MAHE-IM: Multiple Aggregation of Heterogeneous Relation Embedding for Influence Maximization on Heterogeneous Information Network

作者：

Highlights：

• A embedding method MAHE-IM for IM on heterogeneous network.

• MAHE-IM extracts and aggregates multiple heterogeneous relationships.

• Eight network embedding and seven GNN methods extended for IM.

• MAHE-IM outperforms eighteen state-of-the-art algorithms.

• A web server (https://mahe-im.com/) is developed for maximizing user convenience.

摘要

•A embedding method MAHE-IM for IM on heterogeneous network.•MAHE-IM extracts and aggregates multiple heterogeneous relationships.•Eight network embedding and seven GNN methods extended for IM.•MAHE-IM outperforms eighteen state-of-the-art algorithms.•A web server (https://mahe-im.com/) is developed for maximizing user convenience.

论文关键词：Influence maximization,Heterogeneous information network,Network embedding

论文评审过程：Received 12 July 2021, Revised 20 April 2022, Accepted 22 April 2022, Available online 26 April 2022, Version of Record 7 May 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117289