PEER trains a proxy model on augmented data under mutual information regularization, then periodically averages proxy snapshots into the task model, improving out-of-distribution accuracy and reducing mid-training fluctuation.
Guerrero Peña, Heitor Rapela Medeiros, Thomas Dubail, Eric Granger, and Marco Pedersoli
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
-
PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization
PEER trains a proxy model on augmented data under mutual information regularization, then periodically averages proxy snapshots into the task model, improving out-of-distribution accuracy and reducing mid-training fluctuation.