|
|||||
|
|
| 基于决策树集成的偏标记学习算法* | |
| 引用本文： | 于菲,张敏灵. 基于决策树集成的偏标记学习算法*[J]. 模式识别与人工智能, 2016, 29(4): 367-375. DOI: 10.16451/j.cnki.issn1003-6059.201604009 |
| 作者姓名： | 于菲 张敏灵 |
| 作者单位： | 东南大学 计算机科学与工程学院 南京 210096 东南大学 计算机网络和信息集成教育部重点实验室 南京 210096 |
| 基金项目： | 国家自然科学基金项目(No.61573104,61222309)、教育部新世纪优秀人才支持计划(No.NCET-13-0130)资助 |
| 摘 要： | 为了克服偏标记学习中监督信息缺失的问题，根据偏标记样本的性质设计决策树生成过程中的样本分裂规则，改造决策树的建立算法.文中算法首先对样本进行bootstrap采样并建立多棵决策树，然后对各决策树结果进行投票得出最终预测结果.在人工数据集和真实数据集上的实验表明，文中算法具有较好的分类性能. |
| 关 键 词： | 弱监督学习 偏标记学习 随机森林 集成学习 |
| 收稿时间： | 2015-05-15 |
Decision Tree Ensemble Based Partial Label Learning Algorithm |
|
| YU Fei,ZHANG Minling. Decision Tree Ensemble Based Partial Label Learning Algorithm[J]. Pattern Recognition and Artificial Intelligence, 2016, 29(4): 367-375. DOI: 10.16451/j.cnki.issn1003-6059.201604009 | |
| Authors: | YU Fei ZHANG Minling |
| Affiliation: | School of Computer Science and Engineering, Southeast University, Nanjing 210096 Key Laboratory of Computer Network and Information Integration of Ministry of Education,Southeast University, Nanjing 210096 |
| Abstract: | To overcome the problem of the missing supervision information in partial label learning, a special splitting measure for the generation of decision tree is designed according to the property of partial label examples and the growth algorithm of decision tree is modified. In the proposed algorithm, bootstrap sampling is employed to construct multiple decision trees, and then the final prediction result is obtained by voting on the classification results of each decision tree. Experiments on artificial datasets and real-world datasets validate the good performance of the proposed algorithm. |
| Keywords: | Weakly Supervised Learning Partial Label Learning Random Forest Ensemble Learning |
| 点击此处可从《模式识别与人工智能》浏览原始摘要信息 | |
| 点击此处可从《模式识别与人工智能》下载全文 | |