# FNNC: Achieving Fairness through Neural Networks

arXiv: https://arxiv.org/abs/1811.00247 · HTML: https://mlsanity.com/paper/1811.00247/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Nov 2018.

## Built on by (most cited first, 30 of 43)

- [Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey](https://mlsanity.com/paper/2207.07068/) (2022)
- [Leveling Down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifiers](https://mlsanity.com/paper/2203.04913/) (2022)
- [Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition](https://mlsanity.com/paper/2210.09943/) (2022)
- [FairTune: Optimizing Parameter Efficient Fine Tuning for Fairness in Medical Image Analysis](https://mlsanity.com/paper/2310.05055/) (2023)
- [Technical Challenges for Training Fair Neural Networks](https://mlsanity.com/paper/2102.06764/) (2021)
- [Last-Layer Fairness Fine-tuning is Simple and Effective for Neural Networks](https://mlsanity.com/paper/2304.03935/) (2023)
- [Optimal Transport of Classifiers to Fairness](https://mlsanity.com/paper/2202.03814/) (2022)
- [OxonFair: A Flexible Toolkit for Algorithmic Fairness](https://mlsanity.com/paper/2407.13710/) (2024)
- [Robustness Disparities in Commercial Face Detection](https://mlsanity.com/paper/2108.12508/) (2021)
- [Are Two Heads the Same as One? Identifying Disparate Treatment in Fair Neural Networks](https://mlsanity.com/paper/2204.04440/) (2022)
- [Federated Learning Meets Fairness and Differential Privacy](https://mlsanity.com/paper/2108.09932/) (2021)
- [Representative & Fair Synthetic Data](https://mlsanity.com/paper/2104.03007/) (2021)
- [Gradual (In)Compatibility of Fairness Criteria](https://mlsanity.com/paper/2109.04399/) (2021)
- [Comparing Human and Machine Bias in Face Recognition](https://mlsanity.com/paper/2110.08396/) (2021)
- [Learning to Teach Fairness-aware Deep Multi-task Learning](https://mlsanity.com/paper/2206.08403/) (2022)
- [Diffusion Theory as a Scalpel: Detecting and Purifying Poisonous Dimensions in Pre-trained Language Models Caused by Backdoor or Bias](https://mlsanity.com/paper/2305.04547/) (2023)
- [fairret: a Framework for Differentiable Fairness Regularization Terms](https://mlsanity.com/paper/2310.17256/) (2023)
- [FairSample: Training Fair and Accurate Graph Convolutional Neural Networks Efficiently](https://mlsanity.com/paper/2401.14702/) (2024)
- [Generalized Disparate Impact for Configurable Fairness Solutions in ML](https://mlsanity.com/paper/2305.18504/) (2023)
- [Machine Learning Fairness for Depression Detection using EEG Data](https://mlsanity.com/paper/2501.18192/) (2025)
- [Neurosymbolic AI and its Taxonomy: a survey](https://mlsanity.com/paper/2305.08876/) (2023)
- [Robustness Disparities in Face Detection](https://mlsanity.com/paper/2211.15937/) (2022)
- [When Fairness Meets Privacy: Exploring Privacy Threats in Fair Binary Classifiers via Membership Inference Attacks](https://mlsanity.com/paper/2311.03865/) (2023)
- [Fairness via In-Processing in the Over-parameterized Regime: A Cautionary Tale](https://mlsanity.com/paper/2206.14853/) (2022)
- [Toward the Tradeoffs between Privacy, Fairness and Utility in Federated Learning](https://mlsanity.com/paper/2311.18190/) (2023)
- [Are Commercial Face Detection Models as Biased as Academic Models?](https://mlsanity.com/paper/2201.10047/) (2022)
- [Looking Beyond What You See: An Empirical Analysis on Subgroup Intersectional Fairness for Multi-label Chest X-ray Classification Using Social Determinants of Racial Health Inequities](https://mlsanity.com/paper/2403.18196/) (2024)
- [FineFACE: Fair Facial Attribute Classification Leveraging Fine-grained Features](https://mlsanity.com/paper/2408.16881/) (2024)
- [How optimal transport can tackle gender biases in multi-class neural-network classifiers for job recommendations?](https://mlsanity.com/paper/2302.14063/) (2023)
- [Investigating the Effects of Fairness Interventions Using Pointwise Representational Similarity](https://mlsanity.com/paper/2305.19294/) (2023)

## Abstract (arXiv)

In classification models fairness can be ensured by solving a constrained optimization problem. We focus on fairness constraints like Disparate Impact, Demographic Parity, and Equalized Odds, which are non-decomposable and non-convex. Researchers define convex surrogates of the constraints and then apply convex optimization frameworks to obtain fair classifiers. Surrogates serve only as an upper bound to the actual constraints, and convexifying fairness constraints might be challenging. We propose a neural network-based framework, FNNC, to achieve fairness while maintaining high accuracy in classification. The above fairness constraints are included in the loss using Lagrangian multipliers. We prove bounds on generalization errors for the constrained losses which asymptotically go to zero. The network is optimized using two-step mini-batch stochastic gradient descent. Our experiments show that FNNC performs as good as the state of the art, if not better. The experimental evidence supplements our theoretical guarantees. In summary, we have an automated solution to achieve fairness in classification, which is easily extendable to many fairness constraints.