Abstract
Federated learning (FL) is a distributed machine learning technique in which multiple clients cooperate to train a shared model without exchanging their raw data. However, heterogeneity of data distribution among clients usually leads to poor model inference. In this paper, a prototype-based federated learning framework is proposed, which can achieve better inference performance with only a few changes to the last global iteration of the typical federated learning process. In the last iteration, the server aggregates the prototypes transmitted from distributed clients and then sends them back to local clients for their respective model inferences. Experiments on two baseline datasets show that our proposal can achieve higher accuracy (at least 1%) and relatively efficient communication than two popular baselines under different heterogeneous settings.
Abstract (translated)
分布式学习(FL)是一种分布式机器学习技术,它多个客户端合作训练一个共享模型,而无需交换他们的原始数据。然而,客户端数据分布的不一致通常导致模型推理效果不佳。在本文中,我们提出了基于原型的分布式学习框架,该框架仅需要对典型的分布式学习流程的最后一个全局迭代进行少量更改,就能实现更好的推理性能。在最后一个迭代中,服务器将分布式客户端传输的原型聚合起来,然后将它们发送给本地客户端,以进行各自模型推理。对两个基准数据集的实验表明,我们的提议能够在不同不一致环境下(至少达到1%)实现更高的精度(至少1%)和更高效的沟通。
URL
https://arxiv.org/abs/2303.12296