# On Disentangled and Locally Fair Representations

arXiv: https://arxiv.org/abs/2205.02673 · HTML: https://mlsanity.com/paper/2205.02673/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 36 references that are in the map.
- First posted on arXiv 5 May 2022.

## Builds on (most cited first, 22 of 22)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Deep Learning and the Information Bottleneck Principle](https://mlsanity.com/paper/1503.02406/) (2015)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (2019)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [Deep Domain Confusion: Maximizing for Domain Invariance](https://mlsanity.com/paper/1412.3474/) (2014)
- [A Reductions Approach to Fair Classification](https://mlsanity.com/paper/1803.02453/) (2018)
- [On Fairness and Calibration](https://mlsanity.com/paper/1709.02012/) (2017)
- [Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment](https://mlsanity.com/paper/1610.08452/) (2016)
- [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)
- [Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations](https://mlsanity.com/paper/1707.00075/) (2017)
- [On the Fairness of Disentangled Representations](https://mlsanity.com/paper/1905.13662/) (2019)
- [Fader Networks: Manipulating Images by Sliding Attributes](https://mlsanity.com/paper/1706.00409/) (2017)
- [Achieving Fairness through Adversarial Learning: an Application to Recidivism Prediction](https://mlsanity.com/paper/1807.00199/) (2018)
- [Fairness Through Computationally-Bounded Awareness](https://mlsanity.com/paper/1803.03239/) (2018)
- [Fair Bayesian Optimization](https://mlsanity.com/paper/2006.05109/) (2020)
- [Auditing Black-box Models for Indirect Influence](https://mlsanity.com/paper/1602.07043/) (2016)
- [Penalizing Unfairness in Binary Classification](https://mlsanity.com/paper/1707.00044/) (2017)
- [Learning Fair Representations for Kernel Models](https://mlsanity.com/paper/1906.11813/) (2019)
- [Domain Intersection and Domain Difference](https://mlsanity.com/paper/1908.11628/) (2019)
- [A Two-Step Disentanglement Method](https://mlsanity.com/paper/1709.00199/) (2017)

## Abstract (arXiv)

We study the problem of performing classification in a manner that is fair for sensitive groups, such as race and gender. This problem is tackled through the lens of disentangled and locally fair representations. We learn a locally fair representation, such that, under the learned representation, the neighborhood of each sample is balanced in terms of the sensitive attribute. For instance, when a decision is made to hire an individual, we ensure that the K most similar hired individuals are racially balanced. Crucially, we ensure that similar individuals are found based on attributes not correlated to their race. To this end, we disentangle the embedding space into two representations. The first of which is correlated with the sensitive attribute while the second is not. We apply our local fairness objective only to the second, uncorrelated, representation. Through a set of experiments, we demonstrate the necessity of both disentangled and local fairness for obtaining fair and accurate representations. We evaluate our method on real-world settings such as predicting income and re-incarceration rate and demonstrate the advantage of our method.