论文标题
更友好的行业：高效设计的联合学习
More Industry-friendly: Federated Learning with High Efficient Design
论文作者
论文摘要
尽管自Google抛弃了联邦学习范式以来，已经取得了许多成就，但研究人员仍然有很大的空间来优化其效率。在本文中，我们提出了一种配备了双头设计的高效FL方法，旨在对非IID数据集进行个性化优化，以及用于节省通信的逐渐模型共享设计。实验结果表明，与其他最先进的方法（SOTA）相比，我们的方法具有更稳定的精度性能和在各种数据分布之间具有更好的沟通效率，使其更加友好。
Although many achievements have been made since Google threw out the paradigm of federated learning (FL), there still exists much room for researchers to optimize its efficiency. In this paper, we propose a high efficient FL method equipped with the double head design aiming for personalization optimization over non-IID dataset, and the gradual model sharing design for communication saving. Experimental results show that, our method has more stable accuracy performance and better communication efficient across various data distributions than other state of art methods (SOTAs), makes it more industry-friendly.
