Decoupled Federated Learning on Long-Tailed and Non-IID data with Feature Statistics

arXiv:2403.08364v1 Announce Type: new
Abstract: Federated learning is designed to enhance data security and privacy, but faces challenges when dealing with heterogeneous data in long-tailed and non-IID distributions. This paper explores an overlooked scenario where tail classes are sparsely distributed over a few clients, causing the models trained with these classes to have a lower probability of being selected during client aggregation, leading to slower convergence rates and poorer model performance. To address this issue, we propose a two-stage Decoupled …

abstract arxiv challenges cs.ai cs.lg data data security data security and privacy distributed feature federated learning paper privacy security security and privacy statistics type