# FairNN- Conjoint Learning of Fair Representations for Fair Decisions

arXiv: https://arxiv.org/abs/2004.02173 · HTML: https://mlsanity.com/paper/2004.02173/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Apr 2020.

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

- [A survey on datasets for fairness-aware machine learning](https://mlsanity.com/paper/2110.00530/) (2021)
- [Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey](https://mlsanity.com/paper/2207.07068/) (2022)
- [Online Fairness-Aware Learning with Imbalanced Data Streams](https://mlsanity.com/paper/2108.06231/) (2021)
- [Fair Representation Learning for Continuous Sensitive Attributes using Expectation of Integral Probability Metrics](https://mlsanity.com/paper/2505.06435/) (2025)
- [Local Causal Discovery with Background Knowledge](https://mlsanity.com/paper/2408.07890/) (2024)
- [Multi-fairness under class-imbalance](https://mlsanity.com/paper/2104.13312/) (2021)
- [Parity-based Cumulative Fairness-aware Boosting](https://mlsanity.com/paper/2201.01148/) (2022)
- [Fairness in Federated Learning for Spatial-Temporal Applications](https://mlsanity.com/paper/2201.06598/) (2022)
- [Analysing Fairness of Privacy-Utility Mobility Models](https://mlsanity.com/paper/2304.06469/) (2023)
- [Bias Mitigation Methods for Binary Classification Decision-Making Systems: Survey and Recommendations](https://mlsanity.com/paper/2305.20020/) (2023)
- [Identifying Reasons for Bias: An Argumentation-Based Approach](https://mlsanity.com/paper/2310.16506/) (2023)

## Abstract (arXiv)

In this paper, we propose FairNN a neural network that performs joint feature representation and classification for fairness-aware learning. Our approach optimizes a multi-objective loss function in which (a) learns a fair representation by suppressing protected attributes (b) maintains the information content by minimizing a reconstruction loss and (c) allows for solving a classification task in a fair manner by minimizing the classification error and respecting the equalized odds-based fairness regularized. Our experiments on a variety of datasets demonstrate that such a joint approach is superior to separate treatment of unfairness in representation learning or supervised learning. Additionally, our regularizers can be adaptively weighted to balance the different components of the loss function, thus allowing for a very general framework for conjoint fair representation learning and decision making.