# Fast Convergence through Distributed Augmentation for Class-Imbalanced Federated Learning

arXiv: https://arxiv.org/abs/2610.05279 · HTML: https://mlsanity.com/paper/2610.05279/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 24 references that are in the map.
- First posted on arXiv 4 Oct 2026.

## Builds on (most cited first, 13 of 13)

- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Adaptive Federated Optimization](https://mlsanity.com/paper/2003.00295/) (2020)
- [Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization](https://mlsanity.com/paper/2007.07481/) (2020)
- [Agnostic Federated Learning](https://mlsanity.com/paper/1902.00146/) (2019)
- [Synthetic Data from Diffusion Models Improves ImageNet Classification](https://mlsanity.com/paper/2304.08466/) (2023)
- [FedFA: Federated Learning with Feature Anchors to Align Features and Classifiers for Heterogeneous Data](https://mlsanity.com/paper/2211.09299/) (2022)
- [A Survey on Class Imbalance in Federated Learning](https://mlsanity.com/paper/2303.11673/) (2023)
- [Stabilized Proximal-Point Methods for Federated Optimization](https://mlsanity.com/paper/2407.07084/) (2024)
- [A Closer Look at Data Augmentation Strategies for Finetuning-Based Low/Few-Shot Object Detection](https://mlsanity.com/paper/2408.10940/) (2024)
- [Balancing Label Imbalance in Federated Environments Using Only Mixup and Artificially-Labeled Noise](https://mlsanity.com/paper/2409.13235/) (2024)
- [On Homomorphic Encryption Based Strategies for Class Imbalance in Federated Learning](https://mlsanity.com/paper/2410.21192/) (2024)

## Abstract (arXiv)

In federated learning, mitigating class imbalance is essential to improve minority-class performance. A common approach to address this problem is to augment minority-class samples to achieve local class balance. Existing approaches treat augmentation as a heuristic and do not establish how the amount of augmentation influences the convergence of federated learning, leading to excessive augmentation and increased training time. To address this limitation, we first establish the relationship between augmentation and the convergence behavior of federated learning. Leveraging this insight, we propose DAFL, a distributed augmentation framework that determines the minimum augmentation required for each client-class pair by jointly minimizing augmentation and training time while constraining global class imbalance, thereby improving minority-class F1-score. Experimental results demonstrate that DAFL consistently improves minority-class F1-score while substantially reducing training time, particularly under severe global class imbalance and high label proportion imbalance.