Ensemble of Unsupervised and Supervised Models with Different Label Spaces

Abstract

Ensemble approaches of multiple supervised and unsupervised models have been exhibited to be effective in predicting labels of new instances. Those approaches, however, require the label spaces of all supervised models to be identical to the target testing instances. In many real world applications, it is often difficult to collect such supervised models for the ensemble. In contrast, it is much easier to get large amounts of supervised models with different label spaces at a stroke. In this paper, we aim to build a novel ensemble approach that allows supervised models with different label spaces. Each supervised model is associated with an anomaly detection model. We view each supervised model as a partial voter and we manage to maximize the consensus between partial voting from supervised models and unsupervised models. In the experiments, we demonstrate the effectiveness of our approach in different data sets.