Few-shot Link Prediction on N-ary Facts

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wei, Jiyao, Guan, Saiping, Jin, Xiaolong, Guo, Jiafeng, Cheng, Xueqi
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929299741736960
author Wei, Jiyao
Guan, Saiping
Jin, Xiaolong
Guo, Jiafeng
Cheng, Xueqi
author_facet Wei, Jiyao
Guan, Saiping
Jin, Xiaolong
Guo, Jiafeng
Cheng, Xueqi
contents Hyper-relational facts, which consist of a primary triple (head entity, relation, tail entity) and auxiliary attribute-value pairs, are widely present in real-world Knowledge Graphs (KGs). Link Prediction on Hyper-relational Facts (LPHFs) is to predict a missing element in a hyper-relational fact, which helps populate and enrich KGs. However, existing LPHFs studies usually require an amount of high-quality data. They overlook few-shot relations, which have limited instances, yet are common in real-world scenarios. Thus, we introduce a new task, Few-Shot Link Prediction on Hyper-relational Facts (FSLPHFs). It aims to predict a missing entity in a hyper-relational fact with limited support instances. To tackle FSLPHFs, we propose MetaRH, a model that learns Meta Relational information in Hyper-relational facts. MetaRH comprises three modules: relation learning, support-specific adjustment, and query inference. By capturing meta relational information from limited support instances, MetaRH can accurately predict the missing entity in a query. As there is no existing dataset available for this new task, we construct three datasets to validate the effectiveness of MetaRH. Experimental results on these datasets demonstrate that MetaRH significantly outperforms existing representative models.
format Preprint
id arxiv_https___arxiv_org_abs_2305_06104
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Few-shot Link Prediction on N-ary Facts
Wei, Jiyao
Guan, Saiping
Jin, Xiaolong
Guo, Jiafeng
Cheng, Xueqi
Artificial Intelligence
Information Retrieval
Machine Learning
Hyper-relational facts, which consist of a primary triple (head entity, relation, tail entity) and auxiliary attribute-value pairs, are widely present in real-world Knowledge Graphs (KGs). Link Prediction on Hyper-relational Facts (LPHFs) is to predict a missing element in a hyper-relational fact, which helps populate and enrich KGs. However, existing LPHFs studies usually require an amount of high-quality data. They overlook few-shot relations, which have limited instances, yet are common in real-world scenarios. Thus, we introduce a new task, Few-Shot Link Prediction on Hyper-relational Facts (FSLPHFs). It aims to predict a missing entity in a hyper-relational fact with limited support instances. To tackle FSLPHFs, we propose MetaRH, a model that learns Meta Relational information in Hyper-relational facts. MetaRH comprises three modules: relation learning, support-specific adjustment, and query inference. By capturing meta relational information from limited support instances, MetaRH can accurately predict the missing entity in a query. As there is no existing dataset available for this new task, we construct three datasets to validate the effectiveness of MetaRH. Experimental results on these datasets demonstrate that MetaRH significantly outperforms existing representative models.
title Few-shot Link Prediction on N-ary Facts
topic Artificial Intelligence
Information Retrieval
Machine Learning
url https://arxiv.org/abs/2305.06104