An automated pruning pipeline that skips fine-tuning when accuracy drop is small and freezes less sensitive layers, cutting pruning time up to 9.61x with similar final accuracy.
Automatic attention pruning: Improv- ing and automating model pruning using attentions,
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
-
ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks
An automated pruning pipeline that skips fine-tuning when accuracy drop is small and freezes less sensitive layers, cutting pruning time up to 9.61x with similar final accuracy.