Knowledge Graph Random Neural Networks for Recommender Systems

作者：

Highlights：

• A knowledge graph random neural network for recommendation is proposed.

• A random feature propagation framework with DropNode strategy is built.

• The consistency regularization is designed to optimize the prediction.

摘要

•A knowledge graph random neural network for recommendation is proposed.•A random feature propagation framework with DropNode strategy is built.•The consistency regularization is designed to optimize the prediction.

论文关键词：Recommendation,Knowledge graph,Graph neural networks,Feature propagation

论文评审过程：Received 29 July 2021, Revised 29 January 2022, Accepted 28 March 2022, Available online 11 April 2022, Version of Record 25 April 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117120