Dataset Similarity to Assess Semisupervised Learning Under Distribution Mismatch Between the Labeled and Unlabeled Datasets.
Saúl Calderón RamírezLuis OalaJordina Torrents-BarrenaShengxiang YangDavid A. ElizondoArmaghan MoemeniSimon Colreavy-DonnellyWojciech SamekMiguel A. Molina-CabelloEzequiel López-RubioPublished in: IEEE Trans. Artif. Intell. (2023)
Keyphrases
- semisupervised learning
- supervised learning
- unlabeled data
- semi supervised learning
- labeled examples
- labeled data
- synthetic datasets
- training data
- co training
- ground truth labels
- active learning
- supervised and unsupervised learning
- similarity measure
- semi supervised
- unsupervised learning
- data sets
- training set
- machine learning
- text classification
- feature set
- training examples
- prior knowledge
- natural language processing
- data points
- text categorization
- class labels
- cost sensitive
- statistical learning
- data analysis
- label propagation
- image segmentation
- information retrieval