Double graphs-based discriminant projections for dimensionality reduction.
Jianping GouYa XueHongxing MaYong LiuYongzhao ZhanJia KePublished in: Neural Comput. Appl. (2020)
Keyphrases
- dimensionality reduction
- principal component analysis
- linear projection
- low dimensional
- graph embedding
- feature extraction
- locality preserving projections
- linear discriminant
- discriminant analysis
- graph construction
- class separability
- linear dimensionality reduction
- linear discriminant analysis
- high dimensional
- discriminant projection
- high dimensional data
- discriminant information
- graph theory
- pattern recognition
- high dimensionality
- feature selection
- data representation
- structure preserving
- feature space
- graph matching
- principal components
- data points
- manifold learning
- pattern recognition and machine learning
- three dimensional
- tomographic reconstruction
- nonlinear dimensionality reduction
- random projections
- graph theoretic
- lower dimensional
- subspace learning
- dimensionality reduction methods
- weighted graph
- graph kernels
- graph databases
- radon transform
- data sets
- dimension reduction
- directed graph
- kernel learning
- graph partitioning
- undirected graph
- graph mining
- discrete tomography
- bipartite graph
- distance measure
- face recognition
- neural network