MGLGAN：a generative adversarial model based on multi-layer graph convolution net and recurrent neural networks for link prediction

Jiantong Song; Xiaoqiang Xiao; Weixun Ning; Xu Zhang

doi:10.1117/12.2635719

6 May 2022 MGLGAN：a generative adversarial model based on multi-layer graph convolution net and recurrent neural networks for link prediction

Jiantong Song, Xiaoqiang Xiao, Weixun Ning, Xu Zhang

Author Affiliations +

Proceedings Volume 12256, International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2022); 122562H (2022) https://doi.org/10.1117/12.2635719
Event: 2022 International Conference on Electronic Information Engineering, Big Data and Computer Technology, 2022, Sanya, China

Abstract

Link prediction is a technology to find existing but unobserved links (static) or predict new links (dynamic) by studying the network topology. In real life, most networks change with time. Some recent works focus on the dynamic prediction of networks, but they do not solve the weight problem in link prediction well. At the same time, the methods based on matrix decomposition and node embedding used in most link prediction tasks have some problems, such as huge amount of calculation or can’t better represent the time evolution. In this paper, we extend the method of predicting the weight between nodes in dynamic networks and propose a generative adversarial model based on multi-layer graph convolution and recurrent neural network. The model consists of a generator and discriminator trained during an adversarial process. Multi-layer graph convolution used to approximate the high order similarity of network graph, so as to compensate the time evolution characteristic that RNN network can only deal with low order similarity. Using the process of confrontation training, the model can learn the representation of robust time evolution and predict with high accuracy. Experiments on several real data sets show that our model has good adaptability better than several baseline models.

Citation Download Citation

Jiantong Song, Xiaoqiang Xiao, Weixun Ning, and Xu Zhang "MGLGAN：a generative adversarial model based on multi-layer graph convolution net and recurrent neural networks for link prediction", Proc. SPIE 12256, International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2022), 122562H (6 May 2022); https://doi.org/10.1117/12.2635719

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available