Tackling the supervised label ranking problem by bagging weak learners
详细信息 查看全文
- 作者：Juan A. Aledoa ; juanangel.aledo@uclm.es" class="auth_mail" title="E-mail the corresponding author ; José ; A. Gá ; mez ; b ; jose.gamez@uclm.es" class="auth_mail" title="E-mail the corresponding author ; David Molinac ; david.molina@uclm.es" class="auth_mail" title="E-mail the corresponding author
- 关键词：Supervised classification ; Label ranking problem ; Bagging ; Ensemble ; Mallows model ; Decision tree
- 刊名：Information Fusion
- 出版年：2017
- 出版时间：May 2017
- 年：2017
- 卷：35
- 期：Complete
- 页码：38-50
- 全文大小：725 K
文摘
- •
Weak decision tree-based label rankers are designed for the label ranking problem.
- •
An ensemble of weak learners is proposed to approach the label ranking problem.
- •
The use of proposed weak learners leads to faster but accurate ensembles.
- •
Results are comparable to the state-of-the-art algorithm in the complete case.
- •
Results are significantly better when learning from incomplete rankings.