FedReLa: Imbalanced Federated Learning via Re-Labeling
Guangzheng Hu, Patricia Menéndez, Feng Liu, Mingming Gong, Guanghui Wang, Liuhua Peng
stat.ML, cs.CV, cs.LG
Submitted: 2026-06-24
Code: https://github.com/guangzhengh/FedReLa
License: http://creativecommons.org/licenses/by-nc-sa/4.0/
The gist: Federated learning has emerged as the foremost approach for decentralized model training with privacy preservation.
Terminology
Abstract
Federated learning has emerged as the foremost approach for decentralized model training with privacy preservation. The global class imbalance and cross-client data heterogeneity naturally coexist, and the mismatch between local and global imbalances exacerbates the performance degradation of the aggregated model. The agnosticism of global class distribution poses significant challenges for data-level methods, especially under extreme conditions with severe class absence across clients. In this paper, we propose FedReLa, a novel data-level approach that tackles the coexistence of data heterogeneity and class imbalance in federated learning. By re-labeling samples with a feature-dependent label re-allocator, FedReLa corrects biased global decision boundaries without requiring knowledge of the global class distribution. This modular, model-agnostic approach can be integrated with algorithmic methods to deliver consistent improvements without additional communication overhead. Through extensive experiments, our method significantly improves the accuracy of minority classes and the overall accuracy on stepwise-imbalanced and long-tailed datasets, outperforming the previous state of the art.
Sources
- Federated Learning Based on Dynamic Regularization
- On Bridging Generic and Personalized Federated Learning for Image Classification
- SCAFFOLD: Stochastic Controlled Averaging for Federated Learning
- Optimal Client Sampling for Federated Learning
- FedMix: Mixed Supervised Federated Learning for Medical Image Segmentation
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Long-tail learning via logit adjustment
- Conditional Image Synthesis With Auxiliary Classifier GANs
- FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Data
- Federated Learning on Heterogeneous and Long-Tailed Data via Classifier Re-Training with Federated Features
- You Are Your Own Best Teacher: Achieving Centralized-level Performance in Federated Learning under Heterogeneous and Long-tailed Data
- mixup: Beyond Empirical Risk Minimization
- Federated Learning with Non-IID Data
Related papers
- Behavior of prediction performance metrics with rare events
- Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
- A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
- Scalable Posterior Uncertainty for Flexible Density-Based Clustering
- A Transport Geometry of Benign Overfitting
- Efficient quadratic entropy with distance sketches