Generating Unbiased Pseudo-labels via a Theoretically Guaranteed Chebyshev Constraint to Unify Semi-supervised Classification and Regression.
Jiaqi WuJunbiao PangQingming HuangPublished in: CoRR (2023)
Keyphrases
- semi supervised classification
- pairwise constraints
- semi supervised
- pairwise
- semi supervised learning
- unlabeled data
- labeled data
- spectral clustering
- data representation
- document clustering
- training data
- regression model
- model selection
- support vector
- class labels
- distance metric
- metric learning
- training examples
- support vector regression
- loss function
- machine learning
- text classification
- text mining
- learning algorithm