# FairBranch: Mitigating Bias Transfer in Fair Multi-task Learning

arXiv: https://arxiv.org/abs/2310.13746 · HTML: https://mlsanity.com/paper/2310.13746/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 33 references that are in the map.
- First posted on arXiv 20 Oct 2023.

## Builds on (most cited first, 24 of 24)

- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [A Survey on Multi-Task Learning](https://mlsanity.com/paper/1707.08114/) (2017)
- [GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks](https://mlsanity.com/paper/1711.02257/) (2017)
- [An Overview of Multi-Task Learning in Deep Neural Networks](https://mlsanity.com/paper/1706.05098/) (2017)
- [Retiring Adult: New Datasets for Fair Machine Learning](https://mlsanity.com/paper/2108.04884/) (2021)
- [Which Tasks Should Be Learned Together in Multi-task Learning?](https://mlsanity.com/paper/1905.07553/) (2019)
- [Efficiently Identifying Task Groupings for Multi-Task Learning](https://mlsanity.com/paper/2109.04617/) (2021)
- [Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models](https://mlsanity.com/paper/2010.05874/) (2020)
- [Learning to Branch for Multi-Task Learning](https://mlsanity.com/paper/2006.01895/) (2020)
- [Adapting Auxiliary Losses Using Gradient Similarity](https://mlsanity.com/paper/1812.02224/) (2018)
- [Fully-adaptive Feature Sharing in Multi-Task Networks with Applications in Person Attribute Classification](https://mlsanity.com/paper/1611.05377/) (2016)
- [Similarity and Matching of Neural Network Representations](https://mlsanity.com/paper/2110.14633/) (2021)
- [In Defense of the Unitary Scalarization for Deep Multi-Task Learning](https://mlsanity.com/paper/2201.04122/) (2022)
- [Automated Search for Resource-Efficient Branched Multi-Task Networks](https://mlsanity.com/paper/2008.10292/) (2020)
- [Recon: Reducing Conflicting Gradients from the Root for Multi-Task Learning](https://mlsanity.com/paper/2302.11289/) (2023)
- [Understanding and Improving Fairness-Accuracy Trade-offs in Multi-Task Learning](https://mlsanity.com/paper/2106.02705/) (2021)
- [Similarity of Neural Networks with Gradients](https://mlsanity.com/paper/2003.11498/) (2020)
- [Multi-dimensional discrimination in Law and Machine Learning -- A comparative overview](https://mlsanity.com/paper/2302.05995/) (2023)
- [Fairness in Multi-Task Learning via Wasserstein Barycenters](https://mlsanity.com/paper/2306.10155/) (2023)
- [Learning to Teach Fairness-aware Deep Multi-task Learning](https://mlsanity.com/paper/2206.08403/) (2022)

## Built on by (most cited first, 2 of 2)

- [On Fairness of Task Arithmetic: The Role of Task Vectors](https://mlsanity.com/paper/2505.24262/) (2025)
- [A Deep Latent Factor Graph Clustering with Fairness-Utility Trade-off Perspective](https://mlsanity.com/paper/2510.23507/) (2025)

## Abstract (arXiv)

The generalisation capacity of Multi-Task Learning (MTL) suffers when unrelated tasks negatively impact each other by updating shared parameters with conflicting gradients. This is known as negative transfer and leads to a drop in MTL accuracy compared to single-task learning (STL). Lately, there has been a growing focus on the fairness of MTL models, requiring the optimization of both accuracy and fairness for individual tasks. Analogously to negative transfer for accuracy, task-specific fairness considerations might adversely affect the fairness of other tasks when there is a conflict of fairness loss gradients between the jointly learned tasks - we refer to this as Bias Transfer. To address both negative- and bias-transfer in MTL, we propose a novel method called FairBranch, which branches the MTL model by assessing the similarity of learned parameters, thereby grouping related tasks to alleviate negative transfer. Moreover, it incorporates fairness loss gradient conflict correction between adjoining task-group branches to address bias transfer within these task groups. Our experiments on tabular and visual MTL problems show that FairBranch outperforms state-of-the-art MTLs on both fairness and accuracy.