: Proceedings of the International conference on machine learning – start-page: 4066 year: 2019 end-page: 4075 ident: bib0031 article-title: Deep spectral clustering using dual autoencoder network publication-title: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition – volume: 122 year: 2022 ident: bib0012 article-title: Graph clustering via variational graph embedding publication-title: Pattern Recognit. – volume: 58 start-page: 1594 year: 2020 end-page: 1604 ident: bib0002 article-title: Convolutional and generative adversarial neural networks in manufacturing publication-title: Int. J. Prod. Res. – start-page: 6538 year: 2020 end-page: 6547 ident: bib0005 article-title: S3vae: self-supervised sequential vae for representation disentanglement and data generation publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition – start-page: 1753 year: 2017 end-page: 1759 ident: bib0030 article-title: Improved deep embedded clustering with local structure preservation – year: 2021 ident: bib0007 article-title: Defending adversaries using unsupervised feature clustering VAE publication-title: Proceedings of the International Conference on Machine Learning 2021 Workshop on Adversarial Machine Learning – volume: 11 start-page: 60 year: 2022 ident: bib0036 article-title: Evaluation of rural landscape resources based on cloud model and probabilistic linguistic term set publication-title: Land – volume: 263 start-page: 110261 year: 2023 ident: bib0037 article-title: Cloud-cluster: an uncertainty clustering algorithm based on cloud model publication-title: Knowl. Based Syst. – year: 2022 ident: bib0003 article-title: Anomaly analysis in images and videos: a comprehensive review publication-title: ACM Comput. Surv. CSUR – year: 2016 ident: bib0013 article-title: The variational fair autoencoder publication-title: Proceedings of the International Conference on Learning Representations – start-page: 3467 year: 2017 end-page: 3474 ident: bib0018 article-title: Deep recurrent music writer: memory-enhanced variational autoencoder-based musical score composition and an objective measure publication-title: Proceedings of the International Joint Conference on Neural Networks – start-page: 1 year: 2017 end-page: 12 ident: bib0025 article-title: Deep unsupervised clustering with gaussian mixture variational autoencoders publication-title: Proceedings of the International Conference on Learning Representations – year: 2022 ident: 10.1016/j.patcog.2023.109530_bib0003 article-title: Anomaly analysis in images and videos: a comprehensive review – start-page: 1 year: 2017 ident: 10.1016/j.patcog.2023.109530_bib0026 article-title: Understanding disentangling in β-VAE – start-page: 1 year: 2017 ident: 10.1016/j.patcog.2023.109530_bib0025 article-title: Deep unsupervised clustering with gaussian mixture variational autoencoders – year: 2016 ident: 10.1016/j.patcog.2023.109530_bib0013 article-title: The variational fair autoencoder – start-page: 2615 year: 2018 ident: 10.1016/j.patcog.2023.109530_bib0027 article-title: Isolating sources of disentanglement in VAEs – start-page: 4066 year: 2019 ident: 10.1016/j.patcog.2023.109530_bib0031 article-title: Deep spectral clustering using dual autoencoder network – volume: 11 start-page: 60 issue: 1 year: 2022 ident: 10.1016/j.patcog.2023.109530_bib0036 article-title: Evaluation of rural landscape resources based on cloud model and probabilistic linguistic term set publication-title: Land doi: 10.3390/land11010060 – volume: 54 start-page: 783 year: 2022 ident: 10.1016/j.patcog.2023.109530_bib0004 article-title: A physically constrained variational autoencoder for geochemical pattern recognition publication-title: Math. Geosci. doi: 10.1007/s11004-021-09979-1 – volume: 76 start-page: 367 year: 2018 ident: 10.1016/j.patcog.2023.109530_bib0008 article-title: Weighted variational model for selective image segmentation with application to medical images publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2017.11.019 – start-page: 630 year: 2019 ident: 10.1016/j.patcog.2023.109530_bib0014 article-title: Multi-stage variational autoencoders for coarse-to-fine image generation – start-page: 1 year: 2016 ident: 10.1016/j.patcog.2023.109530_bib0015 article-title: Variational graph autoencoders – volume: 44 start-page: 1992 issue: 4 year: 2020 ident: 10.1016/j.patcog.2023.109530_bib0033 article-title: Heterogeneous graph attention network for unsupervised multiple-target domain adaptation publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2020.3026079 – volume: 507 start-page: 553 year: 2020 ident: 10.1016/j.patcog.2023.109530_bib0022 article-title: Multigranulation rough-fuzzy clustering based on shadowed sets publication-title: Inf. Sci. doi: 10.1016/j.ins.2018.05.053 – start-page: 6538 year: 2020 ident: 10.1016/j.patcog.2023.109530_bib0005 article-title: S3vae: self-supervised sequential vae for representation disentanglement and data generation – start-page: 3467 year: 2017 ident: 10.1016/j.patcog.2023.109530_bib0018 article-title: Deep recurrent music writer: memory-enhanced variational autoencoder-based musical score composition and an objective measure – volume: 33 start-page: 9098 year: 2020 ident: 10.1016/j.patcog.2023.109530_bib0032 article-title: Adversarial learning for robust deep clustering publication-title: Adv. Neural Inf. Process. Syst. – volume: 107 year: 2020 ident: 10.1016/j.patcog.2023.109530_bib0019 article-title: Dirichlet variational autoencoder publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2020.107514 – year: 2019 ident: 10.1016/j.patcog.2023.109530_bib0021 article-title: The deep weight prior – volume: 121 year: 2022 ident: 10.1016/j.patcog.2023.109530_bib0017 article-title: Creating synthetic minority class samples based on autoencoder extreme learning machine publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2021.108191 – start-page: 188 year: 2020 ident: 10.1016/j.patcog.2023.109530_bib0006 article-title: FD-VAE: a feature driven VAE architecture for flexible synthetic data generation – year: 2017 ident: 10.1016/j.patcog.2023.109530_bib0011 article-title: Pixelvae: a latent variable model for natural images – start-page: 1 year: 2016 ident: 10.1016/j.patcog.2023.109530_bib0016 article-title: Importance weighted autoencoders – start-page: 708 year: 2018 ident: 10.1016/j.patcog.2023.109530_bib0035 article-title: Learning disentangled joint continuous and discrete representations – start-page: 1965 year: 2017 ident: 10.1016/j.patcog.2023.109530_bib0024 article-title: Variational deep embedding: an unsupervised and generative approach to clustering – year: 2017 ident: 10.1016/j.patcog.2023.109530_bib0009 article-title: Variational lossy autoencoder – start-page: 2649 year: 2018 ident: 10.1016/j.patcog.2023.109530_bib0034 article-title: Disentangling by factorising – volume: 81 start-page: 280 year: 2018 ident: 10.1016/j.patcog.2023.109530_bib0010 article-title: Variational inference based bayes online classifiers with concept drift adaptation publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2018.04.007 – year: 2021 ident: 10.1016/j.patcog.2023.109530_bib0007 article-title: Defending adversaries using unsupervised feature clustering VAE – volume: 8 start-page: 43992 year: 2020 ident: 10.1016/j.patcog.2023.109530_bib0023 article-title: Variational autoencoder with optimizing gaussian mixture model priors publication-title: IEEE Access doi: 10.1109/ACCESS.2020.2977671 – start-page: 7920 year: 2020 ident: 10.1016/j.patcog.2023.109530_bib0028 article-title: Guided variational autoencoder for disentanglement learning – start-page: 1753 year: 2017 ident: 10.1016/j.patcog.2023.109530_bib0030 article-title: Improved deep embedded clustering with local structure preservation – volume: 58 start-page: 1594 issue: 5 year: 2020 ident: 10.1016/j.patcog.2023.109530_bib0002 article-title: Convolutional and generative adversarial neural networks in manufacturing publication-title: Int. J. Prod. Res. doi: 10.1080/00207543.2019.1662133 – volume: 122 year: 2022 ident: 10.1016/j.patcog.2023.109530_bib0012 article-title: Graph clustering via variational graph embedding publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2021.108334 – volume: 100 start-page: 107166 year: 2020 ident: 10.1016/j.patcog.2023.109530_bib0020 article-title: Discovering influential factors in variational autoencoders publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2019.107166 – volume: 263 start-page: 110261 year: 2023 ident: 10.1016/j.patcog.2023.109530_bib0037 article-title: Cloud-cluster: an uncertainty clustering algorithm based on cloud model publication-title: Knowl. Based Syst. doi: 10.1016/j.knosys.2023.110261 – volume: 7 start-page: 1 year: 2006 ident: 10.1016/j.patcog.2023.109530_bib0038 article-title: Statistical comparisons of classifiers over multiple data sets publication-title: J. Mach. Learn. Res. – year: 2014 ident: 10.1016/j.patcog.2023.109530_bib0001 article-title: Auto-encoding variational bayes – start-page: 478 year: 2016 ident: 10.1016/j.patcog.2023.109530_bib0029 article-title: Unsupervised deep embedding for clustering analysis |
| SSID | ssj0017142 |
| Score | 2.5364597 |
| Snippet | •The initial concepts in latent space are described as prior distribution obtained by the proposed cloud model-based clustering algorithm.•Variational lower... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 109530 |
| SubjectTerms | Cloud Model Concept embedded Deep Learning Interpretability Disentangled representation Variational autoencoder |
| Title | Cloud-VAE: Variational autoencoder with concepts embedded |
| URI | https://dx.doi.org/10.1016/j.patcog.2023.109530 |
| Volume | 140 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: ScienceDirect database customDbUrl: eissn: 1873-5142 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017142 issn: 0031-3203 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1LT9wwELaWx4ELUKDiUaocuCGjJE7WCYdKK7RVWyGExEMrLpHjTLqLlmQFCYJ_33FsZ3cLakslLtHKijfRfNaXmfHMZ0IOchl0BUhGu7lgNEi9kMYZeFSgsxzneTf2RaMze8rPzqLBID7vdL7YXpjHMS-K6Okpnrwr1DiGYKvW2TfA3f4pDuBvBB2vCDte_wn4k3FZZ_S611fB_jWGwjbdJ-qqVLKVSj3CVpyropaHQ7hLAQlo7szO80Z4UzW7mAqj6X796ahumLuG30ZuRlU9HWoSq8NamG9jc_pXc9cQimdRzuYbfNZWu5kkmG2EmVYdNcTKPMp8V3MVaC6NOKPoj82TrRZnekHcOodwezTBD1D580g9WCldhWbTZl4S-0IrTroM4ycVQ7EFsuTzMEZWW-p97w9-tPtI3Au0Xrx5Pds82VT4vXzW687JjMNxuU5WTaTg9DTCH0gHig2yZk_hcAwpb5K4BfzYmYHbmYHbUXA7Fm7Hwr1Frr72L0--UXMgBpW-71UUwIsydCnzkANLAxm4AQBjIMAF3-XdFL11mWGMCZxnWYrBL_gpz11Q3Yw5MvFHsliUBWwTRwpIw8jNpMD4PuNCpMyTITrDXAnCecEOYdYSiTRq8erQknFiywJvE22_RNkv0fbbIbSdNdFqKX-5n1sjJ8bj055cguvijzN3_3vmHlmZLutPZLG6r2GfLMvHavRw_9ksoF8lPnoB |
| 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=Cloud-VAE%3A+Variational+autoencoder+with+concepts+embedded&rft.jtitle=Pattern+recognition&rft.au=Liu%2C+Yue&rft.au=Liu%2C+Zitu&rft.au=Li%2C+Shuang&rft.au=Yu%2C+Zhenyao&rft.date=2023-08-01&rft.pub=Elsevier+Ltd&rft.issn=0031-3203&rft.eissn=1873-5142&rft.volume=140&rft_id=info:doi/10.1016%2Fj.patcog.2023.109530&rft.externalDocID=S0031320323002303 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0031-3203&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0031-3203&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0031-3203&client=summon |