Incremental Semi-Supervised Clustering Ensemble for High Dimensional Data Clustering. Yu, Z., Luo, P., You, J., Wong, H., Leung, H., Wu, S., Zhang, J., & Han, G. IEEE Transactions on Knowledge and Data Engineering, 28(3):701–714, March, 2016. Conference Name: IEEE Transactions on Knowledge and Data Engineeringdoi abstract bibtex Traditional cluster ensemble approaches have three limitations: (1) They do not make use of prior knowledge of the datasets given by experts. (2) Most of the conventional cluster ensemble methods cannot obtain satisfactory results when handling high dimensional data. (3) All the ensemble members are considered, even the ones without positive contributions. In order to address the limitations of conventional cluster ensemble approaches, we first propose an incremental semi-supervised clustering ensemble framework (ISSCE) which makes use of the advantage of the random subspace technique, the constraint propagation approach, the proposed incremental ensemble member selection process, and the normalized cut algorithm to perform high dimensional data clustering. The random subspace technique is effective for handling high dimensional data, while the constraint propagation approach is useful for incorporating prior knowledge. The incremental ensemble member selection process is newly designed to judiciously remove redundant ensemble members based on a newly proposed local cost function and a global cost function, and the normalized cut algorithm is adopted to serve as the consensus function for providing more stable, robust, and accurate results. Then, a measure is proposed to quantify the similarity between two sets of attributes, and is used for computing the local cost function in ISSCE. Next, we analyze the time complexity of ISSCE theoretically. Finally, a set of nonparametric tests are adopted to compare multiple semisupervised clustering ensemble approaches over different datasets. The experiments on 18 real-world datasets, which include six UCI datasets and 12 cancer gene expression profiles, confirm that ISSCE works well on datasets with very high dimensionality, and outperforms the state-of-the-art semi-supervised clustering ensemble approaches.
@article{yu_incremental_2016,
title = {Incremental {Semi}-{Supervised} {Clustering} {Ensemble} for {High} {Dimensional} {Data} {Clustering}},
volume = {28},
issn = {1558-2191},
doi = {10.1109/TKDE.2015.2499200},
abstract = {Traditional cluster ensemble approaches have three limitations: (1) They do not make use of prior knowledge of the datasets given by experts. (2) Most of the conventional cluster ensemble methods cannot obtain satisfactory results when handling high dimensional data. (3) All the ensemble members are considered, even the ones without positive contributions. In order to address the limitations of conventional cluster ensemble approaches, we first propose an incremental semi-supervised clustering ensemble framework (ISSCE) which makes use of the advantage of the random subspace technique, the constraint propagation approach, the proposed incremental ensemble member selection process, and the normalized cut algorithm to perform high dimensional data clustering. The random subspace technique is effective for handling high dimensional data, while the constraint propagation approach is useful for incorporating prior knowledge. The incremental ensemble member selection process is newly designed to judiciously remove redundant ensemble members based on a newly proposed local cost function and a global cost function, and the normalized cut algorithm is adopted to serve as the consensus function for providing more stable, robust, and accurate results. Then, a measure is proposed to quantify the similarity between two sets of attributes, and is used for computing the local cost function in ISSCE. Next, we analyze the time complexity of ISSCE theoretically. Finally, a set of nonparametric tests are adopted to compare multiple semisupervised clustering ensemble approaches over different datasets. The experiments on 18 real-world datasets, which include six UCI datasets and 12 cancer gene expression profiles, confirm that ISSCE works well on datasets with very high dimensionality, and outperforms the state-of-the-art semi-supervised clustering ensemble approaches.},
number = {3},
journal = {IEEE Transactions on Knowledge and Data Engineering},
author = {Yu, Zhiwen and Luo, Peinan and You, Jane and Wong, Hau-San and Leung, Hareton and Wu, Si and Zhang, Jun and Han, Guoqiang},
month = mar,
year = {2016},
note = {Conference Name: IEEE Transactions on Knowledge and Data Engineering},
keywords = {Algorithm design and analysis, Cancer, Cluster ensemble, Clustering algorithms, Cost function, Gene expression, Linear programming, Search problems, cancer gene expression profile, clustering analysis, random subspace, semi-supervised clustering},
pages = {701--714},
}
Downloads: 0
{"_id":"bwsFPYiLvTPDCnXrX","bibbaseid":"yu-luo-you-wong-leung-wu-zhang-han-incrementalsemisupervisedclusteringensembleforhighdimensionaldataclustering-2016","author_short":["Yu, Z.","Luo, P.","You, J.","Wong, H.","Leung, H.","Wu, S.","Zhang, J.","Han, G."],"bibdata":{"bibtype":"article","type":"article","title":"Incremental Semi-Supervised Clustering Ensemble for High Dimensional Data Clustering","volume":"28","issn":"1558-2191","doi":"10.1109/TKDE.2015.2499200","abstract":"Traditional cluster ensemble approaches have three limitations: (1) They do not make use of prior knowledge of the datasets given by experts. (2) Most of the conventional cluster ensemble methods cannot obtain satisfactory results when handling high dimensional data. (3) All the ensemble members are considered, even the ones without positive contributions. In order to address the limitations of conventional cluster ensemble approaches, we first propose an incremental semi-supervised clustering ensemble framework (ISSCE) which makes use of the advantage of the random subspace technique, the constraint propagation approach, the proposed incremental ensemble member selection process, and the normalized cut algorithm to perform high dimensional data clustering. The random subspace technique is effective for handling high dimensional data, while the constraint propagation approach is useful for incorporating prior knowledge. The incremental ensemble member selection process is newly designed to judiciously remove redundant ensemble members based on a newly proposed local cost function and a global cost function, and the normalized cut algorithm is adopted to serve as the consensus function for providing more stable, robust, and accurate results. Then, a measure is proposed to quantify the similarity between two sets of attributes, and is used for computing the local cost function in ISSCE. Next, we analyze the time complexity of ISSCE theoretically. Finally, a set of nonparametric tests are adopted to compare multiple semisupervised clustering ensemble approaches over different datasets. The experiments on 18 real-world datasets, which include six UCI datasets and 12 cancer gene expression profiles, confirm that ISSCE works well on datasets with very high dimensionality, and outperforms the state-of-the-art semi-supervised clustering ensemble approaches.","number":"3","journal":"IEEE Transactions on Knowledge and Data Engineering","author":[{"propositions":[],"lastnames":["Yu"],"firstnames":["Zhiwen"],"suffixes":[]},{"propositions":[],"lastnames":["Luo"],"firstnames":["Peinan"],"suffixes":[]},{"propositions":[],"lastnames":["You"],"firstnames":["Jane"],"suffixes":[]},{"propositions":[],"lastnames":["Wong"],"firstnames":["Hau-San"],"suffixes":[]},{"propositions":[],"lastnames":["Leung"],"firstnames":["Hareton"],"suffixes":[]},{"propositions":[],"lastnames":["Wu"],"firstnames":["Si"],"suffixes":[]},{"propositions":[],"lastnames":["Zhang"],"firstnames":["Jun"],"suffixes":[]},{"propositions":[],"lastnames":["Han"],"firstnames":["Guoqiang"],"suffixes":[]}],"month":"March","year":"2016","note":"Conference Name: IEEE Transactions on Knowledge and Data Engineering","keywords":"Algorithm design and analysis, Cancer, Cluster ensemble, Clustering algorithms, Cost function, Gene expression, Linear programming, Search problems, cancer gene expression profile, clustering analysis, random subspace, semi-supervised clustering","pages":"701–714","bibtex":"@article{yu_incremental_2016,\n\ttitle = {Incremental {Semi}-{Supervised} {Clustering} {Ensemble} for {High} {Dimensional} {Data} {Clustering}},\n\tvolume = {28},\n\tissn = {1558-2191},\n\tdoi = {10.1109/TKDE.2015.2499200},\n\tabstract = {Traditional cluster ensemble approaches have three limitations: (1) They do not make use of prior knowledge of the datasets given by experts. (2) Most of the conventional cluster ensemble methods cannot obtain satisfactory results when handling high dimensional data. (3) All the ensemble members are considered, even the ones without positive contributions. In order to address the limitations of conventional cluster ensemble approaches, we first propose an incremental semi-supervised clustering ensemble framework (ISSCE) which makes use of the advantage of the random subspace technique, the constraint propagation approach, the proposed incremental ensemble member selection process, and the normalized cut algorithm to perform high dimensional data clustering. The random subspace technique is effective for handling high dimensional data, while the constraint propagation approach is useful for incorporating prior knowledge. The incremental ensemble member selection process is newly designed to judiciously remove redundant ensemble members based on a newly proposed local cost function and a global cost function, and the normalized cut algorithm is adopted to serve as the consensus function for providing more stable, robust, and accurate results. Then, a measure is proposed to quantify the similarity between two sets of attributes, and is used for computing the local cost function in ISSCE. Next, we analyze the time complexity of ISSCE theoretically. Finally, a set of nonparametric tests are adopted to compare multiple semisupervised clustering ensemble approaches over different datasets. The experiments on 18 real-world datasets, which include six UCI datasets and 12 cancer gene expression profiles, confirm that ISSCE works well on datasets with very high dimensionality, and outperforms the state-of-the-art semi-supervised clustering ensemble approaches.},\n\tnumber = {3},\n\tjournal = {IEEE Transactions on Knowledge and Data Engineering},\n\tauthor = {Yu, Zhiwen and Luo, Peinan and You, Jane and Wong, Hau-San and Leung, Hareton and Wu, Si and Zhang, Jun and Han, Guoqiang},\n\tmonth = mar,\n\tyear = {2016},\n\tnote = {Conference Name: IEEE Transactions on Knowledge and Data Engineering},\n\tkeywords = {Algorithm design and analysis, Cancer, Cluster ensemble, Clustering algorithms, Cost function, Gene expression, Linear programming, Search problems, cancer gene expression profile, clustering analysis, random subspace, semi-supervised clustering},\n\tpages = {701--714},\n}\n\n\n\n","author_short":["Yu, Z.","Luo, P.","You, J.","Wong, H.","Leung, H.","Wu, S.","Zhang, J.","Han, G."],"key":"yu_incremental_2016","id":"yu_incremental_2016","bibbaseid":"yu-luo-you-wong-leung-wu-zhang-han-incrementalsemisupervisedclusteringensembleforhighdimensionaldataclustering-2016","role":"author","urls":{},"keyword":["Algorithm design and analysis","Cancer","Cluster ensemble","Clustering algorithms","Cost function","Gene expression","Linear programming","Search problems","cancer gene expression profile","clustering analysis","random subspace","semi-supervised clustering"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/mh_lenguyen","dataSources":["iwKepCrWBps7ojhDx"],"keywords":["algorithm design and analysis","cancer","cluster ensemble","clustering algorithms","cost function","gene expression","linear programming","search problems","cancer gene expression profile","clustering analysis","random subspace","semi-supervised clustering"],"search_terms":["incremental","semi","supervised","clustering","ensemble","high","dimensional","data","clustering","yu","luo","you","wong","leung","wu","zhang","han"],"title":"Incremental Semi-Supervised Clustering Ensemble for High Dimensional Data Clustering","year":2016}