Nearest Neighbor Classifier with Margin Penalty for Active Learning

Yuan Cao, Zhiqiao Gao, Jie Hu, Mingchuan Yang, Jinpeng Chen

Abstract: As deep learning becomes the mainstream in the field of natural language processing, the need for suitable active learning method are becoming unprecedented urgent. Active Learning (AL) methods based on nearest neighbor classifier are proposed and demonstrated superior results. However, existing nearest neighbor classifiers are not suitable for classifying mutual exclusive classes because inter-class discrepancy cannot be assured. As a result, informative samples in the margin area can not be discovered and AL performance are damaged. To this end, we propose a novel Nearest neighbor Classifier with Margin penalty for Active Learning (NCMAL). Firstly, mandatory margin penalties are added between classes, therefore both inter-class discrepancy and intra-class compactness are both assured. Secondly, a novel sample selection strategy is proposed to discover informative samples within the margin area. To demonstrate the effectiveness of the methods, we conduct extensive experiments on three real-world datasets with other state-of-the-art methods. The experimental results demonstrate that our method achieves better results with fewer annotated samples than all baseline methods.