一种基于局部和相似性嵌入的特征选择算法

A Feature Selection Method Based on Locality and Similarity Embedding

现有的特征选择算法更多的只强调数据局部性,忽略了数据间的相似性。针对这一问题,提出一种基于局部和相似性嵌入的特征选择算法,将图学习、特征选择和稀疏编码并入到同一个模型中,强调数据的局部性和相似结构,通过寻找一个能保持数据局部性和相似性的投影矩阵来选择最相关的特征。通过实验与目前流行的几种算法进行对比,验证了本文方法的有效性。

Most of the existing feature selection algorithms only emphasize the locality of data and ignore the similarity between data samples.In order to solve the problem,a feature selection method based on locality and Similarity embedding was proposed.Graph learning,feature selection and sparse coding were integrated into a framework,emphasizing the locality and similar structure of data at the same time.Aims to find a projection matrix that can maintain the locality and similarity of data and then select the most relevant features.The effectiveness of the proposed method is verified by comparison with several popular algorithms.