Cost-sensitive classification with inadequate labeled data

详细信息	查看全文 | 推荐本文 |

• 作者：Tao Wang^a ; ^{wangtao@it.uts.edu.au} ; Zhenxing Qin^a ; ^{zqin@it.uts.edu.au} ; Shichao Zhang^b ; ^{zhangsc@gxnu.edu.cn} ; Chengqi Zhang^a ; ^{chengqi@it.uts.edu.au}
• 关键词：Cost-sensitive learning ; Classification ; Semi-supervised learning ; Expectation maximization
• 刊名：Information Systems
• 出版年：2012
• 期刊代码：64_03064379
• 类别：cp
• 出版时间：July, 2012
• 卷：37
• 期：5
• 页码：508-516
• 文件大小：371 K

摘要

It is an actual and challenging issue to learn cost-sensitive models from those datasets that are with few labeled data and plentiful unlabeled data, because some time labeled data are very difficult, time consuming and/or expensive to obtain. To solve this issue, in this paper we proposed two classification strategies to learn cost-sensitive classifier from training datasets with both labeled and unlabeled data, based on Expectation Maximization (EM). The first method, Direct-EM, uses EM to build a semi-supervised classifier, then directly computes the optimal class label for each test example using the class probability produced by the learning model. The second method, CS-EM, modifies EM by incorporating misclassification cost into the probability estimation process. We conducted extensive experiments to evaluate the efficiency, and results show that when using only a small number of labeled training examples, the CS-EM outperforms the other competing methods on majority of the selected UCI data sets across different cost ratios, especially when cost ratio is high.