Few-shot Link Prediction on N-ary Facts

TL;DR

This paper introduces the task of few-shot link prediction on hyper-relational facts in knowledge graphs, proposing a meta-learning model called MetaRH that effectively predicts missing entities with limited data, validated on newly constructed datasets.

Contribution

The paper defines a new few-shot link prediction task for hyper-relational facts and proposes MetaRH, a meta-learning model that captures relational information from limited support instances.

Findings

MetaRH outperforms existing models on three newly constructed datasets.

MetaRH effectively captures meta relational information from few support instances.

The new datasets validate the effectiveness of the proposed approach.

Abstract

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.