Node selection based on label quantity information in federated learning

Jiahua MA; Xinghua SUN; Wenchao XIA; Xijun WANG; Hongzhou TAN; Hongbo ZHU

doi:10.11959/j.issn.2096-3750.2021.00249

您当前的位置：

首页 >

文章列表页 >

Node selection based on label quantity information in federated learning

Theory and Technology | 更新时间：2024-06-05

- Node selection based on label quantity information in federated learning
- Chinese Journal on Internet of Things Vol. 5, Issue 4, Pages: 46-53(2021)
- 作者机构：
  
  1. 中山大学，广东广州510006
  2. 南京邮电大学，江苏南京 210023
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.2096-3750.2021.00249
  CLC： TP391.4
- Published：30 December 2021，
  
  Published Online：2021-12，
- 稿件说明：
移动端阅览
JIAHUA MA, XINGHUA SUN, WENCHAO XIA, et al. Node selection based on label quantity information in federated learning. [J]. Chinese journal on internet of things, 2021, 5(4): 46-53.
DOI：

JIAHUA MA, XINGHUA SUN, WENCHAO XIA, et al. Node selection based on label quantity information in federated learning. [J]. Chinese journal on internet of things, 2021, 5(4): 46-53. DOI： 10.11959/j.issn.2096-3750.2021.00249.

摘要

针对节点数据分布差异给联邦学习算法性能带来不良影响的问题，提出了一个基于标签量信息的节点选择算法。算法设计了一个关于节点标签量信息的优化目标，考虑在一定时耗限制下选择标签分布尽可能均衡的节点组合优化问题。根据节点组合的综合标签分布与模型收敛的相关性，新算法降低了全局模型的权重偏移上界以改善算法的收敛稳定性。仿真验证了新算法与现有的节点选择算法相比拥有更高的收敛效率。

Abstract

Aiming at the problem that the difference of node data distribution has adverse effect on the performance of federated learning algorithm

a node selection algorithm based on label quantity information was proposed.An optimization objective based on the label quantity information of nodes was designed

considering the optimization problem of selecting the nodes with balanced label distribution under a certain time consumption limit.According to the correlation between the aggregated label distribution of selected nodes and the convergence of the global model

the upper bound of the weight divergence of the global model was reduced to improve the convergence stability of the algorithm.Simulation results shows that the new algorithm had higher convergence efficiency than the existing node selection algorithm.

关键词

联邦学习节点选择通信时延

Keywords

federated learningnode selectioncommunication delay

references

MCMAHAN H B, MOORE E, RAMAGE D ,et al. Communication-efficient learning of deep networks from decentralized data[EB]. 2016.

YANG H H, LIU Z Z, QUEK T Q S ,et al. Scheduling policies for federated learning in wireless networks[J]. IEEE Transactions on Communications, 2020,68(1): 317-333.

NISHIO T, YONETANI R . Client selection for federated learning with heterogeneous resources in mobile edge[C]// Proceedings of ICC 2019- 2019 IEEE International Conference on Communications (ICC). Piscataway:IEEE Press, 2019: 1-7.

REN J K, HE Y H, WEN D Z ,et al. Scheduling for cellular federated edge learning with importance and channel awareness[J]. IEEE Transactions on Wireless Communications, 2020,19(11): 7690-7703.

HUANG T S, LIN W W, WU W T ,et al. An efficiency-boosting client selection scheme for federated learning with fairness guarantee[J]. IEEE Transactions on Parallel and Distributed Systems, 2021,32(7): 1552-1564.

XU J, WANG H Q . Client selection and bandwidth allocation in wireless federated learning networks:a long-term perspective[J]. IEEE Transactions on Wireless Communications, 2021,20(2): 1188-1200.

SHI W Q, ZHOU S, NIU Z S ,et al. Joint device scheduling and resource allocation for latency constrained wireless federated learning[J]. IEEE Transactions on Wireless Communications, 2021,20(1): 453-467.

ZHANG W Y, WANG X M, ZHOU P ,et al. Client selection for federated learning with non-IID data in mobile edge computing[J]. IEEE Access, 2021,9: 24462-24474.

RIBERO M, VIKALO H . Communication-efficient federated learning via optimal client sampling[EB]. 2020.

WU W T, HE L G, LIN W W ,et al. Accelerating federated learning over reliability-agnostic clients in mobile edge computing systems[J]. IEEE Transactions on Parallel and Distributed Systems, 2021,32(7): 1539-1551.

NGUYEN H T, SEHWAG V, HOSSEINALIPOUR S ,et al. Fast-convergent federated learning[J]. IEEE Journal on Selected Areas in Communications, 2021,39(1): 201-218.

YEGANEH Y, FARSHAD A, NAVAB N ,et al. Inverse distance aggregation for federated learning with non-IID data[M]// Domain Adaptation and Representation Transfer,and Distributed and Collaborative Learning. Cham: Springer International Publishing, 2020: 150-159.

ZHAO Y, LI M, LAI L Z ,et al. Federated learning with non-IID data[EB]. 2018.

MA J H, SUN X H, XIA W C ,et al. Client selection based on label quantity information for federated learning[C]// PIMRC:Workshop on Native-AI Empowered Wireless Networks. 2021.

CALDAS S, WU P, LI T ,et al. LEAF:a benchmark for federated settings[EB]. 2018.

AKDENIZ M R, LIU Y P, SAMIMI M K ,et al. Millimeter wave channel modeling and cellular capacity evaluation[J]. IEEE Journal on Selected Areas in Communications, 2014,32(6): 1164-1179.

Views

478

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Stable federated learning method for low-altitude IoT networks based on election strategy

Communication-efficient model pruning for federated learning in mobile edge computing

A survey of federated learning for 6G networks

Clients selection method based on knapsack model in federated learning

An incentive mechanism with bandwidth allocation for federated learning

Related Author

ZHANG Qiankun

ZHU Zhengyu

BAI Tianshui

WANG Guanghui

SHEN Lingfeng

WU Jiansheng

ZHAO Haitao

ZHANG Xi

Related Institution

China Information Technology Designing & Consulting Institute Co., Ltd.

School of Electrical and Information Engineering, Zhengzhou University

Henan International Joint Laboratory of Intelligent Network Theory and Key Technology

School of Software, Henan University

School of Computer Science, Nanjing University of Posts and Telecommunications

⁰