Manifold-based Verbalizer Space Re-embedding for Tuning-free Prompt-based Classification.
Haochun WangSendong ZhaoChi LiuNuwa XiMuzhen CaiBing QinTing LiuPublished in: CoRR (2023)
Keyphrases
- low dimensional
- decision trees
- embedding space
- manifold learning
- classification accuracy
- support vector
- feature space
- pattern recognition
- graph embedding
- nonlinear dimensionality reduction
- feature extraction
- geodesic distance
- search space
- face recognition
- vector space
- locality preserving projections
- classification method
- pairwise distances
- classification scheme
- euclidean space
- pattern classification
- image classification
- neural network
- machine learning
- support vector machine
- training set
- data sets
- class labels
- manifold embedding
- feature selection
- training data
- multidimensional scaling
- riemannian manifolds
- linear subspace
- feature vectors
- supervised learning
- feature set
- parameter space
- dimension reduction