# Fair Representations by Compression

arXiv: https://arxiv.org/abs/2105.14044 · HTML: https://mlsanity.com/paper/2105.14044/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 48 references that are in the map.
- First posted on arXiv 28 May 2021.

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

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [Conditional Image Generation with PixelCNN Decoders](https://mlsanity.com/paper/1606.05328/) (2016)
- [Pixel Recurrent Neural Networks](https://mlsanity.com/paper/1601.06759/) (2016)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [A Reductions Approach to Fair Classification](https://mlsanity.com/paper/1803.02453/) (2018)
- [Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness](https://mlsanity.com/paper/1711.05144/) (2017)
- [Learning Adversarially Fair and Transferable Representations](https://mlsanity.com/paper/1802.06309/) (2018)
- [Lossy Image Compression with Compressive Autoencoders](https://mlsanity.com/paper/1703.00395/) (2017)
- [Revisiting Classifier Two-Sample Tests](https://mlsanity.com/paper/1610.06545/) (2016)
- [The Variational Fair Autoencoder](https://mlsanity.com/paper/1511.00830/) (2015)
- [Emergence of Invariance and Disentanglement in Deep Representations](https://mlsanity.com/paper/1706.01350/) (2017)
- [Flexibly Fair Representation Learning by Disentanglement](https://mlsanity.com/paper/1906.02589/) (2019)
- [Censoring Representations with an Adversary](https://mlsanity.com/paper/1511.05897/) (2015)
- [FairGAN: Fairness-aware Generative Adversarial Networks](https://mlsanity.com/paper/1805.11202/) (2018)
- [Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations](https://mlsanity.com/paper/1704.00648/) (2017)
- [On the Fairness of Disentangled Representations](https://mlsanity.com/paper/1905.13662/) (2019)
- [The Frontiers of Fairness in Machine Learning](https://mlsanity.com/paper/1810.08810/) (2018)
- [Conditional Probability Models for Deep Image Compression](https://mlsanity.com/paper/1801.04260/) (2018)
- [Invariant Representations without Adversarial Training](https://mlsanity.com/paper/1805.09458/) (2018)
- [Learning Controllable Fair Representations](https://mlsanity.com/paper/1812.04218/) (2018)
- [Fairness Through Computationally-Bounded Awareness](https://mlsanity.com/paper/1803.03239/) (2018)
- [A Closer Look at the Optimization Landscapes of Generative Adversarial Networks](https://mlsanity.com/paper/1906.04848/) (2019)
- [Creating Fair Models of Atherosclerotic Cardiovascular Disease Risk](https://mlsanity.com/paper/1809.04663/) (2018)
- [Provably Fair Representations](https://mlsanity.com/paper/1710.04394/) (2017)
- [Invariant Representations through Adversarial Forgetting](https://mlsanity.com/paper/1911.04060/) (2019)
- [Unsupervised Adversarial Invariance](https://mlsanity.com/paper/1809.10083/) (2018)
- [Learning Smooth and Fair Representations](https://mlsanity.com/paper/2006.08788/) (2020)
- [Learning unbiased features](https://mlsanity.com/paper/1412.5244/) (2014)

## Built on by (most cited first, 7 of 7)

- [The Pursuit of Fairness in Artificial Intelligence Models: A Survey](https://mlsanity.com/paper/2403.17333/) (2024)
- [Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learning](https://mlsanity.com/paper/2203.12748/) (2022)
- [Ultra-marginal Feature Importance: Learning from Data with Causal Guarantees](https://mlsanity.com/paper/2204.09938/) (2022)
- [SoFaiR: Single Shot Fair Representation Learning](https://mlsanity.com/paper/2204.12556/) (2022)
- [Ex-Ante Assessment of Discrimination in Dataset](https://mlsanity.com/paper/2208.07918/) (2022)
- [Learning and DiSentangling Patient Static Information from Time-series Electronic HEalth Record (STEER)](https://mlsanity.com/paper/2309.11373/) (2023)
- [Differential Adjusted Parity for Learning Fair Representations](https://mlsanity.com/paper/2502.09765/) (2025)

## Abstract (arXiv)

Organizations that collect and sell data face increasing scrutiny for the discriminatory use of data. We propose a novel unsupervised approach to transform data into a compressed binary representation independent of sensitive attributes. We show that in an information bottleneck framework, a parsimonious representation should filter out information related to sensitive attributes if they are provided directly to the decoder. Empirical results show that the proposed method, FBC, achieves state-of-the-art accuracy-fairness trade-off. Explicit control of the entropy of the representation bit stream allows the user to move smoothly and simultaneously along both rate-distortion and rate-fairness curves. endabstract