arxiv2020专题

阅读记录【arXiv2020】 Adaptive Personalized Federated Learning

Adaptive Personalized Federated Learning 论文地址: https://arxiv.org/abs/2003.13461 摘要 对联邦学习算法个性化程度的研究表明,只有最大化全局模型的性能才会限制局部模型的个性化能力。在本文中,我们提倡自适应个性化联合学习(APFL)算法,其中每个客户端将训练其本地模型,同时为全局模型做出贡献。我们推导出局部模型和全局模

持续学习-Towards reusable network components by learning compatible representations-arxiv2020

Abstract This paper proposed to make a first step towards compatible and hence reusable network components. Split a network into two components: a feature extractor and a target task head. 最终验证在三个应