Deep Fuzzy Clustering Network With Matrix Norm Regularization
Recently, deep clustering networks, which able to learn latent embedding and clustering assignment simultaneously, attract lots of attention. Among the deep clustering networks, the suitable regularization term is not only beneficial to training of neural network, but also enhancing clustering perfo...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10443360/ |
| _version_ | 1797292038537871360 |
|---|---|
| author | Feiyu Chen Yan Li Wei Wang |
| author_facet | Feiyu Chen Yan Li Wei Wang |
| author_sort | Feiyu Chen |
| collection | DOAJ |
| description | Recently, deep clustering networks, which able to learn latent embedding and clustering assignment simultaneously, attract lots of attention. Among the deep clustering networks, the suitable regularization term is not only beneficial to training of neural network, but also enhancing clustering performance. In the paper, we propose a deep fuzzy clustering network with mixed matrix norm regularization (DFCNR). Specifically, DFCNR uses the weighted intra-class variance as clustering loss, <inline-formula> <tex-math notation="LaTeX">$\ell _{1,2}$ </tex-math></inline-formula> norm and the Frobenius norm of soft assignment matrix as regularization term, where the minimization of <inline-formula> <tex-math notation="LaTeX">$\ell _{1,2}$ </tex-math></inline-formula> norm aims to achieve balanced assignment, and maximization of Frobenius norm aims to achieve discriminative assignment. Moreover, by solving the quadratic convex constraint optimization problem about soft assignment, we derive the activation function of clustering layer. Extensive experiments conducted on several datasets illustrate the superiority of the proposed approach in comparison with current methods. |
| first_indexed | 2024-03-07T19:46:27Z |
| format | Article |
| id | doaj.art-744b9aee2e094cc19a40b9c52488d621 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-07T19:46:27Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-744b9aee2e094cc19a40b9c52488d6212024-02-29T00:00:48ZengIEEEIEEE Access2169-35362024-01-0112286772868310.1109/ACCESS.2024.336879510443360Deep Fuzzy Clustering Network With Matrix Norm RegularizationFeiyu Chen0Yan Li1https://orcid.org/0009-0002-7311-9179Wei Wang2https://orcid.org/0000-0001-5062-6720National Center for Applied Mathematics in Chongqing, Chongqing Normal University, Chongqing, ChinaSchool of Mathematical Sciences, Chongqing Normal University, Chongqing, ChinaDepartment of Computer Science, Army Medical University, Chongqing, ChinaRecently, deep clustering networks, which able to learn latent embedding and clustering assignment simultaneously, attract lots of attention. Among the deep clustering networks, the suitable regularization term is not only beneficial to training of neural network, but also enhancing clustering performance. In the paper, we propose a deep fuzzy clustering network with mixed matrix norm regularization (DFCNR). Specifically, DFCNR uses the weighted intra-class variance as clustering loss, <inline-formula> <tex-math notation="LaTeX">$\ell _{1,2}$ </tex-math></inline-formula> norm and the Frobenius norm of soft assignment matrix as regularization term, where the minimization of <inline-formula> <tex-math notation="LaTeX">$\ell _{1,2}$ </tex-math></inline-formula> norm aims to achieve balanced assignment, and maximization of Frobenius norm aims to achieve discriminative assignment. Moreover, by solving the quadratic convex constraint optimization problem about soft assignment, we derive the activation function of clustering layer. Extensive experiments conducted on several datasets illustrate the superiority of the proposed approach in comparison with current methods.https://ieeexplore.ieee.org/document/10443360/Autoencoderdeep fuzzy clusteringdeep learningmatrix norm regularization |
| spellingShingle | Feiyu Chen Yan Li Wei Wang Deep Fuzzy Clustering Network With Matrix Norm Regularization IEEE Access Autoencoder deep fuzzy clustering deep learning matrix norm regularization |
| title | Deep Fuzzy Clustering Network With Matrix Norm Regularization |
| title_full | Deep Fuzzy Clustering Network With Matrix Norm Regularization |
| title_fullStr | Deep Fuzzy Clustering Network With Matrix Norm Regularization |
| title_full_unstemmed | Deep Fuzzy Clustering Network With Matrix Norm Regularization |
| title_short | Deep Fuzzy Clustering Network With Matrix Norm Regularization |
| title_sort | deep fuzzy clustering network with matrix norm regularization |
| topic | Autoencoder deep fuzzy clustering deep learning matrix norm regularization |
| url | https://ieeexplore.ieee.org/document/10443360/ |
| work_keys_str_mv | AT feiyuchen deepfuzzyclusteringnetworkwithmatrixnormregularization AT yanli deepfuzzyclusteringnetworkwithmatrixnormregularization AT weiwang deepfuzzyclusteringnetworkwithmatrixnormregularization |