← Search

Guangzheng Hu

2 accepted papers

2026

FedReLa: Imbalanced Federated Learning via Re-Labeling

ICML 2026poster

Federated learning has emerged as the foremost approach for decentralized model training with privacy preserving. 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 aggr…

Cited by 0SourceScholar
2025

Learning Imbalanced Data with Beneficial Label Noise

ICML 2025poster

Data imbalance is a common factor hindering classifier performance. Data-level approaches for imbalanced learning, such as resampling, often lead to information loss or generative errors. Building on theoretical studies of imbalance ratio in binary classification, it is found that adding suitable la…

Cited by 0SourcePDFScholar