Counterfactual Fairness with Disentangled Causal Effect Variational Autoencoder

by   Hyemi Kim, et al.

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


Disentangled Representation with Causal Constraints for Counterfactual Fairness

Much research has been devoted to the problem of learning fair represent...

VACA: Design of Variational Graph Autoencoders for Interventional and Counterfactual Queries

In this paper, we introduce VACA, a novel class of variational graph aut...

Decomposition of Total Effect with the Notion of Natural Counterfactual Interaction Effect

Mediation analysis serves as a crucial tool to obtain causal inference b...

A Critical Look At The Identifiability of Causal Effects with Deep Latent Variable Models

Using deep latent variable models in causal inference has attracted cons...

Adaptation Speed Analysis for Fairness-aware Causal Models

For example, in machine translation tasks, to achieve bidirectional tran...

Path-Specific Counterfactual Fairness

We consider the problem of learning fair decision systems in complex sce...

Achieving Counterfactual Fairness for Causal Bandit

In online recommendation, customers arrive in a sequential and stochasti...

Please sign up or login with your details

Forgot password? Click here to reset