# Mitigating Bias in Federated Learning

arXiv: https://arxiv.org/abs/2012.02447 · HTML: https://mlsanity.com/paper/2012.02447/

## Key facts

- Cited by 56 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Dec 2020.

## Built on by (most cited first, 30 of 56)

- [Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey](https://mlsanity.com/paper/2207.07068/) (2022)
- [FairFed: Enabling Group Fairness in Federated Learning](https://mlsanity.com/paper/2110.00857/) (2021)
- [Federated Learning with Fair Averaging](https://mlsanity.com/paper/2104.14937/) (2021)
- [Differential Privacy and Fairness in Decisions and Learning Tasks: A Survey](https://mlsanity.com/paper/2202.08187/) (2022)
- [Enforcing fairness in private federated learning via the modified method of differential multipliers](https://mlsanity.com/paper/2109.08604/) (2021)
- [FedJAX: Federated learning simulation with JAX](https://mlsanity.com/paper/2108.02117/) (2021)
- [A Multi-agent Reinforcement Learning Approach for Efficient Client Selection in Federated Learning](https://mlsanity.com/paper/2201.02932/) (2022)
- [Privacy and Fairness in Federated Learning: on the Perspective of Trade-off](https://mlsanity.com/paper/2306.14123/) (2023)
- [LEO-Split: A Semi-Supervised Split Learning Framework over LEO Satellite Networks](https://mlsanity.com/paper/2501.01293/) (2025)
- [Algorithm Fairness in AI for Medicine and Healthcare](https://mlsanity.com/paper/2110.00603/) (2021)
- [Local Stochastic Bilevel Optimization with Momentum-Based Variance Reduction](https://mlsanity.com/paper/2205.01608/) (2022)
- [Improving Fairness in AI Models on Electronic Health Records: The Case for Federated Learning Methods](https://mlsanity.com/paper/2305.11386/) (2023)
- [Do We Really Need to Design New Byzantine-robust Aggregation Rules?](https://mlsanity.com/paper/2501.17381/) (2025)
- [FLoRA: Single-shot Hyper-parameter Optimization for Federated Learning](https://mlsanity.com/paper/2112.08524/) (2021)
- [PrivFairFL: Privacy-Preserving Group Fairness in Federated Learning](https://mlsanity.com/paper/2205.11584/) (2022)
- [Bias Propagation in Federated Learning](https://mlsanity.com/paper/2309.02160/) (2023)
- [Recent Methodological Advances in Federated Learning for Healthcare](https://mlsanity.com/paper/2310.02874/) (2023)
- [Communication-Efficient Agnostic Federated Averaging](https://mlsanity.com/paper/2104.02748/) (2021)
- [FAIR-FATE: Fair Federated Learning with Momentum](https://mlsanity.com/paper/2209.13678/) (2022)
- [Mitigating Group Bias in Federated Learning: Beyond Local Fairness](https://mlsanity.com/paper/2305.09931/) (2023)
- [Demystifying Local and Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition](https://mlsanity.com/paper/2307.11333/) (2023)
- [Not All Federated Learning Algorithms Are Created Equal: A Performance Evaluation Study](https://mlsanity.com/paper/2403.17287/) (2024)
- [Models of fairness in federated learning](https://mlsanity.com/paper/2112.00818/) (2021)
- [Navigating Heterogeneity and Privacy in One-Shot Federated Learning with Diffusion Models](https://mlsanity.com/paper/2405.01494/) (2024)
- [Incentivizing Honesty among Competitors in Collaborative Learning and Optimization](https://mlsanity.com/paper/2305.16272/) (2023)
- [Scaff-PD: Communication Efficient Fair and Robust Federated Learning](https://mlsanity.com/paper/2307.13381/) (2023)
- [Mitigating Group Bias in Federated Learning for Heterogeneous Devices](https://mlsanity.com/paper/2309.07085/) (2023)
- [GLOCALFAIR: Jointly Improving Global and Local Group Fairness in Federated Learning](https://mlsanity.com/paper/2401.03562/) (2024)
- [PraFFL: A Preference-Aware Scheme in Fair Federated Learning](https://mlsanity.com/paper/2404.08973/) (2024)
- [Achieving Fairness Across Local and Global Models in Federated Learning](https://mlsanity.com/paper/2406.17102/) (2024)

## Abstract (arXiv)

As methods to create discrimination-aware models develop, they focus on centralized ML, leaving federated learning (FL) unexplored. FL is a rising approach for collaborative ML, in which an aggregator orchestrates multiple parties to train a global model without sharing their training data. In this paper, we discuss causes of bias in FL and propose three pre-processing and in-processing methods to mitigate bias, without compromising data privacy, a key FL requirement. As data heterogeneity among parties is one of the challenging characteristics of FL, we conduct experiments over several data distributions to analyze their effects on model performance, fairness metrics, and bias learning patterns. We conduct a comprehensive analysis of our proposed techniques, the results demonstrating that these methods are effective even when parties have skewed data distributions or as little as 20% of parties employ the methods.