Laplacian-Based Dimensionality Reduction Including Spectral Clustering, Laplacian Eigenmap, Locality Preserving Projection, Graph Embedding, and Diffusion Map: Tutorial and Survey.
Benyamin GhojoghAli GhodsiFakhri KarrayMark CrowleyPublished in: CoRR (2021)
Keyphrases
- dimensionality reduction
- graph embedding
- spectral clustering
- locality preserving projections
- kernel pca
- locally linear embedding
- graph laplacian
- low dimensional
- manifold learning
- label information
- subspace learning
- manifold structure
- principal component analysis
- high dimensional data
- high dimensional
- data representation
- pairwise
- nonlinear dimensionality reduction
- linear discriminant analysis
- clustering method
- feature extraction
- data clustering
- pattern recognition
- unsupervised learning
- feature space
- high dimensionality
- dimension reduction
- input space
- data points
- euclidean space
- clustering algorithm
- dimensionality reduction methods
- k means
- euclidean distance
- metric learning
- pairwise constraints
- discriminant analysis
- feature selection
- singular value decomposition
- training set
- face recognition
- image segmentation
- sparse representation
- sparse coding
- semi supervised
- linear combination