Knowledge Graph Embedding Bi-Vector Models for Symmetric Relation

05/23/2019
by   Jinkui Yao, et al.
0

Knowledge graph embedding (KGE) models have been proposed to improve the performance of knowledge graph reasoning. However, there is a general phenomenon in most of KGEs, as the training progresses, the symmetric relations tend to zero vector, if the symmetric triples ratio is high enough in the dataset. This phenomenon causes subsequent tasks, e.g. link prediction etc., of symmetric relations to fail. The root cause of the problem is that KGEs do not utilize the semantic information of symmetric relations. We propose KGE bi-vector models, which represent the symmetric relations as vector pair, significantly increasing the processing capability of the symmetry relations. We generate the benchmark datasets based on FB15k and WN18 by completing the symmetric relation triples to verify models. The experiment results of our models clearly affirm the effectiveness and superiority of our models against baseline.

READ FULL TEXT

page 1

page 4

research
10/27/2021

Rot-Pro: Modeling Transitivity by Projection in Knowledge Graph Embedding

Knowledge graph embedding models learn the representations of entities a...
research
04/15/2021

Node Co-occurrence based Graph Neural Networks for Knowledge Graph Link Prediction

We introduce a novel embedding model, named NoKE, which aims to integrat...
research
03/18/2020

Realistic Re-evaluation of Knowledge Graph Completion Methods: An Experimental Study

In the active research area of employing embedding models for knowledge ...
research
10/10/2020

RatE: Relation-Adaptive Translating Embedding for Knowledge Graph Completion

Many graph embedding approaches have been proposed for knowledge graph c...
research
10/02/2020

TeRo: A Time-aware Knowledge Graph Embedding via Temporal Rotation

In the last few years, there has been a surge of interest in learning re...
research
08/12/2021

HopfE: Knowledge Graph Representation Learning using Inverse Hopf Fibrations

Recently, several Knowledge Graph Embedding (KGE) approaches have been d...
research
08/13/2018

A Capsule Network-based Embedding Model for Knowledge Graph Completion and Search Personalization

In this paper, we introduce an embedding model, named CapsE, exploring a...

Please sign up or login with your details

Forgot password? Click here to reset