Efficient Active Novel Class Detection for Data Stream Classification

Abstract : One substantial aspect of data stream classification is the possible appearance of novel unseen classes which must be identified in order to avoid confusion with existing classes. Detecting such new classes is omitted by most existing techniques and rarely addressed in the literature. We address this issue and propose an efficient method to identify novel class emergence in a multi-class data stream. The proposed method incrementally maintains a covered feature space of existing (known) classes. An incoming data point is designated as "insider" or "outsider" depending on whether it lies inside or outside the covered space area. An insider represents a possible instance of an existing class, while an outsider may be an instance of a possible novel class. The proposed method is able to iteratively select those insiders (resp. outsiders) that are more likely to be members of a novel (resp. an existing) class, and eventually distinguish the actual novel and existing classes accurately. We show how to actively query the labels of the identified novel class instances that are most uncertain. The method also allows us to balance between the rapidity of the novelty detection and its efficiency. Experiments using real world data prove the effectiveness of our approach for both the novel class detection and classification accuracy.