arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2012.08809cs.LGcs.AIcs.DC
收藏

更行业友好:高效设计的联邦学习

More Industry-friendly: Federated Learning with High Efficient Design

Huawei Technologies Co., Ltd(华为技术有限公司);Nanjing University(南京大学)

Dingwei Li, Qinglong Chang, Lixue Pang, Yanfang Zhang, Xudong Sun, Jikun Ding, Liang Zhang

摘要:

自Google提出联邦学习(FL)范式以来,虽然已经取得了许多成就,但其效率仍有很大的提升空间。本文提出了一种高效的FL方法,该方法采用双头设计,旨在对非IID数据集进行个性化优化,并采用渐进模型共享设计,以节省通信。实验结果表明,该方法在不同的数据分布下具有更稳定的准确性和更好的通信效率,具有更好的行业友好性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑