# Taking Advantage of Multitask Learning for Fair Classification

arXiv: https://arxiv.org/abs/1810.08683 · HTML: https://mlsanity.com/paper/1810.08683/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Oct 2018.

## Built on by (most cited first, 24 of 24)

- [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)
- [Understanding and Improving Fairness-Accuracy Trade-offs in Multi-Task Learning](https://mlsanity.com/paper/2106.02705/) (2021)
- [A Survey on Fairness for Machine Learning on Graphs](https://mlsanity.com/paper/2205.05396/) (2022)
- [FairMask: Better Fairness via Model-based Rebalancing of Protected Attributes](https://mlsanity.com/paper/2110.01109/) (2021)
- [Fairness in Multi-Task Learning via Wasserstein Barycenters](https://mlsanity.com/paper/2306.10155/) (2023)
- [OxonFair: A Flexible Toolkit for Algorithmic Fairness](https://mlsanity.com/paper/2407.13710/) (2024)
- [Are Two Heads the Same as One? Identifying Disparate Treatment in Fair Neural Networks](https://mlsanity.com/paper/2204.04440/) (2022)
- [Bias Reducing Multitask Learning on Mental Health Prediction](https://mlsanity.com/paper/2208.03621/) (2022)
- [Learning to Teach Fairness-aware Deep Multi-task Learning](https://mlsanity.com/paper/2206.08403/) (2022)
- [Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Tools](https://mlsanity.com/paper/2309.17337/) (2023)
- [Group-blind optimal transport to group parity and its constrained variants](https://mlsanity.com/paper/2310.11407/) (2023)
- [Bipol: A Novel Multi-Axes Bias Evaluation Metric with Explainability for NLP](https://mlsanity.com/paper/2304.04029/) (2023)
- [Bipol: Multi-axes Evaluation of Bias with Explainability in Benchmark Datasets](https://mlsanity.com/paper/2301.12139/) (2023)
- [Enhancing Fairness and Performance in Machine Learning Models: A Multi-Task Learning Approach with Monte-Carlo Dropout and Pareto Optimality](https://mlsanity.com/paper/2404.08230/) (2024)
- [Algorithmic Fairness: A Tolerance Perspective](https://mlsanity.com/paper/2405.09543/) (2024)
- [Fair Robust Active Learning by Joint Inconsistency](https://mlsanity.com/paper/2209.10729/) (2022)
- [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)
- [Responsible AI (RAI) Games and Ensembles](https://mlsanity.com/paper/2310.18832/) (2023)
- [Robust-Multi-Task Gradient Boosting](https://mlsanity.com/paper/2507.11411/) (2025)
- [Developing Fairness-Aware Task Decomposition to Improve Equity in Post-Spinal Fusion Complication Prediction](https://mlsanity.com/paper/2512.00598/) (2025)
- [Robust multi-task boosting using clustering and local ensembling](https://mlsanity.com/paper/2602.14231/) (2026)
- [Controllable Pareto Trade-off between Fairness and Accuracy](https://mlsanity.com/paper/2509.13651/) (2025)

## Abstract (arXiv)

A central goal of algorithmic fairness is to reduce bias in automated decision making. An unavoidable tension exists between accuracy gains obtained by using sensitive information (e.g., gender or ethnic group) as part of a statistical model, and any commitment to protect these characteristics. Often, due to biases present in the data, using the sensitive information in the functional form of a classifier improves classification accuracy. In this paper we show how it is possible to get the best of both worlds: optimize model accuracy and fairness without explicitly using the sensitive feature in the functional form of the model, thereby treating different individuals equally. Our method is based on two key ideas. On the one hand, we propose to use Multitask Learning (MTL), enhanced with fairness constraints, to jointly learn group specific classifiers that leverage information between sensitive groups. On the other hand, since learning group specific models might not be permitted, we propose to first predict the sensitive features by any learning method and then to use the predicted sensitive feature to train MTL with fairness constraints. This enables us to tackle fairness with a three-pronged approach, that is, by increasing accuracy on each group, enforcing measures of fairness during training, and protecting sensitive information during testing. Experimental results on two real datasets support our proposal, showing substantial improvements in both accuracy and fairness.