arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.07433cs.LGcs.DC
收藏

聚合延迟联邦学习

Aggregation Delayed Federated Learning

Northwestern University(西北大学)

Ye Xue, Diego Klabjan, Yuan Luo

摘要:

联邦学习是一种分布式机器学习范例,其中多个数据所有者(客户端)协作训练一个机器学习模型,同时将数据保存在他们自己的设备上。客户端数据集的异构性是联邦学习算法面临的最大挑战之一。研究发现,标准联邦算法(如FedAvg)在非IID数据上会降低性能。许多现有的处理非IID数据的工作采用与FedAvg相同的聚合框架,并专注于改进服务器端或客户端的模型更新。在这项工作中,我们通过引入延迟聚合的再分配回合来从不同的角度应对这一挑战。我们在多个任务上进行了实验,结果表明,该框架显着提高了非IID数据的性能。

英文摘要:

Federated learning is a distributed machine learning paradigm where multiple data owners (clients) collaboratively train one machine learning model while keeping data on their own devices. The heterogeneity of client datasets is one of the most important challenges of federated learning algorithms. Studies have found performance reduction with standard federated algorithms, such as FedAvg, on non-IID data. Many existing works on handling non-IID data adopt the same aggregation framework as FedAvg and focus on improving model updates either on the server side or on clients. In this work, we tackle this challenge in a different view by introducing redistribution rounds that delay the aggregation. We perform experiments on multiple tasks and show that the proposed framework significantly improves the performance on non-IID data.

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。

↑