Bias Propagation in Federated Learning

Hong Chang, R. Shokri
2/12/2026

No official code found. Best implementation: privacytrustlab/bias_in_FL (10 stars, last commit 2023-03-28).

Abstract

We show that participating in federated learning can be detrimental to group fairness. In fact, the bias of a few parties against under-represented groups (identified by sensitive attributes such as gender or race) can propagate through the network to all the parties in the network. We analyze and explain bias propagation in federated learning on naturally partitioned real-world datasets. Our analysis reveals that biased parties unintentionally yet stealthily encode their bias in a small number of model parameters, and throughout the training, they steadily increase the dependence of the global model on sensitive attributes. What is important to highlight is that the experienced bias in federated learning is higher than what parties would otherwise encounter in centralized training with a model trained on the union of all their data. This indicates that the bias is due to the algorithm. Our work calls for auditing group fairness in federated learning and designing learning algorithms that are robust to bias propagation.

View on arXivView PDF

Code Implementations(1)

privacytrustlab/bias_in_FLCommunity100%

This is the code repository for the paper titled "Bias Propagation in Federated Learning" which was accepted to the International Conference on Learning Representations (ICLR) 2023.

102Shell, PythonFeb 22, 20233 years ago

Similar Papers

A Survey on Group Fairness in Federated Learning: Challenges, Taxonomy of Solutions and Directions for Future Research

87% match1 repo22024

EAB-FL: Exacerbating Algorithmic Bias through Model Poisoning Attacks in Federated Learning

86% match1 repo2024

Demystifying Local and Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition

86% match1 repo52023

Fairness in Federated Learning: Trends, Challenges, and Opportunities

85% match2025

Global Group Fairness in Federated Learning via Function Tracking

85% match1 repo12025

GLOCALFAIR: Jointly Improving Global and Local Group Fairness in Federated Learning

84% match2024

Cite this paper

@article{chang2026bias,
  title  = {Bias Propagation in Federated Learning},
  author = {Hong Chang and R. Shokri},
  year   = {2026},
  eprint = {2309.02160},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/pdf/2309.02160},
  journal = {ICLR 2023 2023}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2309.02160.svg)](https://codeofpaper.com/paper/2309.02160)

Discussion