Semi-Supervised Boosting for Multi-Class Classification

Most semi-supervised learning algorithms have been designed for binary classification, and are extended to multi-class classification by approaches such as one-against-the-rest. The main shortcoming of these approaches is that they are unable to exploit the fact that each example is only assigned to one class. Additional problems with extending semisupervised binary classifiers to multi-class problems include imbalanced classification and different output scales of different binary classifiers. We propose a semi-supervised boosting framework, termed Multi-Class Semi-Supervised Boosting (MCSSB), that directly solves the semisupervised multi-class learning problem. Compared to the existing semisupervised boosting methods, the proposed framework is advantageous in that it exploits both classification confidence and similarities among examples when deciding the pseudo-labels for unlabeled examples. Empirical study with a number of UCI datasets shows that the proposed MCSSB algorithm performs better than the state-of-the-art boosting algorithms for semi-supervised learning.