Semi-supervised weighting for averaged one-dependence estimators

摘要

Averaged one-dependence estimators (AODE) is a state-of-the-art machine learning tool for classification due to its simplicity, high computational efficiency, and excellent classification accuracy. Weighting provides an effective mechanism to ensemble superparent one-dependence estimators (SPODEs) in AODE by linearly aggregating their weighted probability estimates. Supervised weighting and unsupervised weighting are proposed to learn weights from labeled or unlabeled data, whereas their interoperability has not previously been investigated. In this paper, we propose a novel weighting paradigm in the framework of semi-supervised learning, called semi-supervised weighting (SSW). Two different versions of weighted AODEs, supervised weighted AODE (SWAODE) which performs weighting at training time and unsupervised weighted AODE (UWAODE) which performs weighting at classification time, are built severally. Log likelihood function is introduced to linearly aggregate the outcomes of these two weighted AODEs. The proposed algorithm, called SSWAODE, is validated on 38 benchmark datasets from the University of California at Irvine (UCI) machine learning repository and the experimental results prove the effectiveness and robustness of SSW for weighting AODE in terms of zero-one loss, bias, variance and etc. SSWAODE well achieves the balance between the ground-truth dependencies approximation and the effectiveness of probability estimation.