Loss-Aware Weight based Adaptive Aggregation for Federated Learning under Class Imbalance
作者
Yesol Jeon,Sangwook Park
出处
期刊:2019 34th International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC)日期:2025-07-07卷期号:: 1-4
标识
DOI:10.1109/itc-cscc66376.2025.11137742
摘要
Federated Learning (FL) is a data-decentralized learning paradigm that preserves data privacy by enabling model training without sharing raw data. However, FL suffers from performance degradation caused by class imbalance, a common form of statistical heterogeneity in non-independent and identically distributed environments. This paper proposes a modified FedAvg aggregation strategy that adjusts client weights using the ratio between the minimum and maximum class-wise average losses observed during training, reflecting the reliability of each local model. Unlike previous methods, it does not require prior knowledge of class distributions and dynamically adjusts aggregation weights based on client-wise reliability. Experiments on the CIFAR-10 dataset partitioned with a Dirichlet distribution demonstrate that the proposed method improves global model accuracy by 4–5% under severe class imbalance while maintaining comparable performance under more balanced conditions. Additionally, the method improves the stability of local updates for clients with extremely imbalanced data distributions. These findings demonstrate the effectiveness of the proposed weighting strategy in mitigating performance degradation caused by class imbalance in FL environments.