# Learning to Teach Fairness-aware Deep Multi-task Learning

arXiv: https://arxiv.org/abs/2206.08403 · HTML: https://mlsanity.com/paper/2206.08403/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 25 references that are in the map.
- First posted on arXiv 16 Jun 2022.

## Builds on (most cited first, 17 of 17)

- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks](https://mlsanity.com/paper/1711.02257/) (2017)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [Retiring Adult: New Datasets for Fair Machine Learning](https://mlsanity.com/paper/2108.04884/) (2021)
- [Empirical Risk Minimization under Fairness Constraints](https://mlsanity.com/paper/1802.08626/) (2018)
- [Multi-task Deep Reinforcement Learning with PopArt](https://mlsanity.com/paper/1809.04474/) (2018)
- [FNNC: Achieving Fairness through Neural Networks](https://mlsanity.com/paper/1811.00247/) (2018)
- [Learning to Teach with Dynamic Loss Functions](https://mlsanity.com/paper/1810.12081/) (2018)
- [Understanding and Improving Fairness-Accuracy Trade-offs in Multi-Task Learning](https://mlsanity.com/paper/2106.02705/) (2021)
- [Taking Advantage of Multitask Learning for Fair Classification](https://mlsanity.com/paper/1810.08683/) (2018)
- [General Fair Empirical Risk Minimization](https://mlsanity.com/paper/1901.10080/) (2019)
- [Rank-Based Multi-task Learning for Fair Regression](https://mlsanity.com/paper/2009.11405/) (2020)
- [Deep Multi-Task Augmented Feature Learning via Hierarchical Graph Neural Network](https://mlsanity.com/paper/2002.04813/) (2020)
- [VOGUE: Answer Verbalization through Multi-Task Learning](https://mlsanity.com/paper/2106.13316/) (2021)

## Built on by (most cited first, 8 of 8)

- [Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey](https://mlsanity.com/paper/2207.07068/) (2022)
- [Fairness in Multi-Task Learning via Wasserstein Barycenters](https://mlsanity.com/paper/2306.10155/) (2023)
- [Synthetic Tabular Data Generation for Class Imbalance and Fairness: A Comparative Study](https://mlsanity.com/paper/2409.05215/) (2024)
- [On Fairness of Task Arithmetic: The Role of Task Vectors](https://mlsanity.com/paper/2505.24262/) (2025)
- [FairBranch: Mitigating Bias Transfer in Fair Multi-task Learning](https://mlsanity.com/paper/2310.13746/) (2023)
- [TransFair: Transferring Fairness from Ocular Disease Classification to Progression Prediction](https://mlsanity.com/paper/2412.00051/) (2024)
- [Group Fairness in Multi-Task Reinforcement Learning](https://mlsanity.com/paper/2503.07817/) (2025)
- [Controllable Pareto Trade-off between Fairness and Accuracy](https://mlsanity.com/paper/2509.13651/) (2025)

## Abstract (arXiv)

Fairness-aware learning mainly focuses on single task learning (STL). The fairness implications of multi-task learning (MTL) have only recently been considered and a seminal approach has been proposed that considers the fairness-accuracy trade-off for each task and the performance trade-off among different tasks. Instead of a rigid fairness-accuracy trade-off formulation, we propose a flexible approach that learns how to be fair in a MTL setting by selecting which objective (accuracy or fairness) to optimize at each step. We introduce the L2T-FMT algorithm that is a teacher-student network trained collaboratively; the student learns to solve the fair MTL problem while the teacher instructs the student to learn from either accuracy or fairness, depending on what is harder to learn for each task. Moreover, this dynamic selection of which objective to use at each step for each task reduces the number of trade-off weights from 2T to T, where T is the number of tasks. Our experiments on three real datasets show that L2T-FMT improves on both fairness (12-19%) and accuracy (up to 2%) over state-of-the-art approaches.