Graph Federated Learning for CIoT Devices in Smart Home Applications

计算机科学 图形 计算机网络 分布式计算 计算机安全 理论计算机科学
作者
Arash Rasti-Meymandi,Seyed Mohammad Sheikholeslami,Jamshid Abouei,Konstantinos N. Plataniotis
出处
期刊:IEEE Internet of Things Journal [Institute of Electrical and Electronics Engineers]
卷期号:10 (8): 7062-7079 被引量:16
标识
DOI:10.1109/jiot.2022.3228727
摘要

This paper deals with the problem of statistical and system heterogeneity in a cross-silo Federated Learning (FL) framework where there exist a limited number of Consumer Internet of Things (CIoT) devices in a smart building. We propose a novel Graph Signal Processing (GSP)-inspired aggregation rule based on graph filtering dubbed ``G-Fedfilt''. The proposed aggregator enables a structured flow of information based on the graph's topology. This behavior allows capturing the interconnection of CIoT devices and training domain-specific models. The embedded graph filter is equipped with a tunable parameter which enables a continuous trade-off between domain-agnostic and domain-specific FL. In the case of domain-agnostic, it forces G-Fedfilt to act similar to the conventional Federated Averaging (FedAvg) aggregation rule. The proposed G-Fedfilt also enables an intrinsic smooth clustering based on the graph connectivity without explicitly specified which further boosts the personalization of the models in the framework. In addition, the proposed scheme enjoys a communication-efficient time-scheduling to alleviate the system heterogeneity. This is accomplished by adaptively adjusting the amount of training data samples and sparsity of the models' gradients to reduce communication desynchronization and latency. Simulation results show that the proposed G-Fedfilt achieves up to $3.99\% $ better classification accuracy than the conventional FedAvg when concerning model personalization on the statistically heterogeneous local datasets, while it is capable of yielding up to $2.41\%$ higher accuracy than FedAvg in the case of testing the generalization of the models.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
科研通AI5应助儒雅老太采纳,获得10
4秒前
英姑应助科研猫猫采纳,获得10
6秒前
Akim应助Shandongdaxiu采纳,获得10
6秒前
zgt01完成签到,获得积分10
8秒前
哈哈完成签到 ,获得积分10
9秒前
13秒前
松山少林学武功完成签到 ,获得积分10
13秒前
14秒前
17秒前
18秒前
米缸发布了新的文献求助10
19秒前
倪晓琳发布了新的文献求助10
19秒前
包子完成签到,获得积分10
20秒前
儒雅老太发布了新的文献求助10
24秒前
混子完成签到,获得积分10
25秒前
28秒前
升学顺利身体健康完成签到,获得积分10
31秒前
liangchenglvliao完成签到 ,获得积分10
32秒前
甘泊寓完成签到,获得积分10
33秒前
1_0发布了新的文献求助10
33秒前
儒雅老太完成签到,获得积分10
35秒前
圣诞节完成签到,获得积分10
35秒前
可爱的函函应助叶95采纳,获得10
40秒前
负责冰凡完成签到,获得积分20
42秒前
科研通AI5应助柠橙采纳,获得30
43秒前
46秒前
46秒前
50秒前
51秒前
ding应助黄饱饱采纳,获得10
51秒前
Ava应助黄饱饱采纳,获得10
51秒前
Orange应助黄饱饱采纳,获得10
51秒前
柠橙发布了新的文献求助30
56秒前
1分钟前
核桃应助祁归一采纳,获得10
1分钟前
Julie完成签到 ,获得积分10
1分钟前
Hmbb完成签到,获得积分10
1分钟前
Lucas应助科研通管家采纳,获得10
1分钟前
科研通AI2S应助科研通管家采纳,获得10
1分钟前
爆米花应助科研通管家采纳,获得10
1分钟前
高分求助中
【此为提示信息,请勿应助】请按要求发布求助,避免被关 20000
ISCN 2024 – An International System for Human Cytogenomic Nomenclature (2024) 3000
Continuum Thermodynamics and Material Modelling 2000
Encyclopedia of Geology (2nd Edition) 2000
105th Edition CRC Handbook of Chemistry and Physics 1600
Maneuvering of a Damaged Navy Combatant 650
基于CZT探测器的128通道能量时间前端读出ASIC设计 300
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 物理 生物化学 纳米技术 计算机科学 化学工程 内科学 复合材料 物理化学 电极 遗传学 量子力学 基因 冶金 催化作用
热门帖子
关注 科研通微信公众号,转发送积分 3777324
求助须知:如何正确求助?哪些是违规求助? 3322593
关于积分的说明 10210806
捐赠科研通 3037943
什么是DOI,文献DOI怎么找? 1666984
邀请新用户注册赠送积分活动 797900
科研通“疑难数据库(出版商)”最低求助积分说明 758072