Pairwise Sparsity Preserving Embedding for Unsupervised Subspace Learning and Classification
Pairwise Sparsity Preserving Embedding for Unsupervised Subspace Learning and Classification
复制标题
DOI：
10.1109/tip.2013.2277780
复制
发表时间：
2013-12
影响因子：
10.6
通讯作者：
Zhao Zhang;Shuicheng Yan;Mingbo Zhao
中科院分区：
文献类型：
--
作者：
Zhao Zhang;Shuicheng Yan;Mingbo Zhao
提出了两种新的无监督降维技术，称为稀疏距离保持嵌入（SDPE）和稀疏邻近保持嵌入（SPPE），用于特征提取和分类。SDPE和SPPE在稀疏表示恢复的干净数据空间中执行，并且在去除噪声的数据上使用增强的欧几里得距离来测量点的成对相似性。在提取信息特征时，SDPE和SPPE的目标是除了保留稀疏特征之外，还保留数据点之间的成对相似性。本文通过一个凸优化算法计算所有向量的稀疏表示。稀疏编码能够保留数据的局部信息，使SDPE和SPPE具有自然的鉴别能力、自适应的邻域以及对低维嵌入中的噪声和错误的鲁棒性。我们还从数学上证明了SDPE和SPPE可以有效地扩展到有监督的判别学习中。SDPE和SPPE的有效性进行了大量的模拟检查。与其他相关的国家的最先进的无监督算法的比较表明，有前途的结果提供了我们的技术。
Two novel unsupervised dimensionality reduction techniques, termed sparse distance preserving embedding (SDPE) and sparse proximity preserving embedding (SPPE), are proposed for feature extraction and classification. SDPE and SPPE perform in the clean data space recovered by sparse representation and enhanced Euclidean distances over noise removed data are employed to measure pairwise similarities of points. In extracting informative features, SDPE and SPPE aim at preserving pairwise similarities between data points in addition to preserving the sparse characteristics. This paper calculates the sparsest representation of all vectors jointly by a convex optimization. The sparsest codes enable certain local information of data to be preserved, and can endow SDPE and SPPE a natural discriminating power, adaptive neighborhood and robust characteristic against noise and errors in delivering low-dimensional embeddings. We also mathematically show SDPE and SPPE can be effectively extended for discriminant learning in a supervised manner. The validity of SDPE and SPPE is examined by extensive simulations. Comparison with other related state-of-the-art unsupervised algorithms show that promising results are delivered by our techniques.