In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning.
Mamshad Nayeem RizveKevin DuarteYogesh Singh RawatMubarak ShahPublished in: ICLR (2021)
Keyphrases
- semi supervised learning
- label propagation
- unsupervised learning
- manifold regularization
- semi supervised
- active learning
- unlabeled data
- regularization framework
- labeled data
- discriminative models
- supervised learning
- training data
- boosting framework
- multi label classification
- multi view learning
- multiple instance learning
- co training
- machine learning
- semi supervised classification
- partially labeled
- natural language processing
- graph based semi supervised learning
- pairwise constraints
- dimensionality reduction
- semi supervised learning algorithms
- unlabeled instances