# FairMean: Promoting Fairness in Distributed Learning under Label Poisoning Attacks

arXiv: https://arxiv.org/abs/2609.26377 · HTML: https://mlsanity.com/paper/2609.26377/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 22 references that are in the map.
- First posted on arXiv 22 Sep 2026.

## Builds on (most cited first, 11 of 11)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates](https://mlsanity.com/paper/1803.01498/) (2018)
- [Fair Resource Allocation in Federated Learning](https://mlsanity.com/paper/1905.10497/) (2019)
- [Robust Aggregation for Federated Learning](https://mlsanity.com/paper/1912.13445/) (2019)
- [Towards Fairness-Aware Federated Learning](https://mlsanity.com/paper/2111.01872/) (2021)
- [On Tilted Losses in Machine Learning: Theory and Applications](https://mlsanity.com/paper/2109.06141/) (2021)
- [Advances and Open Challenges in Federated Foundation Models](https://mlsanity.com/paper/2404.15381/) (2024)
- [AdaFed: Fair Federated Learning via Adaptive Common Descent Direction](https://mlsanity.com/paper/2401.04993/) (2024)
- [Mean Aggregator is More Robust than Robust Aggregators under Label Poisoning Attacks on Distributed Heterogeneous Data](https://mlsanity.com/paper/2404.13647/) (2024)
- [Bant: Byzantine Antidote via Trial Function and Trust Scores](https://mlsanity.com/paper/2505.07614/) (2025)
- [Fairness in Federated Learning: Trends, Challenges, and Opportunities](https://mlsanity.com/paper/2509.00799/) (2025)

## Abstract (arXiv)

Fairness-aware distributed learning prioritizes clients with large losses to reduce performance disparities, but label poisoning can create large losses, thereby inducing a fairness--robustness conflict. We propose FairMean to manage this conflict. FairMean weights client gradients using a bounded, nondecreasing function of local loss. The increasing weights prioritize high-loss clients to promote fairness, while the upper bound prevents excessive loss-induced amplification of poisoned-client gradients. In the absence of label poisoning, we show that minimizing the FairMean objective is more conducive to solution fairness than minimizing the standard average-loss objective. Under label poisoning, we establish an average-stationarity bound whose attack-dependent term is proportional to the square of the poisoned-client fraction. Experiments show that FairMean promotes fairness by reducing accuracy variance while improving worst-client accuracy.