4.6 Article

Deep learning model construction for a semi-supervised classification with feature learning

期刊

COMPLEX & INTELLIGENT SYSTEMS
卷 9, 期 3, 页码 3011-3021

出版社

SPRINGER HEIDELBERG
DOI: 10.1007/s40747-022-00641-9

关键词

Deep learning; Feature learning; Semi-supervised classification; Deep architecture

向作者/读者索取更多资源

Several deep learning architectures with feature learning have been proposed for image processing, data interpretation, speech recognition, and video analysis. This paper presents DLM-SSC, a unique method that combines high-order convolution and feature learning for semi-supervised node classification tasks. The suggested approaches outperform similar algorithms in terms of efficiency and effectiveness, as demonstrated on citation datasets and other datasets.
Several deep models were proposed in image processing, data interpretation, speech recognition, and video analysis. Most of these architectures need a massive proportion of training samples and use arbitrary configuration. This paper constructs a deep learning architecture with feature learning. Graph convolution networks (GCNs), semi-supervised learning and graph data representation, have become increasingly popular as cost-effective and efficient methods. Most existing merging node descriptions for node distribution on the graph use stabilised neighbourhood knowledge, typically requiring a significant amount of variables and a high degree of computational complexity. To address these concerns, this research presents DLM-SSC, a unique method semi-supervised node classification tasks that can combine knowledge from multiple neighbourhoods at the same time by integrating high-order convolution and feature learning. This paper employs two function learning techniques for reducing the number of parameters and hidden layers: modified marginal fisher analysis (MMFA) and kernel principal component analysis (KPCA). The MMFA and KPCA weight matrices are modified layer by layer when implementing the DLM, a supervised pretraining technique that doesn't require a lot of information. Free measuring on citation datasets (Citeseer, Pubmed, and Cora) and other data sets demonstrate that the suggested approaches outperform similar algorithms.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.6
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据