FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Data

arXiv:2401.08977v2 Announce Type: replace
Abstract: Federated Long-Tailed Learning (Fed-LT), a paradigm wherein data collected from decentralized local clients manifests a globally prevalent long-tailed distribution, has garnered considerable attention in recent times. In the context of Fed-LT, existing works have predominantly centered on addressing the data imbalance issue to enhance the efficacy of the generic global model while neglecting the performance at the local level. In contrast, conventional Personalized Federated Learning (pFL) techniques are primarily devised to optimize personalized local models …

abstract arxiv attention context cs.ai cs.lg data decentralized distribution fed federated learning issue paradigm type