CAD-VAE: Leveraging Correlation-Aware Latents for Comprehensive Fair Disentanglement
This addresses fairness issues in representation learning for AI applications, but it is incremental as it builds on existing disentanglement methods.
The paper tackles the problem of deep generative models inheriting biases by encoding sensitive attributes with predictive features, proposing CAD-VAE to separate overlapping factors using a correlated latent code, resulting in fairer representations and improved fairness-aware image editing as demonstrated on benchmark datasets.
While deep generative models have significantly advanced representation learning, they may inherit or amplify biases and fairness issues by encoding sensitive attributes alongside predictive features. Enforcing strict independence in disentanglement is often unrealistic when target and sensitive factors are naturally correlated. To address this challenge, we propose \textbf{CAD-VAE} (\textbf{C}orrelation-\textbf{A}ware \textbf{D}isentangled \textbf{VAE}), which introduces a correlated latent code to capture the information shared between the target and sensitive attributes. Given this correlated latent, our method effectively separates overlapping factors without extra domain knowledge by directly minimizing the conditional mutual information between target and sensitive codes. A relevance-driven optimization strategy refines the correlated code by efficiently capturing essential correlated features and eliminating redundancy. Extensive experiments on benchmark datasets demonstrate that CAD-VAE produces fairer representations, realistic counterfactuals, and improved fairness-aware image editing. Source code is available : https://github.com/merry7cherry/CAD-VAE