Clustering Labeled Data and Cross-Validation for Classification with Few Positives in Yeast.
Miles TrochessetAnthony J. BonnerPublished in: BIOKDD (2004)
Keyphrases
- cross validation
- labeled data
- model selection
- unlabeled data
- training set
- training and test data
- text classification
- supervised learning
- semi supervised learning
- semi supervised
- class labels
- support vector
- data points
- semi supervised classification
- labeled and unlabeled data
- training data
- active learning
- unseen data
- unsupervised learning
- co training
- domain adaptation
- transfer learning
- class distribution
- generalization error
- hyperparameters
- training examples
- classification accuracy
- ls svm
- supervised classification
- pairwise constraints
- labeled instances
- binary classifiers
- labeled training data
- feature space
- learning algorithm
- labeled examples
- neural network
- multi label
- target domain
- binary classification
- incremental learning
- support vector machine svm
- nearest neighbor
- knn
- prior knowledge
- multitask learning
- k means
- decision trees
- data sets
- labeling effort