PulseAugur
EN
LIVE 07:44:42

FedReLa tackles class imbalance in federated learning via re-labeling

By PulseAugur Editorial · [2 sources] ·

Researchers have introduced FedReLa, a new data-level approach designed to address class imbalance and data heterogeneity in federated learning. This method employs a feature-dependent label re-allocator to correct biased global decision boundaries without needing to know the overall class distribution. FedReLa is a modular and model-agnostic technique that can be integrated with existing algorithmic methods to enhance performance, particularly for minority classes and imbalanced datasets, outperforming current state-of-the-art methods. AI

IMPACT Improves minority class accuracy and overall performance in federated learning systems facing data heterogeneity and imbalance.

RANK_REASON The cluster contains an academic paper detailing a new method for federated learning.

Read on arXiv stat.ML →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

FedReLa tackles class imbalance in federated learning via re-labeling

COVERAGE [2]

  1. arXiv stat.ML TIER_1 English(EN) · Guangzheng Hu, Patricia Men\'endez, Feng Liu, Mingming Gong, Guanghui Wang, Liuhua Peng ·

    FedReLa: Imbalanced Federated Learning via Re-Labeling

    arXiv:2606.26037v1 Announce Type: new 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…

  2. arXiv stat.ML TIER_1 English(EN) · Liuhua Peng ·

    FedReLa: Imbalanced Federated Learning via Re-Labeling

    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 d…

RELATED ENTITIES

RELATED TOPICS