Predicting from a Different Perspective: A Re-ranking Model for Inductive Knowledge Graph Completion

TL;DR

This paper introduces ReDistLP, a re-ranking model that improves inductive knowledge graph completion by leveraging differences in initial and re-ranked predictions, outperforming existing methods on most benchmarks.

Contribution

The paper proposes ReDistLP, a novel re-ranking approach that enhances rule-induction models for inductive knowledge graph completion by utilizing prediction differences.

Findings

ReDistLP outperforms state-of-the-art methods on 2 out of 3 benchmarks.

The model effectively leverages prediction differences to improve accuracy.

ReDistLP enhances the effectiveness of rule-based inductive models.

Abstract

Rule-induction models have demonstrated great power in the inductive setting of knowledge graph completion. In this setting, the models are tested on a knowledge graph entirely composed of unseen entities. These models learn relation patterns as rules by utilizing subgraphs. Providing the same inputs with different rules leads to differences in the model's predictions. In this paper, we focus on the behavior of such models. We propose a re-ranking-based model called ReDistLP (Re-ranking with a Distinct Model for Link Prediction). This model enhances the effectiveness of re-ranking by leveraging the difference in the predictions between the initial retriever and the re-ranker. ReDistLP outperforms the state-of-the-art methods in 2 out of 3 benchmarks.