Bridging the Gap: Neural Collapse Inspired Prompt Tuning for Generalization under Class Imbalance.
Didi ZhuYinchuan LiMin ZhangJunkun YuanJiashuo LiuZexi LiKun KuangChao WuPublished in: CoRR (2023)
Keyphrases
- class imbalance
- class distribution
- active learning
- cost sensitive
- cost sensitive learning
- high dimensionality
- imbalanced datasets
- random subspaces
- small disjuncts
- neural network
- concept drift
- feature selection
- minority class
- majority class
- software defect prediction
- sampling methods
- imbalanced data
- multi class
- error prone
- training samples
- supervised learning
- training set
- data streams
- training data