非独立同分布与长尾分布下的联邦学习优化方法

冯文举; 杨焱青; 贾振红; 张琳琳

doi:10.13568/j.cnki.651094.651316.2024.12.30.0001

您当前的位置：

首页 >

文章列表页 >

非独立同分布与长尾分布下的联邦学习优化方法

空-天-地一体化智能数字基座关键技术研究与行业应用专题 | 更新时间：2026-01-22

- 非独立同分布与长尾分布下的联邦学习优化方法
- 非独立同分布与长尾分布下的联邦学习优化方法
- 新疆大学学报（自然科学版中英文） 2025年42卷第4期页码：425-433
- 作者机构：
  
  1. 新疆大学计算机科学与技术学院
  2. 新疆大学软件学院
- 作者简介：
- 基金信息：
  
  新疆维吾尔自治区天山英才科技创新团队“面向公共安全的信号检测与处理技术研究”（2023TSYCTD0012）;新疆维吾尔自治区教育厅高校科研计划“基于深度生成模型的工控网络攻击检测技术研究”（XJEDU2021Y003）;新疆维吾尔自治区重大科技专项“能源数据标准化体系研究”（2022A01007-4）
- DOI：10.13568/j.cnki.651094.651316.2024.12.30.0001
  中图分类号： TP181
- 纸质出版：2025
- 稿件说明：
移动端阅览
[1]冯文举,杨焱青,贾振红,等.非独立同分布与长尾分布下的联邦学习优化方法[J].新疆大学学报(自然科学版中英文),2025,42(04):425-433.
[1]冯文举,杨焱青,贾振红,等.非独立同分布与长尾分布下的联邦学习优化方法[J].新疆大学学报(自然科学版中英文),2025,42(04):425-433. DOI： 10.13568/j.cnki.651094.651316.2024.12.30.0001.

DOI：10.13568/j.cnki.651094.651316.2024.12.30.0001.

摘要

针对联邦学习中非独立同分布和长尾分布问题，结合对比学习和两阶段学习策略，提出了一种新型联邦学习方法．利用对比学习对齐客户端模型与全局模型之间的特征，减少各客户端之间的特征差异，同时汇总并上传客户端的模型梯度，通过服务器端的虚拟特征重新训练分类器，提升全局模型对少数类数据的学习能力．结果表明：所提方法在Fashion-MNIST数据集上准确率最高提升0.36%，在CIFAR-10数据集上准确率最高提升1.64%.

Abstract

To address the challenges of non-independent and identically distributed data and long-tail distributions in federated learning

a novel federated learning method is proposed by integrating contrastive learning with a two-stage learning strategy. The approach employs contrastive learning to align feature representations between client models and the global model

thereby reducing feature discrepancies across clients. Simultaneously

it aggregates and uploads client model gradients

enabling retraining of the classifier through virtual features on the server side to enhance the global model's learning capability for minority class data. Experimental results demonstrate that the proposed method achieves maximum accuracy improvements of 0.36% on the Fashion-MNIST dataset and1.64% on the CIFAR-10 dataset.

关键词

Keywords

references

XIAO J S,GUO H W,ZHOU J,et al.Tiny object detection with context enhancement and feature purification[J].Expert Systems with Applications,2023,211:118665．

杨晓奇，刘伍颖．文本特征和图结点混合增强的图卷积网络文本分类[J]．新疆大学学报(自然科学版)(中英文)，2024,41(1):69-77+109.YANG X Q,LIU W Y.Hybrid augmentation of text feature and graph node for graph convolutional networks text classification[J].Journal of Xinjiang University(Natural Science Edition in Chinese and English),2024,41(1):69-77+109.(in Chinese)

LI Z P,SHARMA V,MOHANTY S P.Preserving data privacy via federated learning:Challenges and solutions[J].IEEEConsumer Electronics Magazine,2020,9(3):8-16．

WEN J,ZHANG Z X,LAN Y,et al.A survey on federated learning:Challenges and applications[J].International Journal of Machine Learning and Cybernetics,2023,14(2):513-535．

ZHANG C,XIE Y,BAI H,et al.A survey on federated learning[J].Knowledge-Based Systems,2021,216:106775．

BRAUNECK A,SCHMALHORST L,MAJDABADI M M K,et al.Federated machine learning,privacy-enhancing technologies,and data protection laws in medical research:Scoping review[J].Journal of Medical Internet Research,2023,25:e41588．

ZHU J C,CAO J N,SAXENA D,et al.Blockchain-empowered federated learning:Challenges,solutions,and future directions[J].ACM Computing Surveys,2023,55(11):240．

CHEN H M,WANG H D,LONG Q Y,et al.Advancements in federated learning:Models,methods,and privacy[J].ACMComputing Surveys,2024,57(2):46．

SHUAI X,SHEN Y L,JIANG S Y,et al.Balance FL:Addressing class imbalance in long-tail federated learning[C]//2022 21st ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN).May 4-6,2022.Milano,Italy.IEEE,2022:271-284．

LI T,SAHU A K,ZAHEER M,et al.Fed DANE:A federated Newton-type method[C]//2019 53rd Asilomar Conference on Signals,Systems,and Computers.November 3-6,2019.Pacific Grove,CA,USA.IEEE,2019:1227-1231．

汤凌韬，王迪，刘盛云．面向非独立同分布数据的联邦学习数据增强方案[J]．通信学报，2023,44(1):164-176.TANG L T,WANG D,LIU S Y.Data augmentation scheme for federated learning with non-IID data[J].Journal on Communications,2023,44(1):164-176.(in Chinese).

LI Q B,HE B S,SONG D.Model-contrastive federated learning[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).June 20-25,2021.Nashville,TN,USA.IEEE,2021:10708-10717．

HE K M,FAN H Q,WU Y X,et al.Momentum contrast for unsupervised visual representation learning[C]//2020 IEEE/CVFConference on Computer Vision and Pattern Recognition (CVPR).June 13-19,2020.Seattle,WA,USA.IEEE,2020:9726-9735．

REN S Q,HE K M,GIRSHICK R,et al.Faster R-CNN:Towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149．

JI S Y,ZHANG Z Z,YING S H,et al.Kullback-Leibler divergence metric learning[J].IEEE Transactions on Cybernetics,2022,52(4):2047-2058．

WANG Y S,TONG Y X,SHI D Y.Federated latent Dirichlet allocation:A local differential privacy based framework[J].Proceedings of the AAAI Conference on Artificial Intelligence,2020,34(4):6283-6290．

HE K M,ZHANG X Y,REN S Q,et al.Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).June 27-30,2016.Las Vegas,NV,USA.IEEE,2016:770-778．

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

结合对比学习的细粒度长短期偏好序列推荐