TY - GEN
T1 - Cost-sensitive universum-SVM
AU - Dhar, Sauptik
AU - Cherkassky, Vladimir
PY - 2012
Y1 - 2012
N2 - Many applications of machine learning involve analysis of sparse high-dimensional data, where the number of input features is larger than the number of data samples. Standard classification methods may not be sufficient for such data, and this provides motivation for non-standard learning settings. One such new learning methodology is called Learning through Contradictions or Universum support vector machine (U-SVM) [1, 2]. Recent studies [2-10] have shown U-SVM to be quite effective for such sparse high-dimensional data settings. However, these studies use balanced data sets with equal misclassification costs. This paper extends the U-SVM for problems with different misclassification costs, and presents practical conditions for the effectiveness of the cost sensitive U-SVM. Finally, several empirical comparisons are presented to illustrate the utility of the proposed approach.
AB - Many applications of machine learning involve analysis of sparse high-dimensional data, where the number of input features is larger than the number of data samples. Standard classification methods may not be sufficient for such data, and this provides motivation for non-standard learning settings. One such new learning methodology is called Learning through Contradictions or Universum support vector machine (U-SVM) [1, 2]. Recent studies [2-10] have shown U-SVM to be quite effective for such sparse high-dimensional data settings. However, these studies use balanced data sets with equal misclassification costs. This paper extends the U-SVM for problems with different misclassification costs, and presents practical conditions for the effectiveness of the cost sensitive U-SVM. Finally, several empirical comparisons are presented to illustrate the utility of the proposed approach.
KW - Cost-sensitive SVM
KW - Universum SVM
KW - learning through contradiction
KW - support vector machines
UR - http://www.scopus.com/inward/record.url?scp=84873596372&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84873596372&partnerID=8YFLogxK
U2 - 10.1109/ICMLA.2012.45
DO - 10.1109/ICMLA.2012.45
M3 - Conference contribution
AN - SCOPUS:84873596372
SN - 9780769549132
T3 - Proceedings - 2012 11th International Conference on Machine Learning and Applications, ICMLA 2012
SP - 220
EP - 225
BT - Proceedings - 2012 11th International Conference on Machine Learning and Applications, ICMLA 2012
T2 - 11th IEEE International Conference on Machine Learning and Applications, ICMLA 2012
Y2 - 12 December 2012 through 15 December 2012
ER -