关键词: 半监督学习, 新类探测, 自训练, 极限学习机, 最大平均差异, 分布一致性

Abstract: The limited application scenario and unsatisfactory generalization capability are two main defects of traditional semi-supervised learning (SSL) algorithms. Especially, their prediction capabilities will be severely degraded when the training data set includes the samples with new labels. It is usually time-consuming and expensive to label the unlabeled samples by the domain experts. In addition, the wrongly-labeled samples are unavoidable due to the insufficient background knowledge. A new class detection SSL (NCD-SSL) algorithm is proposed in this paper to effectively solve the SSL problems where the unlabeled samples may have the new labels. First, a universal incremental extreme learning machine is designed to deal with both class-incremental and sample-incremental classification problems. Second, the self-training model is improved by using the samples with high-confidence labels and setting a buffer pool to store the samples with low-confidence labels. Third, the samples in buffer pool are further handled with clustering and distribution consistency judgement technologies so that the new classes can be detected. Finally, a series of persuasive experiments are conducted to validate the rationality and effectiveness of NCD-SSL algorithm. The experimental results show that the testing accuracies of NCD-SSL algorithm increase more than 30%, 20%, 10%for 3-classes, 2-classes, 1-class missing cases in comparison with the other six popular SSL algorithms and thus demonstrate the superior SSL performances of NCD-SSL algorithm.

Key words: Semi-supervised learning, new class detection, self-training, extreme learning machine, maximum mean discrepancy, distribution consistency