TitleSemi-Supervised Collective Classification with Hybrid Label Regularization
Publication TypeConference Proceedings
Year of Conference2012
AuthorsMcDowell, LK, Aha, DW
Conference NameProceedings of the 29th International Conference on Machine Learning
Conference LocationEdinburgh, Scotland

Many classification problems involve data instances that are interlinked with each other, such as webpages connected by hyperlinks. Techniques for collective classification (CC) often increase accuracy for such data graphs, but usually require a fully-labeled training graph. In contrast, we examine how to improve the semi-supervised learning of CC models when given only a sparsely-labeled graph, a common situation. We first describe how to use novel combinations of classifiers to exploit the different characteristics of the relational features vs. the non-relational features. We also extend the ideas of label regularization to such hybrid classifiers, enabling them to leverage the unlabeled data to bias the learning process. We find that these techniques, which are ecient and easy to implement, significantly increase accuracy on three real datasets. In addition, our results explain conflicting findings from prior related studies.

Refereed DesignationRefereed
Full Text
NRL Publication Release Number: 
statistical relational learning
collective classification
semi-supervised learning