Unfolding Kernel embeddings of graphs: Enhancing class separation through manifold learning.
Luca RossiAndrea TorselloEdwin R. HancockPublished in: Pattern Recognit. (2015)
Keyphrases
- manifold learning
- laplacian eigenmaps
- low dimensional
- semi supervised
- neighborhood graph
- dimensionality reduction
- feature space
- dimension reduction
- high dimensional
- nonlinear dimensionality reduction
- feature extraction
- high dimensional data
- subspace learning
- diffusion maps
- locality preserving projections
- head pose estimation
- geodesic distance
- graph embedding
- manifold structure
- discriminant embedding
- latent space
- riemannian manifolds
- sparse representation
- kernel function
- least squares
- reproducing kernel hilbert space
- principal component analysis
- pairwise
- learning algorithm
- locally linear embedding
- high dimensionality
- data points
- embedding space
- manifold embedding
- data sets