Why Stacked Models Perform Effective Collective Classification

Collective classification techniques jointly infer all class labels of a relational data set, using the inferences about one class label to influence inferences about related class labels. Kou and Cohen recently introduced an efficient relational model based on stacking that, despite its simplicity, has equivalent accuracy to more sophisticated joint inference approaches. Using experiments on both real and synthetic data, we show that the primary cause for the performance of the stacked model is the reduction in bias from learning the stacked model on inferred labels rather than true labels. The reduction in variance due to conditional inference also contributes to the effect but it is not as strong. In addition, we show that the performance of the joint inference and stacked learners can be attributed to an implicit weighting of local and relational features at learning time.