DELTA uses reinforcement learning to find useful feature transformations, then a disentangled variational autoencoder to generate transformed features that keep task utility while reducing sensitive-attribute prediction accuracy.
Feature construction and selection using genetic programming and a genetic algorithm,
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
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
DELTA: Variational Disentangled Learning for Privacy-Preserving Data Reprogramming
DELTA uses reinforcement learning to find useful feature transformations, then a disentangled variational autoencoder to generate transformed features that keep task utility while reducing sensitive-attribute prediction accuracy.