When less is more: on the value of "co-training" for semi-supervised software defect predictors.
Suvodeep MajumderJoymallya ChakrabortyTim MenziesPublished in: Empir. Softw. Eng. (2024)
Keyphrases
- co training
- software defect
- semi supervised
- semi supervised learning
- unlabeled data
- software defect prediction
- unlabelled data
- labeled data
- high confidence
- multi view
- supervised learning
- unsupervised learning
- labeled examples
- active learning
- single view
- semi supervised learning algorithms
- semi supervised classification
- pairwise
- confidence estimates
- labeled training data
- text classification
- small set of labeled
- ensemble learning
- partially labeled data
- machine learning
- named entities
- semi supervised learning methods
- training data
- labeled and unlabeled data
- gaussian process
- multi view learning
- neural network
- high dimensionality
- training examples
- feature selection