GEM selects fine-tuning parameters by gradient-to-weight ratio and distributes the budget by layer entropy, reaching 0.1% parameter updates with small accuracy gains on several NLP tasks.
Recursive deep models for semantic compositionality over a sentiment treebank
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
-
GEM: A Scale-Aware and Distribution-Sensitive Sparse Fine-Tuning Framework for Effective Downstream Adaptation
GEM selects fine-tuning parameters by gradient-to-weight ratio and distributes the budget by layer entropy, reaching 0.1% parameter updates with small accuracy gains on several NLP tasks.