Does Decentralized Learning with Non-IID Unlabeled Data Benefit from Self Supervision?
Lirui WangKaiqing ZhangYunzhu LiYonglong TianRuss TedrakePublished in: CoRR (2022)
Keyphrases
- unlabeled data
- active learning
- supervised learning
- learning algorithm
- labeled and unlabeled data
- semi supervised learning
- labeled data
- semi supervised
- co training
- domain adaptation
- sample selection bias
- prior knowledge
- learning process
- learning tasks
- positive examples
- learning frameworks
- multi view learning
- supervised learning algorithms
- class labels
- probabilistic model
- semi supervised classification
- training data
- human experts
- learning problems
- information retrieval
- kernel learning
- labeled examples
- feature space
- training set
- data points
- transfer learning
- background knowledge
- text categorization
- model selection
- text classification
- dimensionality reduction