Stratified Feature Sampling for Semi-Supervised Ensemble Clustering
Ensemble Clustering (EC), which seeks to generate a consensus clustering by integrating multiple base clusterings, has attracted increasing attentions. However, traditional EC methods typically have three main limitations: (1) High dimensional data present a huge challenge to ensemble clustering met...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8825848/ |
| _version_ | 1819174615400841216 |
|---|---|
| author | Jialin Tian Yazhou Ren Xiang Cheng |
| author_facet | Jialin Tian Yazhou Ren Xiang Cheng |
| author_sort | Jialin Tian |
| collection | DOAJ |
| description | Ensemble Clustering (EC), which seeks to generate a consensus clustering by integrating multiple base clusterings, has attracted increasing attentions. However, traditional EC methods typically have three main limitations: (1) High dimensional data present a huge challenge to ensemble clustering methods. (2) Most EC algorithms can not use prior information, e.g., pairwise constraints, to enhance the clustering performance. (3) Even in existing semi-supervised ensemble clustering methods, prior information is not sufficiently used, e.g., only used in generating base clusterings. To alleviate these problems, we propose Stratified Feature Sampling for Semi-Supervised Ensemble Clustering (SFS<sup>3</sup>EC). Firstly, we develop a novel stratified feature sampling method, which can cope with high dimensional data, guarantee the diversity of base clusterings, and reduce the risk that some features are not selected at the same time. Secondly, semi-supervised clustering, i.e., constraint propagation, is applied to obtain base clusterings. Finally, we propose to utilize prior information in both the base clustering generating process and the consensus process, which guarantees that prior information is sufficiently used. We conduct a series of experiments on ten real-world data sets to demonstrate the effectiveness of the proposed model. |
| first_indexed | 2024-12-22T20:41:47Z |
| format | Article |
| id | doaj.art-5aa9d969ad3e4d09980f82f7fc8493fb |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-22T20:41:47Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-5aa9d969ad3e4d09980f82f7fc8493fb2022-12-21T18:13:19ZengIEEEIEEE Access2169-35362019-01-01712866912867510.1109/ACCESS.2019.29395818825848Stratified Feature Sampling for Semi-Supervised Ensemble ClusteringJialin Tian0Yazhou Ren1https://orcid.org/0000-0001-7705-4603Xiang Cheng2School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, ChinaSchool of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, ChinaDepartment of Computer Science, Virginia Tech, Blacksburg, VA, USAEnsemble Clustering (EC), which seeks to generate a consensus clustering by integrating multiple base clusterings, has attracted increasing attentions. However, traditional EC methods typically have three main limitations: (1) High dimensional data present a huge challenge to ensemble clustering methods. (2) Most EC algorithms can not use prior information, e.g., pairwise constraints, to enhance the clustering performance. (3) Even in existing semi-supervised ensemble clustering methods, prior information is not sufficiently used, e.g., only used in generating base clusterings. To alleviate these problems, we propose Stratified Feature Sampling for Semi-Supervised Ensemble Clustering (SFS<sup>3</sup>EC). Firstly, we develop a novel stratified feature sampling method, which can cope with high dimensional data, guarantee the diversity of base clusterings, and reduce the risk that some features are not selected at the same time. Secondly, semi-supervised clustering, i.e., constraint propagation, is applied to obtain base clusterings. Finally, we propose to utilize prior information in both the base clustering generating process and the consensus process, which guarantees that prior information is sufficiently used. We conduct a series of experiments on ten real-world data sets to demonstrate the effectiveness of the proposed model.https://ieeexplore.ieee.org/document/8825848/Constraint propagationensemble clusteringhigh dimensional datasemi-supervised learningstratified feature sampling |
| spellingShingle | Jialin Tian Yazhou Ren Xiang Cheng Stratified Feature Sampling for Semi-Supervised Ensemble Clustering IEEE Access Constraint propagation ensemble clustering high dimensional data semi-supervised learning stratified feature sampling |
| title | Stratified Feature Sampling for Semi-Supervised Ensemble Clustering |
| title_full | Stratified Feature Sampling for Semi-Supervised Ensemble Clustering |
| title_fullStr | Stratified Feature Sampling for Semi-Supervised Ensemble Clustering |
| title_full_unstemmed | Stratified Feature Sampling for Semi-Supervised Ensemble Clustering |
| title_short | Stratified Feature Sampling for Semi-Supervised Ensemble Clustering |
| title_sort | stratified feature sampling for semi supervised ensemble clustering |
| topic | Constraint propagation ensemble clustering high dimensional data semi-supervised learning stratified feature sampling |
| url | https://ieeexplore.ieee.org/document/8825848/ |
| work_keys_str_mv | AT jialintian stratifiedfeaturesamplingforsemisupervisedensembleclustering AT yazhouren stratifiedfeaturesamplingforsemisupervisedensembleclustering AT xiangcheng stratifiedfeaturesamplingforsemisupervisedensembleclustering |