Return
Active forgetting with selective labeling for multi-task learning
DOI:10.1016/j.neucom.2026.134231.png)
Abstract
En 中文
• We propose an active forgetting framework for multi-task learning using selective labeling. • We introduce a multi-task unlearning approach that leverages inter-task and intra-task dependencies. • We achieve significant improvements over existing competitors in data selection and annotation strategies.
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W
Organization
No organization information available
Cited Papers
No cited papers available

