Unsupervised feature selection through Gram-Schmidt orthogonalization—A word co-occurrence perspective

详细信息    查看全文

• 作者：Deqing Wang^a ; ^{dqwang@buaa.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Hui Zhang^a ; ^{hzhang@nlsde.buaa.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Rui Liu^a ; ^{liurui@nlsde.buaa.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Xianglong Liu^a ; ^{xlong_liu@nlsde.buaa.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Jing Wang^b ; ^{jim08@buaa.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae
• 关键词：Feature selection ; Random projection ; Gram&ndash ; Schmidt orthogonalization ; Basis features ; Word co-occurrence matrix
• 刊名：Neurocomputing
• 出版年：2016
• 出版时间：15 January 2016
• 年：2016
• 卷：173
• 期：part_P3
• 页码：845-854
• 全文大小：1163 K

文摘

Feature selection is a key step in many machine learning applications, such as categorization, and clustering. Especially for text data, the original document-term matrix is high-dimensional and sparse, which affects the performance of feature selection algorithms. Meanwhile, labeling training instance is time-consuming and expensive. So unsupervised feature selection algorithms have attracted more attention. In this paper, we propose an unsupervised feature selection algorithm through $\underline{R}$ andom $\underline{P}$ rojection and $\underline{G}$ ram-$\underline{G}$ chmidt $\underline{O}$ rthogonalization (RP-GSO) from the word co-occurrence matrix. The RP-GSO algorithm has three advantages: (1) it takes as input dense word co-occurrence matrix, avoiding the sparseness of original document-term matrix; (2) it selects “basis features” by Gram–Schmidt process, guaranteeing the orthogonalization of feature space; and (3) it adopts random projection to speed up GS process. Extensive experimental results show our proposed RP-GSO approach achieves better performance comparing against supervised and unsupervised feature selection methods in text classification and clustering tasks.