期刊
IEEE ACCESS
卷 9, 期 -, 页码 24462-24474出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2021.3056919
关键词
Data models; Training; Servers; Computational modeling; Internet of Things; Distributed databases; Degradation; Federated learning; mobile edge computing; client selection
资金
- National Natural Science Foundation of China [61872150, 61972448]
- Guangdong Basic and Applied Basic Research Foundation [2020A1515011209]
- Science and Technology Program of Guangzhou [202002030426]
The paper introduces a novel FL algorithm called CSFedAvg to alleviate the accuracy degradation caused by non-IID data, by utilizing weight divergence to recognize the non-IID degrees of clients and selecting clients with lower non-IID data frequency to train models more frequently. Simulations using publicly-available datasets show that the proposed FL algorithm improves training performance compared to existing protocols.
Federated Learning (FL) has recently attracted considerable attention in internet of things, due to its capability of enabling mobile clients to collaboratively learn a global prediction model without sharing their privacy-sensitive data to the server. Despite its great potential, a main challenge of FL is that the training data are usually non-Independent, Identically Distributed (non-IID) on the clients, which may bring the biases in the model training and cause possible accuracy degradation. To address this issue, this paper aims to propose a novel FL algorithm to alleviate the accuracy degradation caused by non-IID data at clients. Firstly, we observe that the clients with different degrees of non-IID data present heterogeneous weight divergence with the clients owning IID data. Inspired by this, we utilize weight divergence to recognize the non-IID degrees of clients. Then, we propose an efficient FL algorithm, named CSFedAvg, in which the clients with lower degree of non-IID data will be chosen to train the models with higher frequency. Finally, we conduct simulations using publicly-available datasets to train deep neural networks. Simulation results show that the proposed FL algorithm improves the training performance compared with existing FL protocol.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据