Checkpoint fusion guided by a 'forget' metric, followed by distillation, lets a single model recover test points that were learned and then forgotten during training, improving accuracy, especially under label noise.
A survey on ensemble learning under the era of deep learning,
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
-
Forget Me Not: Fighting Local Overfitting with Knowledge Fusion and Distillation
Checkpoint fusion guided by a 'forget' metric, followed by distillation, lets a single model recover test points that were learned and then forgotten during training, improving accuracy, especially under label noise.