Hierarchical Dependency Constrained Tree Augmented Naive Bayes Classifiers for Hierarchical Feature Spaces
This work addresses classification challenges in domains with hierarchical features, such as biology or text, but it is incremental as it builds on existing TAN classifiers with specific constraints.
The authors tackled the problem of improving classification accuracy in hierarchical feature spaces by proposing two novel Tree Augmented Naive Bayes algorithms, Hie-TAN and Hie-TAN-Lite, which incorporate hierarchical constraints and reduce redundancy, resulting in better predictive performance compared to existing methods.
The Tree Augmented Naive Bayes (TAN) classifier is a type of probabilistic graphical model that constructs a single-parent dependency tree to estimate the distribution of the data. In this work, we propose two novel Hierarchical dependency-based Tree Augmented Naive Bayes algorithms, i.e. Hie-TAN and Hie-TAN-Lite. Both methods exploit the pre-defined parent-child (generalisation-specialisation) relationships between features as a type of constraint to learn the tree representation of dependencies among features, whilst the latter further eliminates the hierarchical redundancy during the classifier learning stage. The experimental results showed that Hie-TAN successfully obtained better predictive performance than several other hierarchical dependency constrained classification algorithms, and its predictive performance was further improved by eliminating the hierarchical redundancy, as suggested by the higher accuracy obtained by Hie-TAN-Lite.