Bipartite network embedding with Symmetric Neighborhood Convolution

作者：

Highlights：

• A novel neural network-based method for bipartite network embedding.

• Use symmetric one-dimensional convolution kernels for feature learning.

• The method can accommodate the heterogeneity in bipartite structure.

• Extensive experiments manifest the superiority of the proposed method.

摘要

•A novel neural network-based method for bipartite network embedding.•Use symmetric one-dimensional convolution kernels for feature learning.•The method can accommodate the heterogeneity in bipartite structure.•Extensive experiments manifest the superiority of the proposed method.

论文关键词：Network representation learning,Bipartite networks,Graph convolution,Link prediction,Recommendation

论文评审过程：Received 11 April 2021, Revised 6 September 2021, Accepted 24 February 2022, Available online 11 March 2022, Version of Record 17 March 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.116757