An invertible module attached to a frozen pretrained generative model disentangles labels from sensitive attributes in latent space, improving fairness metrics and enabling counterfactual explanations.
Title resolution pending
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
-
Constructing Fair Latent Space for Intersection of Fairness and Explainability
An invertible module attached to a frozen pretrained generative model disentangles labels from sensitive attributes in latent space, improving fairness metrics and enabling counterfactual explanations.