# README: REpresentation learning by fairness-Aware Disentangling MEthod

arXiv: https://arxiv.org/abs/2007.03775 · HTML: https://mlsanity.com/paper/2007.03775/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jul 2020.

## Built on by (most cited first, 10 of 10)

- [FairMask: Better Fairness via Model-based Rebalancing of Protected Attributes](https://mlsanity.com/paper/2110.01109/) (2021)
- [Last-Layer Fairness Fine-tuning is Simple and Effective for Neural Networks](https://mlsanity.com/paper/2304.03935/) (2023)
- [CAD-VAE: Leveraging Correlation-Aware Latents for Comprehensive Fair Disentanglement](https://mlsanity.com/paper/2503.07938/) (2025)
- [Distributionally Generative Augmentation for Fair Facial Attribute Classification](https://mlsanity.com/paper/2403.06606/) (2024)
- [Deep Generative Views to Mitigate Gender Classification Bias Across Gender-Race Groups](https://mlsanity.com/paper/2208.08382/) (2022)
- [Fairness-aware Vision Transformer via Debiased Self-Attention](https://mlsanity.com/paper/2301.13803/) (2023)
- [Achieving Fairness Across Local and Global Models in Federated Learning](https://mlsanity.com/paper/2406.17102/) (2024)
- [Mitigating Bias in Visual Transformers via Targeted Alignment](https://mlsanity.com/paper/2302.04358/) (2023)
- [FairViT: Fair Vision Transformer via Adaptive Masking](https://mlsanity.com/paper/2407.14799/) (2024)
- [The Fairness Stitch: Unveiling the Potential of Model Stitching in Neural Network De-Biasing](https://mlsanity.com/paper/2311.03532/) (2023)

## Abstract (arXiv)

Fair representation learning aims to encode invariant representation with respect to the protected attribute, such as gender or age. In this paper, we design Fairness-aware Disentangling Variational AutoEncoder (FD-VAE) for fair representation learning. This network disentangles latent space into three subspaces with a decorrelation loss that encourages each subspace to contain independent information: 1) target attribute information, 2) protected attribute information, 3) mutual attribute information. After the representation learning, this disentangled representation is leveraged for fairer downstream classification by excluding the subspace with the protected attribute information. We demonstrate the effectiveness of our model through extensive experiments on CelebA and UTK Face datasets. Our method outperforms the previous state-of-the-art method by large margins in terms of equal opportunity and equalized odds.