Abstract
Network embedding is a very important task to represent the high-dimensional network in a lowdimensional vector space, which aims to capture and preserve the network structure. Most existing network embedding methods are based on shallow models. However, actual network structures are complicated which means shallow models cannot obtain the high-dimensional nonlinear features of the network well. The recently proposed unsupervised deep learning models ignore the labels information. To address these challenges, in this paper, we propose an effective network embedding method of Structural Labeled Locally Deep Nonlinear Embedding (SLLDNE). SLLDNE is designed to obtain highly nonlinear features through utilizing deep neural network while preserving the label information of the nodes by using a semi-supervised classifier component to improve the ability of discriminations. Moreover, we exploit linear reconstruction of neighborhood nodes to enable the model to get more structural information. The experimental results of vertex classification on two real-world network datasets demonstrate that SLLDNE outperforms the other state-of-the-art methods.
Highlights
Over recent years, networks have become important and pervasive data carriers, with the scale of data becoming larger and the relationship between data becoming more complex than ever before
The rest of paper is organized as follows: in Section 2, we review some state-of-the-art methods; in Section 3, we introduce some of the basic concepts of network embedding and provide details of the Structural Labeled Locally Deep Nonlinear Embedding (SLLDNE) model; we report on our experiments and provide comprehensive experimental results in Section 4; Section 5 concludes
The results of multi-label classification are shown in Tables 3 and 4, from which we can draw the following conclusions: (1) The proposed SLLDNE achieves a significant and consistent improvement over all baseline methods on both datasets under different training ratios
Summary
Networks have become important and pervasive data carriers, with the scale of data becoming larger and the relationship between data becoming more complex than ever before. Network structures generate a huge potential for data mining, which is beneficial for many network analysis tasks, such as vertex classification[1], visualization[2], and link prediction[3]. Network analysis technology is very important to many real-world applications. Traditional network analysis technology has some limitations. The computational complexity of traditional methods is too high to be applied to modern large-scale networks.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
