An information-theoretic approach to unsupervised feature selection for high-dimensional data.
Shao-Lun HuangLin ZhangLizhong ZhengPublished in: ITW (2017)
Keyphrases
- high dimensional data
- unsupervised feature selection
- dimensionality reduction
- low dimensional
- cluster structure
- nearest neighbor
- data matrix
- high dimensional
- original data
- feature selection
- high dimensionality
- missing values
- subspace clustering
- sparse representation
- data sets
- data points
- similarity search
- dimension reduction
- principal component analysis
- data analysis
- data clustering
- manifold learning
- data distribution
- low rank
- pattern recognition
- linear discriminant analysis
- gene expression data
- data mining applications
- unsupervised learning
- feature extraction
- data representation
- image data
- singular value decomposition
- database