Link Prediction on N-ary Relational Data Based on Relatedness Evaluation

TL;DR

This paper introduces NaLP, a novel method for link prediction on n-ary relational data in knowledge graphs, explicitly modeling role-relatedness and incorporating type constraints without external supervision.

Contribution

It proposes a new approach for n-ary relation link prediction that preserves structure and models relatedness, extending previous triple-based methods.

Findings

NaLP outperforms existing methods on n-ary relation datasets.

Explicit modeling of role relatedness improves prediction accuracy.

Type constraints and negative sampling enhance model robustness.

Abstract

With the overwhelming popularity of Knowledge Graphs (KGs), researchers have poured attention to link prediction to fill in missing facts for a long time. However, they mainly focus on link prediction on binary relational data, where facts are usually represented as triples in the form of (head entity, relation, tail entity). In practice, n-ary relational facts are also ubiquitous. When encountering such facts, existing studies usually decompose them into triples by introducing a multitude of auxiliary virtual entities and additional triples. These conversions result in the complexity of carrying out link prediction on n-ary relational data. It has even proven that they may cause loss of structure information. To overcome these problems, in this paper, we represent each n-ary relational fact as a set of its role and role-value pairs. We then propose a method called NaLP to conduct link prediction on n-ary relational data, which explicitly models the relatedness of all the role and role-value pairs in an n-ary relational fact. We further extend NaLP by introducing type constraints of roles and role-values without any external type-specific supervision, and proposing a more reasonable negative sampling mechanism. Experimental results validate the effectiveness and merits of the proposed methods.