Combating Noisy-Labeled and Imbalanced Data by Two Stage Bi-Dimensional Sample Selection.
Yiliang ZhangYang LuBo HanYiu-ming CheungHanzi WangPublished in: CoRR (2022)
Keyphrases
- imbalanced data
- sample selection
- training data
- support vector machine
- class distribution
- active learning
- classification models
- class imbalance
- decision trees
- training set
- supervised learning
- sampling methods
- feature selection
- linear regression
- classification accuracy
- data sets
- svm classifier
- selection strategy
- ensemble methods
- minority class
- training process
- machine learning
- naive bayes
- test set
- support vector machine svm
- training samples
- semi supervised learning
- k nearest neighbor
- kernel function
- test data
- training examples
- unlabeled data
- random forest
- generalization error
- labeled data
- dimensionality reduction
- multi class
- support vector
- learning algorithm
- data mining