Outer product enhanced heterogeneous information network embedding for recommendation

作者：

Highlights：

• Key information is hidden between embeddings in different dimensions.

• The outer product between embeddings of user and item can mine useful information.

• The recommendation model with outer product is proposed.

• The performance of recommendation can improve by outer product between embeddings.

摘要

•Key information is hidden between embeddings in different dimensions.•The outer product between embeddings of user and item can mine useful information.•The recommendation model with outer product is proposed.•The performance of recommendation can improve by outer product between embeddings.

论文关键词：Heterogeneous information network,Network embedding,Matrix factorization,Outer product,Recommender system

论文评审过程：Received 30 March 2020, Revised 8 September 2020, Accepted 19 November 2020, Available online 21 November 2020, Version of Record 10 February 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.114359