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 2402.05050cs.LGmath.OC
收藏

联邦学习可以找到有利的合作伙伴

Federated Learning Can Find Friends That Are Advantageous

MBZUAI(穆罕默德·本·扎耶德人工智能大学);Department of Machine Learning(机器学习系)

Nazarii Tupitsa, Samuel Horváth, Martin Takáč, Eduard Gorbunov

AI总结:

针对联邦学习中客户端数据异构带来的协作优劣问题,提出自适应聚合权重算法,识别有利数据分布的客户端,证明收敛性不劣于同分布聚合,实验优于传统方法。

摘要:

在联邦学习(FL)中,客户端数据的分布式特性和异构性既带来了机遇也带来了挑战。虽然客户端之间的协作可以显著增强学习过程,但并非所有协作都是有益的;有些甚至可能是有害的。在本研究中,我们提出了一种新颖的算法,为参与FL训练的客户端分配自适应聚合权重,识别出那些数据分布最有利于特定学习目标的客户端。我们证明了我们的聚合方法的收敛性不劣于仅聚合来自具有相同数据分布的客户端的更新的方法。此外,实证评估一致表明,由我们的算法指导的协作优于传统的FL方法。这凸显了明智选择客户端的关键作用,并为未来几年更精简和有效的FL实现奠定了基础。

英文摘要:

In Federated Learning (FL), the distributed nature and heterogeneity of client data present both opportunities and challenges. While collaboration among clients can significantly enhance the learning process, not all collaborations are beneficial; some may even be detrimental. In this study, we introduce a novel algorithm that assigns adaptive aggregation weights to clients participating in FL training, identifying those with data distributions most conducive to a specific learning objective. We demonstrate that our aggregation method converges no worse than the method that aggregates only the updates received from clients with the same data distribution. Furthermore, empirical evaluations consistently reveal that collaborations guided by our algorithm outperform traditional FL approaches. This underscores the critical role of judicious client selection and lays the foundation for more streamlined and effective FL implementations in the coming years.

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。

↑