Embedded Unsupervised Feature Selection
Embedded Unsupervised Feature Selection
复制标题
DOI：
10.1609/aaai.v29i1.9211
复制
发表时间：
2015-01
期刊：
影响因子：
--
通讯作者：
Suhang Wang;Jiliang Tang;Huan Liu
中科院分区：
文献类型：
--
作者：
Suhang Wang;Jiliang Tang;Huan Liu
稀疏学习已被证明是一种强大的监督特征选择技术，它允许将特征选择嵌入到分类（或回归）问题中。近年来，人们越来越关注备用学习在无监督特征选择中的应用。由于缺乏标签信息，这些算法中的绝大多数通常通过聚类算法生成聚类标签，然后使用这些生成的聚类标签将无监督特征选择制定为基于稀疏学习的有监督特征选择。在本文中，我们提出了一种新的无监督特征选择算法EUFS，它通过解析学习直接将特征选择嵌入到聚类算法中，而不需要进行转换。采用乘法器的交替方向法来解决EUFS的优化问题。在各种基准数据集上的实验结果证明了所提出的框架EUFS的有效性。
Sparse learning has been proven to be a powerful techniquein supervised feature selection, which allows toembed feature selection into the classification (or regression)problem. In recent years, increasing attentionhas been on applying spare learning in unsupervisedfeature selection. Due to the lack of label information,the vast majority of these algorithms usually generatecluster labels via clustering algorithms and then formulateunsupervised feature selection as sparse learningbased supervised feature selection with these generatedcluster labels. In this paper, we propose a novel unsupervisedfeature selection algorithm EUFS, which directlyembeds feature selection into a clustering algorithm viasparse learning without the transformation. The AlternatingDirection Method of Multipliers is used to addressthe optimization problem of EUFS. Experimentalresults on various benchmark datasets demonstrate theeffectiveness of the proposed framework EUFS.