Deep learning approach on information diffusion in heterogeneous networks

作者：

Highlights：

• Propose a novel meta-path representation learning on heterogeneous networks.

• Investigate the proposed representation aligned with different types of meta-paths.

• Employ the deep learning based architectures on predicting the information diffusion in heterogeneous networks.

• Apply the proposed algorithm on different diffusion processes including topic diffusion and cascade prediction.

• The results show that the proposed approach outperformed several state-of-the-art methods.

摘要

•Propose a novel meta-path representation learning on heterogeneous networks.•Investigate the proposed representation aligned with different types of meta-paths.•Employ the deep learning based architectures on predicting the information diffusion in heterogeneous networks.•Apply the proposed algorithm on different diffusion processes including topic diffusion and cascade prediction.•The results show that the proposed approach outperformed several state-of-the-art methods.

论文关键词：Heterogeneous networks,Information diffusion,Topic diffusion,Cascade prediction,Network representation learning,Deep learning

论文评审过程：Received 9 December 2018, Revised 23 July 2019, Accepted 22 October 2019, Available online 29 October 2019, Version of Record 16 January 2020.

论文官网地址：https://doi.org/10.1016/j.knosys.2019.105153