A Collaborative Ability Measurement for Co-training

This paper explores collaborative ability of co-training algorithm. We propose a new measurement (CA) for representing the collaborative ability of co-training classifiers based on the overlapping proportion between certain and uncertain instances. The CA measurement indicates whether two classifiers can co-train effectively. We make theoretical analysis for CA values in co-training with independent feature split, with random feature split and without feature split. The experiments justify our analysis. We also explore two variations of the general co-training algorithm and analyze them using the CA measurement.

• Type: Conference
• Year: 2004
• Where: IJCNLP
• Authors: Dan Shen, Jie Zhang, Jian Su, Guodong Zhou, Chew Lim Tan
• Keywords: Co-training, Co-training Algorithm, Feature Split, IJCNLP 2004