In general, semi-supervised clustering can outperform unsupervised clustering. Since 2001, pairwise constraints for semi-supervised clustering have been an important paradigm in this field. In this paper, we show that pairwise constraints (ECs) can affect the performance of clustering in certain situations and analyze the reasons for this in detail. To overcome these disadvantages, we first outline some exemplars constraints. Based on these constraints, we then describe a semi-supervised clustering framework, and design an exemplars constraints expectation-maximization algorithm. Finally, standard datasets are selected for experiments, and experimental results are presented, which show that the exemplars constraints outperform the corresponding unsupervised clustering and semi-supervised algorithms based on pairwise constraints.
Sailan WANG
Sichuan University
Zhenzhi YANG
Jincheng Institute of SiChuan University
Jin YANG
Leshan Normal University
Hongjun WANG
Southwest Jiaotong University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Sailan WANG, Zhenzhi YANG, Jin YANG, Hongjun WANG, "Semi-Supervised Clustering Based on Exemplars Constraints" in IEICE TRANSACTIONS on Information,
vol. E100-D, no. 6, pp. 1231-1241, June 2017, doi: 10.1587/transinf.2016EDP7201.
Abstract: In general, semi-supervised clustering can outperform unsupervised clustering. Since 2001, pairwise constraints for semi-supervised clustering have been an important paradigm in this field. In this paper, we show that pairwise constraints (ECs) can affect the performance of clustering in certain situations and analyze the reasons for this in detail. To overcome these disadvantages, we first outline some exemplars constraints. Based on these constraints, we then describe a semi-supervised clustering framework, and design an exemplars constraints expectation-maximization algorithm. Finally, standard datasets are selected for experiments, and experimental results are presented, which show that the exemplars constraints outperform the corresponding unsupervised clustering and semi-supervised algorithms based on pairwise constraints.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2016EDP7201/_p
Copy
@ARTICLE{e100-d_6_1231,
author={Sailan WANG, Zhenzhi YANG, Jin YANG, Hongjun WANG, },
journal={IEICE TRANSACTIONS on Information},
title={Semi-Supervised Clustering Based on Exemplars Constraints},
year={2017},
volume={E100-D},
number={6},
pages={1231-1241},
abstract={In general, semi-supervised clustering can outperform unsupervised clustering. Since 2001, pairwise constraints for semi-supervised clustering have been an important paradigm in this field. In this paper, we show that pairwise constraints (ECs) can affect the performance of clustering in certain situations and analyze the reasons for this in detail. To overcome these disadvantages, we first outline some exemplars constraints. Based on these constraints, we then describe a semi-supervised clustering framework, and design an exemplars constraints expectation-maximization algorithm. Finally, standard datasets are selected for experiments, and experimental results are presented, which show that the exemplars constraints outperform the corresponding unsupervised clustering and semi-supervised algorithms based on pairwise constraints.},
keywords={},
doi={10.1587/transinf.2016EDP7201},
ISSN={1745-1361},
month={June},}
Copy
TY - JOUR
TI - Semi-Supervised Clustering Based on Exemplars Constraints
T2 - IEICE TRANSACTIONS on Information
SP - 1231
EP - 1241
AU - Sailan WANG
AU - Zhenzhi YANG
AU - Jin YANG
AU - Hongjun WANG
PY - 2017
DO - 10.1587/transinf.2016EDP7201
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E100-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2017
AB - In general, semi-supervised clustering can outperform unsupervised clustering. Since 2001, pairwise constraints for semi-supervised clustering have been an important paradigm in this field. In this paper, we show that pairwise constraints (ECs) can affect the performance of clustering in certain situations and analyze the reasons for this in detail. To overcome these disadvantages, we first outline some exemplars constraints. Based on these constraints, we then describe a semi-supervised clustering framework, and design an exemplars constraints expectation-maximization algorithm. Finally, standard datasets are selected for experiments, and experimental results are presented, which show that the exemplars constraints outperform the corresponding unsupervised clustering and semi-supervised algorithms based on pairwise constraints.
ER -