The Data Value based Asynchronous Federated Learning for UAV Swarm under Unstable Communication Scenarios

计算机科学 异步通信 群体行为 调度(生产过程) 软件部署 强化学习 无线 分布式计算 实时计算 数学优化 人工智能 计算机网络 电信 数学 操作系统
作者
Zhenhua Cui,Tao Yang,Xiaofeng Wu,Hui Feng,Bo Hu
出处
期刊:IEEE Transactions on Mobile Computing [IEEE Computer Society]
卷期号:: 1-15
标识
DOI:10.1109/tmc.2023.3331906
摘要

Federated learning has provided a new approach to coordinating a group of clients to train a machine learning model collaboratively, which can be easily embedded into Unmanned Aerial Vehicle (UAV) swarms. Compared with the terrestrial wireless networks, the UAV swarm faces more precarious communication conditions, rendering synchronous aggregation no longer tenable. Additionally, the data collected from UAVs tend to be heterogeneous due to different deployment regions or requirements. To overcome these restrictions, this paper has proposed a novel two-stage Asynchronous Federated Learning scheme for the UAV swarm. Initially, the convergence property of both convex and non-convex models trained by the proposed scheme is analyzed. In the pre-training stage, we modeled the learning process as a cooperative game with demonstrated monotonicity and submodularity. Furthermore, the Shapley Value is imported to quantify data values of UAVs, and the upper bound of its estimation error rate is derived. In the training stage, a new concept named Network Age of Updates (AoU) is proposed to address the fairness issue, quantifying the model’s generalization capability with data value consideration, and a sequential UAV selection scheduling is performed through the AoU minimization by Whittle Index method. Finally, the system performance is validated through both theoretical analysis and simulations.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

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
Ryan完成签到,获得积分20
刚刚
1秒前
1秒前
1秒前
zhouleiwang发布了新的文献求助10
1秒前
沉默凡梦完成签到,获得积分10
1秒前
人谷发布了新的文献求助10
2秒前
dong应助魏伯安采纳,获得10
2秒前
王哥发布了新的文献求助10
2秒前
2秒前
CQ发布了新的文献求助30
3秒前
3秒前
CC完成签到 ,获得积分10
3秒前
4秒前
罗大壮发布了新的文献求助10
4秒前
walu发布了新的文献求助10
4秒前
HHHHH完成签到,获得积分10
4秒前
5秒前
lalala发布了新的文献求助10
6秒前
pluto应助郭小胖14采纳,获得10
6秒前
6秒前
6秒前
CipherSage应助菠萝采纳,获得10
6秒前
cnm完成签到,获得积分20
7秒前
mo完成签到,获得积分10
7秒前
静俏发布了新的文献求助10
7秒前
111发布了新的文献求助10
7秒前
7秒前
传奇3应助QingSun1采纳,获得10
7秒前
小米饭完成签到,获得积分10
7秒前
量子星尘发布了新的文献求助10
8秒前
勤劳小海豚完成签到,获得积分10
9秒前
Wu关闭了Wu文献求助
9秒前
9秒前
zzk发布了新的文献求助10
9秒前
爽哥发布了新的文献求助30
9秒前
听话的不乐完成签到,获得积分10
10秒前
langjiaqi关注了科研通微信公众号
10秒前
10秒前
淡淡的襄完成签到,获得积分10
10秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 360
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 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3971091
求助须知:如何正确求助?哪些是违规求助? 3515797
关于积分的说明 11179488
捐赠科研通 3250872
什么是DOI,文献DOI怎么找? 1795536
邀请新用户注册赠送积分活动 875891
科研通“疑难数据库(出版商)”最低求助积分说明 805207