DocumentCode :
1260559
Title :
Cross-Domain Semi-Supervised Learning Using Feature Formulation
Author :
Zhu, Xingquan
Author_Institution :
Fac. of Eng. & Inf. Technol., Univ. of Technol., Sydney, NSW, Australia
Volume :
41
Issue :
6
fYear :
2011
Firstpage :
1627
Lastpage :
1638
Abstract :
Semi-Supervised Learning (SSL) traditionally makes use of unlabeled samples by including them into the training set through an automated labeling process. Such a primitive Semi-Supervised Learning (pSSL) approach suffers from a number of disadvantages including false labeling and incapable of utilizing out-of-domain samples. In this paper, we propose a formative Semi-Supervised Learning (fSSL) framework which explores hidden features between labeled and unlabeled samples to achieve semi-supervised learning. fSSL regards that both labeled and unlabeled samples are generated from some hidden concepts with labeling information partially observable for some samples. The key of the fSSL is to recover the hidden concepts, and take them as new features to link labeled and unlabeled samples for semi-supervised learning. Because unlabeled samples are only used to generate new features, but not to be explicitly included in the training set like pSSL does, fSSL overcomes the inherent disadvantages of the traditional pSSL methods, especially for samples not within the same domain as the labeled instances. Experimental results and comparisons demonstrate that fSSL significantly outperforms pSSL-based methods for both within-domain and cross-domain semi-supervised learning.
Keywords :
learning (artificial intelligence); cross-domain semi-supervised learning; feature formulation; formative semi-supervised learning framework; within-domain semi-supervised learning; Correlation; Data models; Feature extraction; Labeling; Machine learning; Semisupervised learning; Training; Cross domain learning; machine learning; semi-supervised learning; transfer learning;
fLanguage :
English
Journal_Title :
Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on
Publisher :
ieee
ISSN :
1083-4419
Type :
jour
DOI :
10.1109/TSMCB.2011.2157999
Filename :
5934438
Link To Document :
بازگشت