Meta-learning provides a framework for the possibility of mimicking artificial intelligence.How-ever,data distribution of the training set fails to be consistent with the one of the testing set as the limited domain d...Meta-learning provides a framework for the possibility of mimicking artificial intelligence.How-ever,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.展开更多
The impact of certain separate characteristics, including the porosity parameter, reaction rate parameter, and viscoelastic parameters of steady convective diffusion across a rectangular channel, has been investigated...The impact of certain separate characteristics, including the porosity parameter, reaction rate parameter, and viscoelastic parameters of steady convective diffusion across a rectangular channel, has been investigated in this article. The model’s momentum and concentration equations were developed using the similarities technique, and the numerically finite volume method was combined with the Beavers and Joseph slip conditions. Various graphs have been used to get insight into various parameters of the problem on velocity and concentration. The cartilage surfaces are assumed to be porous, and the viscosity of synovial fluid varies with hyaluronate (HA) content.展开更多
基金Supported by the National Natural Science Foundation of China(No.61171131)the Key R&D Program of Shandong Province(No.YD01033)the China Scholarship Council Project(No.021608370049).
文摘Meta-learning provides a framework for the possibility of mimicking artificial intelligence.How-ever,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.
文摘The impact of certain separate characteristics, including the porosity parameter, reaction rate parameter, and viscoelastic parameters of steady convective diffusion across a rectangular channel, has been investigated in this article. The model’s momentum and concentration equations were developed using the similarities technique, and the numerically finite volume method was combined with the Beavers and Joseph slip conditions. Various graphs have been used to get insight into various parameters of the problem on velocity and concentration. The cartilage surfaces are assumed to be porous, and the viscosity of synovial fluid varies with hyaluronate (HA) content.
