A Structure-Enriched Neural Network for network embedding. (1st March 2019)

• Record Type: Journal Article
• Authors: Qiao, Lisheng; Zhao, Hongke; Huang, Xiaohui; Li, Kai; Chen, Enhong
• Is Part Of: Expert systems with applications. Volume 117(2019)
• Page Start: 300
• Page End: 311
• Publication Date: 2019-03-01
• Subjects: Network embedding -- Direction adjustment -- Attention mechanism; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2018.09.040
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: A structure-enriched framework for network embedding from a holistic perspective. Introducing the direction tuning parameters into multi-order transition matrices. Using the denoise autoencoder to do the dimension reduction of multi-order matrices. Employing the method with attention mechanism to combine multi-order information. Abstract: Recent years have witnessed the importance of network embedding in many fields, as well as increased attention in academia. Although a number of algorithms have been proposed in this area, most existing models which only utilize the structure topology information of networks often suffer performance losses because of their insufficiency with regard to selecting structure similar patterns, handling noise data, and/or capturing non-linear or high-order structure information. To address these challenges, in this paper, we present a novelS tructure-E nrichedN euralN etwork (SENN) for network embedding. Specifically, SENN can not only capture the complex structure similar patterns observed in networks by introducing direction adjustment parameters of the transition probability, but also introduce a stacked denoise autoencoder to perform the dimension reduction for each order matrix independently. Therefore, SENN can preserve more useful structure information and make the embeddings more robust. Moreover, SENN can effectively integrate the multi-order structure information by the combining layer with attention mechanism. Finally, to compare with other state-of-the-art methods, we conduct extensive experiments with both synthetic and real-world datasets on various tasks (e.g., node classification, visualization). The experimental results clearly demonstrate the effectiveness of our proposed model for network embedding.