A hybrid unlearning framework switches between partial retraining and direct parameter updates, with an optimized variant that retrains the last few slices after subtraction, reporting 1.5x to 8x speedups at comparable accuracy.
In: Proceed- ings of the ACM Web Conference 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A hybrid framework for effective and efficient machine unlearning
A hybrid unlearning framework switches between partial retraining and direct parameter updates, with an optimized variant that retrains the last few slices after subtraction, reporting 1.5x to 8x speedups at comparable accuracy.