Pseudo-Labeling with Graph Active Learning for Few-shot Node Classification.
Quan LiLingwei ChenShixiong JingDinghao WuPublished in: ICDM (2023)
Keyphrases
- active learning
- batch mode active learning
- selective sampling
- classification accuracy
- machine learning
- directed graph
- supervised learning
- active learning framework
- graph structure
- pattern recognition
- sample selection
- feature vectors
- annotation effort
- random sampling
- unsupervised learning
- feature extraction
- text classification
- learning algorithm
- classification algorithm
- training examples
- feature space
- label propagation
- imbalanced data classification
- decision trees
- support vector
- labeling effort
- labeled instances
- training set
- class imbalance
- support vector machine
- image classification
- graph theory
- random walk
- undirected graph
- semi supervised learning
- cost sensitive
- labeling process
- video content
- rare class
- active learning strategies
- connected components
- visual features
- feature selection
- labeled data