文献类型：期刊文献

中文题名：Advancing Graph Convolution Network with Revised Laplacian Matrix

英文题名：Advancing Graph Convolution Network with Revised Laplacian Matrix

作者：Wang, Jiahui[1];Guo, Yi[1,2,3];Wang, Zhihong[1];Tang, Qifeng[1,3];Wen, Xinxiu[1]

机构：[1]East China Univ Sci & Technol, Shanghai 200237, Peoples R China;[2]Natl Engn Lab Big Data Distribut & Exchange Techno, Shanghai 200436, Peoples R China;[3]Shanghai Engn Res Ctr Big Data & Internet Audience, Shanghai 200072, Peoples R China

年份：2020

卷号：29

期号：6

起止页码：1134

中文期刊名：Chinese Journal of Electronics

外文期刊名：CHINESE JOURNAL OF ELECTRONICS

收录：CSTPCD;;EI(收录号：20210910001443);Scopus;WOS:【SCI-EXPANDED(收录号:WOS:001413519700007)】；CSCD:【CSCD2019_2020】；

基金：This work is supported by the National Key Research and Development Program of China (No.2018YFC0807105), the National Natural Science Foundation of China (No.61462073), and the Science and Technology Committee of Shanghai Municipality (No.17DZ1101003, No.18511106602, No.18DZ2252300).

语种：英文

中文关键词：Graph convolution network;Clustering;Label propagation;Laplacian matrix;Graph structure;Fraud detection

外文关键词：Laplace equations; Accuracy; Convolution; Filtering; Computational modeling; Image edge detection; Feature extraction; Stability analysis; Data models; Noise measurement; Graph convolution network; Clustering; Label propagation; Laplacian matrix; Graph structure; Fraud detection

摘要：Graph convolution networks are extremely efficient on the graph-structure data,which both consider the graph and feature information.Most existing models mainly focus on redefining the complicated network structure,while ignoring the negative impact of lowquality input data during the aggregation process.This paper utilizes the revised Laplacian matrix to improve the performance of the original model in the preprocessing stage.The comprehensive experimental results testify that our proposed model performs significantly better than other off-the-shelf models with a lower computational complexity,which gains relatively higher accuracy and stability.
Graph convolution networks are extremely efficient on the graph-structure data, which both consider the graph and feature information. Most existing models mainly focus on redefining the complicated network structure, while ignoring the negative impact of low-quality input data during the aggregation process. This paper utilizes the revised Laplacian matrix to improve the performance of the original model in the preprocessing stage. The comprehensive experimental results testify that our proposed model performs significantly better than other off-the-shelf models with a lower computational complexity, which gains relatively higher accuracy and stability.