L21-Norm Regularized Discriminative Feature Selection for Unsupervised Learning
Yi Yang, Heng Tao Shen, Zhigang Ma, Zi Huang and Xiaofang Zhou
Compared with supervised learning for feature selection, it is much more difficult to select the discriminative features in unsupervised learning due to the lack of label information. Traditional unsupervised feature selection algorithms usually select the features which best preserve the data distribution, e.g., manifold structure, of the whole feature set. Meanwhile, most of the existing unsupervised feature selection algorithms rank each feature individually according to different criteria and select the top ranked features one by one. Such greedy-method like strategy does not guarantee that the selected features constitute the optimal feature subset. Under the assumption that the class label of input data can be predicted by a linear classifier, we incorporate discriminative analysis and L21-norm minimization into a joint framework for unsupervised feature selection. Different from existing unsupervised feature selection algorithms, our algorithm selects the most discriminative feature subset from the whole feature set in batch mode. Extensive experiment on different data types demonstrates the effectiveness of our algorithm.