English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The problem of fair classification can be mollified if we develop a method toremove the embedded sensitive information from the classification features.This line of separating the sensitive information is developed through thecausal inference, and the causal inference enables the counterfactualgenerations to contrast the what-if case of the opposite sensitive attribute.Along with this separation with the causality, a frequent assumption in thedeep latent causal model defines a single latent variable to absorb the entireexogenous uncertainty of the causal graph. However, we claim that suchstructure cannot distinguish the 1) information caused by the intervention(i.e., sensitive variable) and 2) information correlated with the interventionfrom the data. Therefore, this paper proposes Disentangled Causal EffectVariational Autoencoder (DCEVAE) to resolve this limitation by disentanglingthe exogenous uncertainty into two latent variables: either 1) independent tointerventions or 2) correlated to interventions without causality.Particularly, our disentangling approach preserves the latent variablecorrelated to interventions in generating counterfactual examples. We show thatour method estimates the total effect and the counterfactual effect without acomplete causal graph. By adding a fairness regularization, DCEVAE generates acounterfactual fair dataset while losing less original information. Also,DCEVAE generates natural counterfactual images by only flipping sensitiveinformation. Additionally, we theoretically show the differences in thecovariance structures of DCEVAE and prior works from the perspective of thelatent disentanglement.

Counterfactual Fairness with Disentangled Causal Effect Variational Autoencoder