青岛科技大学  English 
赵文仓
赞  

教师拼音名称:zhaowencang

手机版

访问量:

最后更新时间:..

Smoother manifold for graph meta-learning

关键字:

摘要:Meta-learning provides a framework for the possibility of mimicking artificial intelligence. However, data distribution of the training set fails to be consistent with the one of the testing set as the limited domain differences among them. These factors often result in poor generalization in existing meta-learning models. In this work, a novel smoother manifold for graph meta-learning(SGML) is proposed, which derives the similarity parameters of node features from the relationship between nodes and edges in the graph structure, and then utilizes the similarity parameters to yield smoother manifold through embedded propagation module. Smoother manifold can naturally filter out noise from the most important components when generalizing the local mapping relationship to the global.Besides suiting for generalizing on unseen low data issues, the framework is capable to easily perform transductive inference. Experimental results on MiniImageNet and TieredImageNet consistently show that applying SGML to supervised and semi-supervised classification can improve the performance in reducing the noise of domain shift representation.

卷号:v.28

期号:01

是否译文:

崂山校区 - 山东省青岛市松岭路99号   
四方校区 - 山东省青岛市郑州路53号   
中德国际合作区(中德校区) - 山东省青岛市西海岸新区团结路3698号
高密校区 - 山东省高密市杏坛西街1号   
济南校区 - 山东省济南市文化东路80号©2015 青岛科技大学    
管理员邮箱:master@qust.edu.cn