Numerous meta-learning methods focus on the few-shot learning issue,yet most of them assume that various tasks have a shared embedding space,so the generalization ability of the trained model is limited.In order to solve the aforementioned problem,a task-adaptive meta-learning method based on graph neural network(TAGN)is proposed in this paper,where the characterization ability of the original feature extraction network is ameliorated and the classification accuracy is remarkably improved.Firstly,a task-adaptation module based on the self-attention mechanism is employed,where the generalization ability of the model is enhanced on the new task.Secondly,images are classified in non-Euclidean domain,where the disadvantages of poor adaptability of the traditional distance function are overcome.A large number of experiments are conducted and the results show that the proposed methodology has a better performance than traditional task-independent classifica-tion methods on two real-word datasets.

ZHAO Wencang;LI Ming;QIN Wenqian

College of Automation and Electronic Engineering,Qingdao University of Science and Technology,Qingdao 266061,P.R.China

高技术通讯（英文版）

[1]ZHAO Wencang;LI Ming;QIN Wenqian-.Task-adaptation graph network for few-shot learning)[J].高技术通讯（英文版）,2022(02):164-171

TAGN

Task,adaptation,graph,network,few,shot,learning,Numerous,meta,methods,focus,issue,yet,most,them,assume,that,various,tasks,have,shared,embedding,space,generalization,trained,model,limited,In,order,solve,aforementioned,problem,adaptive,neural,proposed,this,paper,where,characterization,original,feature,extraction,ameliorated,classification,accuracy,remarkably,improved,Firstly,module,self,attention,mechanism,employed,enhanced,new,Secondly,images,classified,Euclidean,domain,disadvantages,poor,adaptability,traditional,distance,function,overcome,large,number,experiments,conducted,results,show,methodology,has,better,performance,than,independent,real,word,datasets

0.594295