A Structural Representation Learning for Multi-relational Networks

Abstract

Most of the existing multi-relational network embedding methods, e.g., TransE, are formulated to preserve pair-wise connectivity structures in the networks. With the observations that significant triangular connectivity structures and parallelogram connectivity structures found in many real multi-relational networks are often ignored and that a hard… (More)
DOI: 10.24963/ijcai.2017/565

Topics

7 Figures and Tables

Cite this paper

@inproceedings{Liu2017ASR, title={A Structural Representation Learning for Multi-relational Networks}, author={Lin Liu and Xin Li and William Kwok-Wai Cheung and Chengcheng Xu}, booktitle={IJCAI}, year={2017} }