GCNFusion: An efficient graph convolutional network based model for information diffusion

作者：

Highlights：

• Proposing an unsupervised model for Information Diffusion on graphs.

• Proposing a method for identifying graph influential nodes Inspired by Wrapper’s approaches.

• Using the SIR simulation model for disseminating the information on a graph.

• Conducting several experiments on several real-world data to affirm the efficiency of our method.

摘要

•Proposing an unsupervised model for Information Diffusion on graphs.•Proposing a method for identifying graph influential nodes Inspired by Wrapper’s approaches.•Using the SIR simulation model for disseminating the information on a graph.•Conducting several experiments on several real-world data to affirm the efficiency of our method.

论文关键词：Feature selection,Graph embedding,Graph neural networks,Influential nodes,Information diffusion

论文评审过程：Received 8 September 2021, Revised 3 January 2022, Accepted 28 March 2022, Available online 9 April 2022, Version of Record 6 May 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117053