Improved Multi-label Classification under Temporal Concept Drift: Rethinking Group-Robust Algorithms in a Label-Wise Setting.
Ilias ChalkidisAnders SøgaardPublished in: ACL (Findings) (2022)
Keyphrases
- multi label classification
- concept drift
- multi label
- classification algorithm
- data streams
- label space
- learning algorithm
- data structure
- benchmark datasets
- graph cuts
- text categorization
- prediction accuracy
- data sets
- image classification
- multi class
- prior knowledge
- binary classification
- image segmentation
- neural network