# Improved Adversarial Learning for Fair Classification

arXiv: https://arxiv.org/abs/1901.10443 · HTML: https://mlsanity.com/paper/1901.10443/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jan 2019.

## Built on by (most cited first, 25 of 25)

- [Trustworthy AI: From Principles to Practices](https://mlsanity.com/paper/2110.01167/) (2021)
- [Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey](https://mlsanity.com/paper/2207.07068/) (2022)
- [Trustworthy AI: A Computational Perspective](https://mlsanity.com/paper/2107.06641/) (2021)
- [Fairness in Graph Mining: A Survey](https://mlsanity.com/paper/2204.09888/) (2022)
- [Representation Bias in Data: A Survey on Identification and Resolution Techniques](https://mlsanity.com/paper/2203.11852/) (2022)
- [Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives](https://mlsanity.com/paper/2307.16851/) (2023)
- [Bayes-Optimal Classifiers under Group Fairness](https://mlsanity.com/paper/2202.09724/) (2022)
- [Algorithm Fairness in AI for Medicine and Healthcare](https://mlsanity.com/paper/2110.00603/) (2021)
- [Fair Bayes-Optimal Classifiers Under Predictive Parity](https://mlsanity.com/paper/2205.07182/) (2022)
- [Inferring Sensitive Attributes from Model Explanations](https://mlsanity.com/paper/2208.09967/) (2022)
- [Fair Enough: Searching for Sufficient Measures of Fairness](https://mlsanity.com/paper/2110.13029/) (2021)
- [Fairness with Continuous Optimal Transport](https://mlsanity.com/paper/2101.02084/) (2021)
- [Unmasking Bias in AI: A Systematic Review of Bias Detection and Mitigation Strategies in Electronic Health Record-based Models](https://mlsanity.com/paper/2310.19917/) (2023)
- [Fairness for Robust Learning to Rank](https://mlsanity.com/paper/2112.06288/) (2021)
- [Counterfactually Fair Reinforcement Learning via Sequential Data Preprocessing](https://mlsanity.com/paper/2501.06366/) (2025)
- [Fairness-aware Summarization for Justified Decision-Making](https://mlsanity.com/paper/2107.06243/) (2021)
- [Fair Foundation Models for Medical Image Analysis: Challenges and Perspectives](https://mlsanity.com/paper/2502.16841/) (2025)
- [Machine Learning with Multitype Protected Attributes: Intersectional Fairness through Regularisation](https://mlsanity.com/paper/2509.08163/) (2025)
- [Prediction Sensitivity: Continual Audit of Counterfactual Fairness in Deployed Classifiers](https://mlsanity.com/paper/2202.04504/) (2022)
- [Mitigating Bias in Facial Analysis Systems by Incorporating Label Diversity](https://mlsanity.com/paper/2204.06364/) (2022)
- [FairRR: Pre-Processing for Group Fairness through Randomized Response](https://mlsanity.com/paper/2403.07780/) (2024)
- [Stochastic Projective Splitting: Solving Saddle-Point Problems with Multiple Regularizers](https://mlsanity.com/paper/2106.13067/) (2021)
- [A Tale of Fairness Revisited: Beyond Adversarial Learning for Deep Neural Network Fairness](https://mlsanity.com/paper/2101.02831/) (2021)
- [General Post-Processing Framework for Fairness Adjustment of Machine Learning Models](https://mlsanity.com/paper/2504.16238/) (2025)
- [MIFair: A Mutual-Information Framework for Intersectionality and Multiclass Fairness](https://mlsanity.com/paper/2604.28030/) (2026)

## Abstract (arXiv)

Motivated by concerns that machine learning algorithms may introduce significant bias in classification models, developing fair classifiers has become an important problem in machine learning research. One important paradigm towards this has been providing algorithms for adversarially learning fair classifiers (Zhang et al., 2018; Madras et al., 2018). We formulate the adversarial learning problem as a multi-objective optimization problem and find the fair model using gradient descent-ascent algorithm with a modified gradient update step, inspired by the approach of Zhang et al., 2018. We provide theoretical insight and guarantees that formalize the heuristic arguments presented previously towards taking such an approach. We test our approach empirically on the Adult dataset and synthetic datasets and compare against state of the art algorithms (Celis et al., 2018; Zhang et al., 2018; Zafar et al., 2017). The results show that our models and algorithms have comparable or better accuracy than other algorithms while performing better in terms of fairness, as measured using statistical rate or false discovery rate.