Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

7-2019

Abstract

Entity alignment typically suffers from the issues of structural heterogeneity and limited seed alignments. In this paper, we propose a novel Multi-channel Graph Neural Network model (MuGNN) to learn alignment-oriented knowledge graph (KG) embeddings by robustly encoding two KGs via multiple channels. Each channel encodes KGs via different relation weighting schemes with respect to self-attention towards KG completion and cross-KG attention for pruning exclusive entities respectively, which are further combined via pooling techniques. Moreover, we also infer and transfer rule knowledge for completing two KGs consistently. MuGNN is expected to reconcile the structural differences of two KGs, and thus make better use of seed alignments. Extensive experiments on five publicly available datasets demonstrate our superior performance (5% Hits@1 up on average). Source code and data used in the experiments can be accessed at https://github.com/thunlp/MuGNN.

Discipline

Databases and Information Systems | Graphics and Human Computer Interfaces | OS and Networks

Research Areas

Data Science and Engineering

Publication

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy, 2019 July 28 - August 2

First Page

1452

Last Page

1461

Identifier

10.18653/v1/P19-1140

Publisher

Association for Computational Linguistics

City or Country

Florence, Italy

Additional URL

http://doi.org/10.18653/v1/P19-1140

Download

Share

COinS