A new cross-training approach by using labeled data

Abstract

We propose a new cross-training based learning algorithm in this paper. This algorithm generates three classifiers based on the three subsets of original labeled and unlabeled training set. The proposed algorithm is evaluated using data from the UCI repository by the experiment. Experimental results show that our algorithm can improve classification accuracy compared to those of other algorithms.

Related Papers

• Email classification with co-training(2011)
• → Self-Training with Selection-by-Rejection(2012)19 cited
• → Integrating Co-Training and Recognition for Text Detection(2005)9 cited
• → Reinforced Co-Training(2018)2 cited