Multi-label Classification of Small Samples Using an Ensemble Technique

Recently, multi-label classification problem has become an important challenge in many kinds of classification. In this problem, samples are associated with a set of class labels. Data with small sample essence is an important concept where the number of training samples is much less than the feature dimensions. The classification of small sample data has become a new problem in the fields of machine learning and pattern recognition. Ensemble learning is a kind of supervised learning process in which multiple learners are trained to solve the same problem. In this study, an ensemble learning method is proposed for the classification of multi-label data. To this end, first data is converted to the form of small sample, and then the proposed learning algorithm is applied to it. We used well-known parameters for the validation and evaluation of our results. Our results show that the proposed method can reach to the better performance as compared to the state-of-the-art base classifiers with respect to these parameters.