A diffusion-based hypernetwork can generate classifier weights with near-zero accuracy on a requested forget class and near-retrained accuracy on retained classes.
Machine unlearning for random forests
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Learning to Forget using Hypernetworks
A diffusion-based hypernetwork can generate classifier weights with near-zero accuracy on a requested forget class and near-retrained accuracy on retained classes.