Learning bayesian multinets from labeled and unlabeled data for knowledge representation

The Bayesian network classifiers (BNCs) learned from labeled training data are expected to generalize to fit unlabeled testing data based on the independent and identically distributed (i.i.d.) assumption, whereas the asymmetric independence assertion demonstrates the uncertainty of significance of dependency or independency relationships mined from data. A highly scalable BNC should form a distinct decision boundary that can be especially tailored to specific testing instance for knowledge representation. To address the issue of asymmetric independence assertion, in this paper we propose to learn k-dependence Bayesian multinet classifiers in the framework of multistage classification. By partitioning training set and pseudo training set according to high-confidence class labels, the dependency or independency relationships can be fully mined and represented in the topologies of the committee members. Extensive experimental results indicate that the proposed algorithm achieves competitive classification performance compared to single-topology BNCs (e.g., CFWNB, AIWNB and SKDB) and ensemble BNCs (e.g., WATAN, SA2DE, ATODE and SLB) in terms of zero-one loss, root mean square error (RMSE), Friedman test and Nemenyi test.