Title :
Exploiting Unlabeled Data to Enhance Ensemble Diversity
Author :
Zhang, Min-Ling ; Zhou, Zhi-Hua
Author_Institution :
Sch. of Comput. Sci. & Eng., Southeast Univ., Nanjing, China
Abstract :
Ensemble learning aims to improve generalization ability by using multiple base learners. It is well-known that to construct a good ensemble, the base learners should be accurate as well as diverse. In this paper, unlabeled data is exploited to facilitate ensemble learning by helping augment the diversity among the base learners. Specifically, a semi-supervised ensemble method named UDEED is proposed. Unlike existing semi-supervised ensemble methods where error-prone pseudo-labels are estimated for unlabeled data to enlarge the labeled data to improve accuracy, UDEED works by maximizing accuracies of base learners on labeled data while maximizing diversity among them on unlabeled data. Experiments show that UDEED can effectively utilize unlabeled data for ensemble learning and is highly competitive to well-established semi-supervised ensemble methods.
Keywords :
data analysis; learning (artificial intelligence); optimisation; UDEED; accuracy maximization; ensemble learning; semisupervised ensemble method; unlabeled data; diversity; ensemble learning; unlabeled data;
Conference_Titel :
Data Mining (ICDM), 2010 IEEE 10th International Conference on
Conference_Location :
Sydney, NSW
Print_ISBN :
978-1-4244-9131-5
Electronic_ISBN :
1550-4786
DOI :
10.1109/ICDM.2010.12