A Transductive SVM with quasi-linear kernel based on cluster assumption for semi-supervised classification

Bo Zhou; Di Fu; Chao Dong; Jinglu Hu

doi:10.1109/IJCNN.2015.7280485

A Transductive SVM with quasi-linear kernel based on cluster assumption for semi-supervised classification

Bo Zhou, Di Fu, Chao Dong, Jinglu Hu

Graduate School of Information, Production and Systems

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Citations (Scopus)

Abstract

This paper presents a Transductive Support Vector Machine (TSVM) with quasi-linear kernel based on a clustering assumption for semi-supervised classification. Since the potential separating boundary is located in low density area between classes, a modified density clustering method by considering label information is firstly introduced to extract the information of potential separating boundary in low density region between different classes. Then the information is used to compose a quasi-linear kernel for the TSVM. The optimization of TSVM is further speeded up by developing a pairwise label switching method on minimal sets. Experiment results on benchmark datasets show that the proposed method is effective and improves classification performances.

Original language	English
Title of host publication	2015 International Joint Conference on Neural Networks, IJCNN 2015
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781479919604, 9781479919604, 9781479919604, 9781479919604
DOIs	https://doi.org/10.1109/IJCNN.2015.7280485
Publication status	Published - 2015 Sept 28
Event	International Joint Conference on Neural Networks, IJCNN 2015 - Killarney, Ireland Duration: 2015 Jul 12 → 2015 Jul 17

Publication series

Name	Proceedings of the International Joint Conference on Neural Networks
Volume	2015-September

Other

Other	International Joint Conference on Neural Networks, IJCNN 2015
Country/Territory	Ireland
City	Killarney
Period	15/7/12 → 15/7/17

Keywords

Accuracy
Kernel
Support vector machines
Switches

ASJC Scopus subject areas

Software
Artificial Intelligence

Access to Document

10.1109/IJCNN.2015.7280485

Cite this

Zhou, B., Fu, D., Dong, C., & Hu, J. (2015). A Transductive SVM with quasi-linear kernel based on cluster assumption for semi-supervised classification. In 2015 International Joint Conference on Neural Networks, IJCNN 2015 [7280485] (Proceedings of the International Joint Conference on Neural Networks; Vol. 2015-September). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IJCNN.2015.7280485

A Transductive SVM with quasi-linear kernel based on cluster assumption for semi-supervised classification. / Zhou, Bo; Fu, Di; Dong, Chao et al.
2015 International Joint Conference on Neural Networks, IJCNN 2015. Institute of Electrical and Electronics Engineers Inc., 2015. 7280485 (Proceedings of the International Joint Conference on Neural Networks; Vol. 2015-September).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Zhou, B, Fu, D, Dong, C & Hu, J 2015, A Transductive SVM with quasi-linear kernel based on cluster assumption for semi-supervised classification. in 2015 International Joint Conference on Neural Networks, IJCNN 2015., 7280485, Proceedings of the International Joint Conference on Neural Networks, vol. 2015-September, Institute of Electrical and Electronics Engineers Inc., International Joint Conference on Neural Networks, IJCNN 2015, Killarney, Ireland, 15/7/12. https://doi.org/10.1109/IJCNN.2015.7280485

Zhou B, Fu D, Dong C, Hu J. A Transductive SVM with quasi-linear kernel based on cluster assumption for semi-supervised classification. In 2015 International Joint Conference on Neural Networks, IJCNN 2015. Institute of Electrical and Electronics Engineers Inc. 2015. 7280485. (Proceedings of the International Joint Conference on Neural Networks). doi: 10.1109/IJCNN.2015.7280485

@inproceedings{c87596061b704fa4b7a45b6953428d8f,

title = "A Transductive SVM with quasi-linear kernel based on cluster assumption for semi-supervised classification",

abstract = "This paper presents a Transductive Support Vector Machine (TSVM) with quasi-linear kernel based on a clustering assumption for semi-supervised classification. Since the potential separating boundary is located in low density area between classes, a modified density clustering method by considering label information is firstly introduced to extract the information of potential separating boundary in low density region between different classes. Then the information is used to compose a quasi-linear kernel for the TSVM. The optimization of TSVM is further speeded up by developing a pairwise label switching method on minimal sets. Experiment results on benchmark datasets show that the proposed method is effective and improves classification performances.",

keywords = "Accuracy, Kernel, Support vector machines, Switches",

author = "Bo Zhou and Di Fu and Chao Dong and Jinglu Hu",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; International Joint Conference on Neural Networks, IJCNN 2015 ; Conference date: 12-07-2015 Through 17-07-2015",

year = "2015",

month = sep,

day = "28",

doi = "10.1109/IJCNN.2015.7280485",

language = "English",

series = "Proceedings of the International Joint Conference on Neural Networks",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2015 International Joint Conference on Neural Networks, IJCNN 2015",

}

TY - GEN

T1 - A Transductive SVM with quasi-linear kernel based on cluster assumption for semi-supervised classification

AU - Zhou, Bo

AU - Fu, Di

AU - Dong, Chao

AU - Hu, Jinglu

PY - 2015/9/28

Y1 - 2015/9/28

N2 - This paper presents a Transductive Support Vector Machine (TSVM) with quasi-linear kernel based on a clustering assumption for semi-supervised classification. Since the potential separating boundary is located in low density area between classes, a modified density clustering method by considering label information is firstly introduced to extract the information of potential separating boundary in low density region between different classes. Then the information is used to compose a quasi-linear kernel for the TSVM. The optimization of TSVM is further speeded up by developing a pairwise label switching method on minimal sets. Experiment results on benchmark datasets show that the proposed method is effective and improves classification performances.

AB - This paper presents a Transductive Support Vector Machine (TSVM) with quasi-linear kernel based on a clustering assumption for semi-supervised classification. Since the potential separating boundary is located in low density area between classes, a modified density clustering method by considering label information is firstly introduced to extract the information of potential separating boundary in low density region between different classes. Then the information is used to compose a quasi-linear kernel for the TSVM. The optimization of TSVM is further speeded up by developing a pairwise label switching method on minimal sets. Experiment results on benchmark datasets show that the proposed method is effective and improves classification performances.

KW - Accuracy

KW - Kernel

KW - Support vector machines

KW - Switches

UR - http://www.scopus.com/inward/record.url?scp=84951086404&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84951086404&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2015.7280485

DO - 10.1109/IJCNN.2015.7280485

M3 - Conference contribution

AN - SCOPUS:84951086404

T3 - Proceedings of the International Joint Conference on Neural Networks

BT - 2015 International Joint Conference on Neural Networks, IJCNN 2015

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - International Joint Conference on Neural Networks, IJCNN 2015

Y2 - 12 July 2015 through 17 July 2015

ER -

A Transductive SVM with quasi-linear kernel based on cluster assumption for semi-supervised classification

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this