Local Discriminative Based Sparse Subspace Learning for Feature Selection
Local Discriminative Based Sparse Subspace Learning for Feature Selection
复制标题
基于局部判别的稀疏子空间学习用于特征选择
DOI：
10.1016/j.patcog.2019.03.026
复制
发表时间：
2019
影响因子：
8
通讯作者：
Licheng Jiao
中科院分区：
文献类型：
--
作者：
Ronghua Shang;Yang Meng;Wenbing Wang;Fanhua Shang;Licheng Jiao
子空间学习是一种矩阵分解方法。一些算法将子空间学习应用于特征选择，但忽略了数据中包含的局部判别信息。在本文中，我们提出了一个新的无监督的特征选择算法来解决这个问题，这是所谓的局部判别式的稀疏子空间学习特征选择（LDSSL）。我们首先介绍了一个局部判别模型在我们的特征选择框架的子空间学习。该模型同时保留了数据的局部判别结构和局部几何结构。该算法不仅提高了算法的判别能力，而且充分利用了数据中所包含的局部几何结构信息。局部判别模型是一种线性模型，不能有效地处理非线性数据。因此，我们需要对局部判别模型进行核化以得到非线性版本。然后引入L1范数对特征选择矩阵进行约束，保证了特征选择矩阵的稀疏性，提高了算法的鉴别能力。然后给出了算法的目标函数、收敛性证明和迭代更新规则。我们比较LDSSL与八个国家的最先进的算法在六个数据集。实验结果表明，LDSSL是更有效的比其他八个特征选择算法。
Subspace learning is a matrix decomposition method. Some algorithms apply subspace learning to feature selection, but they ignore the local discriminative information contained in data. In this paper, we propose a new unsupervised feature selection algorithm to address this issue, which is called local discriminative based sparse subspace learning for feature selection (LDSSL). We first introduce a local discriminant model in our feature selection framework of subspace learning. This model preserves both the local discriminant structure and local geometric structure of the data, simultaneously. It can not only improve the discriminate ability of the algorithm, but also utilize the local geometric structure information contained in data. Local discriminant model is a linear model, which cannot deal with nonlinear data effectively. Therefore, we need to kernelize the local discriminant model to get a nonlinear version. We next introduce theL1-normto constrain the feature selection matrix, and this can ensure the sparsity of the feature selection matrix and improve the algorithm's discriminate ability. Then we give the objective function, convergence proof and iterative update rules of the algorithm. We compare LDSSL with eight state-of-the-art algorithms on six datasets. The experimental results show that LDSSL is more effective than eight other feature selection algorithms.