Ensemble Method for Unsupervised Feature Selection
For many large-scale datasets it is necessary to reduce dimensionality to the point where further exploration and analysis can take place. As a result, it is important to develop techniques for selecting features from largescale datasets. However this topic has been well studied in supervised learning area, there are only a few methods proposed for feature selection for clustering. In this paper, we propose a novel ensemble unsupervised feature selection algorithm, in which individual component algorithm uses cluster result obtained in the space of a feature subset of original features to only evaluate every feature in that feature subset. Our experiments with several data sets demonstrate that the proposed algorithm is able to obtain a better and more stable feature subset compared with other existing unsupervised feature selection algorithms.
feature selection unsupervised learning clustering ensemble
Yihui Luo Shuchu Xiong
Department of Information Hunan University of Commerce Changsha, P.R. of China
国际会议
长沙
英文
3492-3495
2009-10-10（万方平台首次上网日期，不代表论文的发表时间）