Complex graph convolutional network for link prediction in knowledge graphs

作者：

Highlights：

• Real embeddings usually suffer from high distortion.

• An extension of graph convolution network is introduced with complex embeddings.

• A novel complex scoring function based on PARATUCK2 decomposition is introduced.

• The results show that complex embeddings lead to performance improvement.

摘要

•Real embeddings usually suffer from high distortion.•An extension of graph convolution network is introduced with complex embeddings.•A novel complex scoring function based on PARATUCK2 decomposition is introduced.•The results show that complex embeddings lead to performance improvement.

论文关键词：Knowledge graph,Link prediction,Graph convolutional network,Complex embeddings,Tensor decomposition

论文评审过程：Received 14 December 2021, Revised 16 February 2022, Accepted 27 February 2022, Available online 26 March 2022, Version of Record 8 April 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.116796