Group feature selection with multiclass support vector machine

Feature reduction is nowadays an important topic in machine learning as it reduces the complexity of the final model and makes it easier to interpret. In some applications, the features arise from multiple sources and it is not so important to select the individual features as to select the important sources. This leads to a group feature selection problem. In this paper, we consider the group feature selection in the multiclass classification setting based on the framework of support vector machines. We reformulate it as a sparse problem by prescribing the maximum number of active groups and propose a novel method based on the ADMM algorithm. We proposed the method in such a way that the main computational load is performed in the first iteration and the remaining iterations can be computed fast. This allows us to handle large problems. We demonstrate the good performance of our method on several real-world datasets.