ALLSH: Active Learning Guided by Local Sensitivity and Hardness.
Shujian ZhangChengyue GongXingchao LiuPengcheng HeWeizhu ChenMingyuan ZhouPublished in: CoRR (2022)
Keyphrases
- active learning
- sensitivity analysis
- semi supervised
- phase transition
- random sampling
- selective sampling
- learning strategies
- high sensitivity
- np complete
- supervised learning
- relevance feedback
- sample selection
- labeled data
- unlabeled data
- machine learning
- neural network
- crowd sourced
- active learning strategies
- batch mode
- pool based active learning
- np hardness
- imbalanced data classification
- learning theory
- information theoretic
- real time
- class imbalance
- cost sensitive
- training examples
- online learning
- support vector machine
- np hard
- training set
- batch mode active learning
- learning algorithm
- music emotion classification