A progressive scheduling trick that updates only the last remaining blocks in later epochs reduces parameter-update counts by about 25% with roughly unchanged GLUE and SQuAD scores.
Parameter-efficient transfer learning for nlp,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Progtuning: Progressive Fine-tuning Framework for Transformer-based Language Models
A progressive scheduling trick that updates only the last remaining blocks in later epochs reduces parameter-update counts by about 25% with roughly unchanged GLUE and SQuAD scores.