典型文献
Pseudo-label based semi-supervised learning in the distributed machine learning framework
文献摘要：
With the emergence of various intelligent applications,machine learning technologies face lots of challenges including large-scale models,application oriented real-time dataset and limited capa-bilities of nodes in practice.Therefore,distributed machine learning(DML)and semi-supervised learning methods which help solve these problems have been addressed in both academia and indus-try.In this paper,the semi-supervised learning method and the data parallelism DML framework are combined.The pseudo-label based local loss function for each distributed node is studied,and the stochastic gradient descent(SGD)based distributed parameter update principle is derived.A demo that implements the pseudo-label based semi-supervised learning in the DML framework is conduc-ted,and the CIFAR-10 dataset for target classification is used to evaluate the performance.Experi-mental results confirm the convergence and the accuracy of the model using the pseudo-label based semi-supervised learning in the DML framework.Given the proportion of the pseudo-label dataset is 20％,the accuracy of the model is over 90％when the value of local parameter update steps be-tween two global aggregations is less than 5.Besides,fixing the global aggregations interval to 3,the model converges with acceptable performance degradation when the proportion of the pseudo-label dataset varies from 20％to 80％.
文献关键词：
中图分类号：
作者姓名：
WANG Xiaoxi;WU Wenjun;YANG Feng;SI Pengbo;ZHANG Xuanyi;ZHANG Yanhua
作者机构：
Faculty of Information Technology,Beijing University of Technology,Beijing 100124,P.R.China;Beijing Capital International Airport Co.,Ltd.,Beijing 101317,P.R.China
文献出处：
引用格式：
[1]WANG Xiaoxi;WU Wenjun;YANG Feng;SI Pengbo;ZHANG Xuanyi;ZHANG Yanhua-.Pseudo-label based semi-supervised learning in the distributed machine learning framework)[J].高技术通讯（英文版）,2022(02):172-180
A类：
B类：
Pseudo,label,semi,supervised,learning,distributed,machine,framework,With,emergence,various,intelligent,applications,technologies,face,lots,challenges,including,large,scale,models,oriented,real,dataset,limited,capa,bilities,nodes,practice,Therefore,DML,methods,which,help,solve,these,problems,have,been,addressed,both,academia,indus,try,In,this,paper,parallelism,are,combined,pseudo,local,loss,function,each,studied,stochastic,gradient,descent,SGD,parameter,update,principle,derived,demo,that,implements,conduc,CIFAR,target,classification,used,evaluate,performance,Experi,mental,results,confirm,convergence,accuracy,using,Given,proportion,over,when,value,steps,tween,two,global,aggregations,less,than,Besides,fixing,interval,converges,acceptable,degradation,varies,from
AB值：
0.545424
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
