Post-processing via random selection or linear combination of differentially private models allows meeting arbitrary target privacy parameters without additional training.
arXiv preprint arXiv:2210.01864 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Differentially Private Model Merging
Post-processing via random selection or linear combination of differentially private models allows meeting arbitrary target privacy parameters without additional training.