# Global Group Fairness in Federated Learning via Function Tracking

arXiv: https://arxiv.org/abs/2503.15163 · HTML: https://mlsanity.com/paper/2503.15163/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 23 references that are in the map.
- First posted on arXiv 19 Mar 2025.

## Builds on (most cited first, 15 of 15)

- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Agnostic Federated Learning](https://mlsanity.com/paper/1902.00146/) (2019)
- [Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learning](https://mlsanity.com/paper/1807.06629/) (2018)
- [Tighter Theory for Local SGD on Identical and Heterogeneous Data](https://mlsanity.com/paper/1909.04746/) (2019)
- [FairBatch: Batch Selection for Model Fairness](https://mlsanity.com/paper/2012.01696/) (2020)
- [MATCHA: Speeding Up Decentralized SGD via Matching Decomposition Sampling](https://mlsanity.com/paper/1905.09435/) (2019)
- [A Distributionally Robust Approach to Fair Classification](https://mlsanity.com/paper/2007.09530/) (2020)
- [GIFAIR-FL: A Framework for Group and Individual Fairness in Federated Learning](https://mlsanity.com/paper/2108.02741/) (2021)
- [Optimality of the Laplace Mechanism in Differential Privacy](https://mlsanity.com/paper/1504.00065/) (2015)
- [PrivFairFL: Privacy-Preserving Group Fairness in Federated Learning](https://mlsanity.com/paper/2205.11584/) (2022)
- [Fair Federated Learning via Bounded Group Loss](https://mlsanity.com/paper/2203.10190/) (2022)
- [FAIR-FATE: Fair Federated Learning with Momentum](https://mlsanity.com/paper/2209.13678/) (2022)
- [Metrizing Fairness](https://mlsanity.com/paper/2205.15049/) (2022)
- [Multi-level Monte-Carlo Gradient Methods for Stochastic Optimization with Biased Oracles](https://mlsanity.com/paper/2408.11084/) (2024)

## Built on by (most cited first, 1 of 1)

- [FeDa4Fair: Client-Level Federated Datasets for Fairness Evaluation](https://mlsanity.com/paper/2506.21095/) (2025)

## Abstract (arXiv)

We investigate group fairness regularizers in federated learning, aiming to train a globally fair model in a distributed setting. Ensuring global fairness in distributed training presents unique challenges, as fairness regularizers typically involve probability metrics between distributions across all clients and are not naturally separable by client. To address this, we introduce a function-tracking scheme for the global fairness regularizer based on a Maximum Mean Discrepancy (MMD), which incurs a small communication overhead. This scheme seamlessly integrates into most federated learning algorithms while preserving rigorous convergence guarantees, as demonstrated in the context of FedAvg. Additionally, when enforcing differential privacy, the kernel-based MMD regularization enables straightforward analysis through a change of kernel, leveraging an intuitive interpretation of kernel convolution. Numerical experiments confirm our theoretical insights.