.png){kind=icon}
返回
Semi-supervised learning with dropouts
.png){kind=icon}
PRE
AI
DOI：10.1016/j.eswa.2022.119235.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Graph Laplacian manifold regularization exploits the intrinsic geometrical properties of the underlying graph over both labeled and unlabeled data to approximate an optimal smooth prediction function. The regularization works on the assumption that abundant unlabeled data add information to the model, which increases accuracy and generalization. However, a large number of unlabeled data points with few labeled data points results in function degeneration which restricts generalization. Higher order regularization through iterated Laplacian semi-norm resolves this problem, but it is not computationally intensive and not scalable. In this paper, we propose dropouts regularization by appropriately balancing the supervised loss and intrinsic regularization terms to enforce smoothness. This is done by increasing the labeled data points by assigning temporary soft -labels to a subset of unlabeled set iteratively. This is followed by the determination of the final labels. Localized Procrustes analysis is, then, used to increase the accuracy of label assignment. Experiments on both synthetic and real-world dataset show that the proposed model outperforms the existing graph Laplacian and its variants by a significant margin.
Keyword:
Dropouts
Graph Laplacian
Manifold regularization
Localized Procrustes analysis
期刊
IF:
7.5
论文数:
2.9W
被引数:
10.2W
机构
引用论文
Graph Laplacian Regularization With Procrustes Analysis for Sensor Node Localization.png)
IEEE SENSORS JOURNAL
IEEE SENSORS JOURNALIF4.5
PREAI
分享收藏Electrochemical study of high and low cobalt oxidation states in Group V substituted borane clusters
PREAI
分享收藏分享收藏Graph convolutional neural networks with node transition probability-based message passing and DropNode regularization基于节点转移概率的消息传递和DropNode正则化的图卷积神经网络
OAAI
OAAI分享收藏
查看更多内容