"Logit Calibration for Non-IID and Long-Tailed Data in Federated Learni" by Huan Wang, Lijuan Wang et al.
Federated learning (FL) strives to enable collaborative training of deep models on the distributed clients of different data without centrally aggregating raw data and hence improving data privacy. Nevertheless, a central challenge in training classification models in the federated system is learning with non-IID data. Most of the existing work is dedicated to eliminating the heterogeneous influence of non-IID data in a federated system. However, in many real-world FL applications, the co-occurrence of data heterogeneity and long-tailed distribution is unavoidable. The universal class distribu...
Source: uow.edu.au
