COLUR restores a noise-damaged model by having a clean teacher flag confident disagreements, unlearning them with label-smoothed gradient ascent, and relearning from mixed soft labels, beating nine baselines on four datasets.
Label smoothing improves machine unlearning, 2024
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
-
COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement
COLUR restores a noise-damaged model by having a clean teacher flag confident disagreements, unlearning them with label-smoothed gradient ascent, and relearning from mixed soft labels, beating nine baselines on four datasets.