让生成模型在保留相关性的同时分离敏感属性，提升公平性
CAD-VAE: Leveraging Correlation-Aware Latents for Comprehensive Fair Disentanglement
- 引入相关性感知隐变量捕捉目标与敏感属性的共现信息
- 通过最小化条件互信息实现无额外知识的公平解耦
- 适合需要公平图像生成与编辑的研究者使用
深度生成模型虽推动了表征学习发展，但可能在编码中继承或放大偏见与公平性问题。当目标因素与敏感属性天然相关时，强制完全独立解耦不现实。为此，本文提出CAD-VAE（相关性感知解耦变分自编码器），引入一个相关隐变量以捕获目标与敏感属性间的共享信息。在此基础上，通过直接最小化目标与敏感代码间的条件互信息，实现无需额外领域知识的有效解耦。同时，采用基于重要性的优化策略，高效提取关键相关特征并消除冗余。在基准数据集上的大量实验表明，CAD-VAE能生成更公平的表示、更真实的反事实样本，并提升公平感知的图像编辑能力。源代码已公开：https://github.com/merry7cherry/CAD-VAE
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。