Improving Hyper-Relational Knowledge Graph Completion

04/16/2021
by   Donghan Yu, et al.
0

Different from traditional knowledge graphs (KGs) where facts are represented as entity-relation-entity triplets, hyper-relational KGs (HKGs) allow triplets to be associated with additional relation-entity pairs (a.k.a qualifiers) to convey more complex information. How to effectively and efficiently model the triplet-qualifier relationship for prediction tasks such as HKG completion is an open challenge for research. This paper proposes to improve the best-performing method in HKG completion, namely STARE, by introducing two novel revisions: (1) Replacing the computation-heavy graph neural network module with light-weight entity/relation embedding processing techniques for efficiency improvement without sacrificing effectiveness; (2) Adding a qualifier-oriented auxiliary training task for boosting the prediction power of our approach on HKG completion. The proposed approach consistently outperforms STARE in our experiments on three benchmark datasets, with significantly improved computational efficiency.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/12/2023

HyperFormer: Enhancing Entity and Relation Interaction for Hyper-Relational Knowledge Graph Completion

Hyper-relational knowledge graphs (HKGs) extend standard knowledge graph...
research
05/29/2023

Representation Learning on Hyper-Relational and Numeric Knowledge Graphs with Transformers

A hyper-relational knowledge graph has been recently studied where a tri...
research
10/30/2018

DSKG: A Deep Sequential Model for Knowledge Graph Completion

Knowledge graph (KG) completion aims to fill the missing facts in a KG, ...
research
10/06/2021

Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representations

Learning good representations on multi-relational graphs is essential to...
research
05/10/2023

ACTC: Active Threshold Calibration for Cold-Start Knowledge Graph Completion

Self-supervised knowledge-graph completion (KGC) relies on estimating a ...
research
07/14/2022

Explainable Sparse Knowledge Graph Completion via High-order Graph Reasoning Network

Knowledge Graphs (KGs) are becoming increasingly essential infrastructur...
research
02/21/2022

Dynamic Relation Repairing for Knowledge Enhancement

Dynamic relation repair aims to efficiently validate and repair the inst...

Please sign up or login with your details

Forgot password? Click here to reset