# CAD-VAE: Leveraging Correlation-Aware Latents for Comprehensive Fair Disentanglement

arXiv: https://arxiv.org/abs/2503.07938 · HTML: https://mlsanity.com/paper/2503.07938/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 56 references that are in the map.
- First posted on arXiv 11 Mar 2025.

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery](https://mlsanity.com/paper/2103.17249/) (2021)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Disentangling by Factorising](https://mlsanity.com/paper/1802.05983/) (2018)
- [Just Train Twice: Improving Group Robustness without Training Group Information](https://mlsanity.com/paper/2107.09044/) (2021)
- [Age Progression/Regression by Conditional Adversarial Autoencoder](https://mlsanity.com/paper/1702.08423/) (2017)
- [Learning Adversarially Fair and Transferable Representations](https://mlsanity.com/paper/1802.06309/) (2018)
- [Learning Not to Learn: Training Deep Neural Networks with Biased Data](https://mlsanity.com/paper/1812.10352/) (2018)
- [Fairness without Demographics through Adversarially Reweighted Learning](https://mlsanity.com/paper/2006.13114/) (2020)
- [Flexibly Fair Representation Learning by Disentanglement](https://mlsanity.com/paper/1906.02589/) (2019)
- [Path-Specific Counterfactual Fairness](https://mlsanity.com/paper/1802.08139/) (2018)
- [Effectively Unbiased FID and Inception Score and where to find them](https://mlsanity.com/paper/1911.07023/) (2019)
- [FairGAN: Fairness-aware Generative Adversarial Networks](https://mlsanity.com/paper/1805.11202/) (2018)
- [Disentangled Representation Learning](https://mlsanity.com/paper/2211.11695/) (2022)
- [Investigating Bias and Fairness in Facial Expression Recognition](https://mlsanity.com/paper/2007.10075/) (2020)
- [Fairness by Learning Orthogonal Disentangled Representations](https://mlsanity.com/paper/2003.05707/) (2020)
- [BiaSwap: Removing dataset bias with bias-tailored swapping augmentation](https://mlsanity.com/paper/2108.10008/) (2021)
- [FACET: Fairness in Computer Vision Evaluation Benchmark](https://mlsanity.com/paper/2309.00035/) (2023)
- [Guided Variational Autoencoder for Disentanglement Learning](https://mlsanity.com/paper/2004.01255/) (2020)
- [Mitigating Information Leakage in Image Representations: A Maximum Entropy Approach](https://mlsanity.com/paper/1904.05514/) (2019)
- [MotionCraft: Physics-based Zero-Shot Video Generation](https://mlsanity.com/paper/2405.13557/) (2024)
- [Fairness-aware Adversarial Perturbation Towards Bias Mitigation for Deployed Deep Models](https://mlsanity.com/paper/2203.01584/) (2022)
- [Counterfactual Fairness with Disentangled Causal Effect Variational Autoencoder](https://mlsanity.com/paper/2011.11878/) (2020)
- [README: REpresentation learning by fairness-Aware Disentangling MEthod](https://mlsanity.com/paper/2007.03775/) (2020)
- [Counterfactual Fairness by Combining Factual and Counterfactual Predictions](https://mlsanity.com/paper/2409.01977/) (2024)

## Built on by (most cited first, 11 of 11)

- [Sensitivity-LoRA: Low-Load Sensitivity-Based Fine-Tuning for Large Language Models](https://mlsanity.com/paper/2509.09119/) (2025)
- [Not All Directions Matter: Towards Structured and Task-Aware Low-Rank Model Adaptation](https://mlsanity.com/paper/2603.14228/) (2026)
- [Visual Variational Autoencoder Prompt Tuning](https://mlsanity.com/paper/2503.17650/) (2025)
- [Learning Straight Flows: Variational Flow Matching for Efficient Generation](https://mlsanity.com/paper/2511.17583/) (2025)
- [ShieldedCode: Learning Robust Representations for Virtual Machine Protected Code](https://mlsanity.com/paper/2601.20679/) (2026)
- [Stochastic Interpolants via Conditional Dependent Coupling](https://mlsanity.com/paper/2509.23122/) (2025)
- [Self-Supervised Visual Prompting for Cross-Domain Road Damage Detection](https://mlsanity.com/paper/2511.12410/) (2025)
- [Iterative Structured Pruning for Large Language Models with Multi-Domain Calibration](https://mlsanity.com/paper/2601.02674/) (2026)
- [Transition Flow Matching](https://mlsanity.com/paper/2603.15689/) (2026)
- [Drift Flow Matching](https://mlsanity.com/paper/2605.17244/) (2026)
- [Posterior Flow Matching](https://mlsanity.com/paper/2610.13994/) (2026)

## Abstract (arXiv)

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 CAD-VAE (Correlation-Aware Disentangled 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