PruneFuse combines pruning at initialization with weight fusion and knowledge distillation to make active learning data selection cheaper and to initialize the final model.
Deep active learning for named entity recognition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Pruning-based Data Selection and Network Fusion for Efficient Deep Learning
PruneFuse combines pruning at initialization with weight fusion and knowledge distillation to make active learning data selection cheaper and to initialize the final model.