A consensus of multiple similarity metrics selects which layers to prune, preserving accuracy, reducing computation, and improving robustness in the tested models.
A survey on deep neural network pruning: Taxonomy, comparison, analysis, and recommen- dations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Layer Pruning with Consensus: A Triple-Win Solution
A consensus of multiple similarity metrics selects which layers to prune, preserving accuracy, reducing computation, and improving robustness in the tested models.