IEICE TRANSACTIONS on Information
Semi-Supervised Feature Selection with Universum Based on Linked Social Media Data
Summary :
Independent and identically distributed (i.i.d) assumptions are commonly used in the machine learning community. However, social media data violate this assumption due to the linkages. Meanwhile, with the variety of data, there exist many samples, i.e., Universum, that do not belong to either class of interest. These characteristics pose great challenges to dealing with social media data. In this letter, we fully take advantage of Universum samples to enable the model to be more discriminative. In addition, the linkages are also taken into consideration in the means of social dimensions. To this end, we propose the algorithm Semi-Supervised Linked samples Feature Selection with Universum (U-SSLFS) to integrate the linking information and Universum simultaneously to select robust features. The empirical study shows that U-SSLFS outperforms state-of-the-art algorithms on the Flickr and BlogCatalog.
- Publication
- IEICE TRANSACTIONS on Information Vol.E97-D No.9 pp.2522-2525
- Publication Date
- 2014/09/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2014EDL8033
- Type of Manuscript
- LETTER
- Category
- Pattern Recognition
Authors
Junyang QIU
PLA University of Science and Technology
Yibing WANG
PLA University of Science and Technology
Zhisong PAN
PLA University of Science and Technology
Bo JIA
PLA University of Science and Technology
Keyword
Latest Issue
Copyrights notice of machine-translated contents
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.
Cite this
Copy
Junyang QIU, Yibing WANG, Zhisong PAN, Bo JIA, "Semi-Supervised Feature Selection with Universum Based on Linked Social Media Data" in IEICE TRANSACTIONS on Information,
vol. E97-D, no. 9, pp. 2522-2525, September 2014, doi: 10.1587/transinf.2014EDL8033.
Abstract: Independent and identically distributed (i.i.d) assumptions are commonly used in the machine learning community. However, social media data violate this assumption due to the linkages. Meanwhile, with the variety of data, there exist many samples, i.e., Universum, that do not belong to either class of interest. These characteristics pose great challenges to dealing with social media data. In this letter, we fully take advantage of Universum samples to enable the model to be more discriminative. In addition, the linkages are also taken into consideration in the means of social dimensions. To this end, we propose the algorithm Semi-Supervised Linked samples Feature Selection with Universum (U-SSLFS) to integrate the linking information and Universum simultaneously to select robust features. The empirical study shows that U-SSLFS outperforms state-of-the-art algorithms on the Flickr and BlogCatalog.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2014EDL8033/_p
Copy
@ARTICLE{e97-d_9_2522,
author={Junyang QIU, Yibing WANG, Zhisong PAN, Bo JIA, },
journal={IEICE TRANSACTIONS on Information},
title={Semi-Supervised Feature Selection with Universum Based on Linked Social Media Data},
year={2014},
volume={E97-D},
number={9},
pages={2522-2525},
abstract={Independent and identically distributed (i.i.d) assumptions are commonly used in the machine learning community. However, social media data violate this assumption due to the linkages. Meanwhile, with the variety of data, there exist many samples, i.e., Universum, that do not belong to either class of interest. These characteristics pose great challenges to dealing with social media data. In this letter, we fully take advantage of Universum samples to enable the model to be more discriminative. In addition, the linkages are also taken into consideration in the means of social dimensions. To this end, we propose the algorithm Semi-Supervised Linked samples Feature Selection with Universum (U-SSLFS) to integrate the linking information and Universum simultaneously to select robust features. The empirical study shows that U-SSLFS outperforms state-of-the-art algorithms on the Flickr and BlogCatalog.},
keywords={},
doi={10.1587/transinf.2014EDL8033},
ISSN={1745-1361},
month={September},}
Copy
TY - JOUR
TI - Semi-Supervised Feature Selection with Universum Based on Linked Social Media Data
T2 - IEICE TRANSACTIONS on Information
SP - 2522
EP - 2525
AU - Junyang QIU
AU - Yibing WANG
AU - Zhisong PAN
AU - Bo JIA
PY - 2014
DO - 10.1587/transinf.2014EDL8033
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E97-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2014
AB - Independent and identically distributed (i.i.d) assumptions are commonly used in the machine learning community. However, social media data violate this assumption due to the linkages. Meanwhile, with the variety of data, there exist many samples, i.e., Universum, that do not belong to either class of interest. These characteristics pose great challenges to dealing with social media data. In this letter, we fully take advantage of Universum samples to enable the model to be more discriminative. In addition, the linkages are also taken into consideration in the means of social dimensions. To this end, we propose the algorithm Semi-Supervised Linked samples Feature Selection with Universum (U-SSLFS) to integrate the linking information and Universum simultaneously to select robust features. The empirical study shows that U-SSLFS outperforms state-of-the-art algorithms on the Flickr and BlogCatalog.
ER -
English
