摘要
为降低数据集中的噪声和异常值对算法的影响并考虑其内在的几何结构,文章给出一种基于L_(2,1)范数的图正则非负矩阵分解(_(2,1),GNMFL)方法,采用投影梯度法求解提出的模型。最后,在多个数据集上的实验结果验证了该算法的有效性。
In order to reduce the influence of noise and outliers in the data set on the algorithm.and consider its geometric structure.This paper presents a graph regular nonnegative matrix decomposition(L_(2,1) GNMFL)method based on L_(2,1) norms.The projection gradient method is used to solve the proposed model.Finally,the experimental results on several data sets verify the effectiveness of the algorithm.
作者
文学春
WEN Xuechun(School of Mathematical Sciences,Guizhou Normal University,Guiyang 550025,China)
出处
《计算机应用文摘》
2023年第1期105-109,共5页
Chinese Journal of Computer Application
关键词
非负矩阵分解L_(2
1)范数
图正则化
特征提取
nonnegative matrix factorization
L_(2,1)norms
graph regularization
feature extraction
