A Comprehensive Study on Knowledge Graph Embedding over Relational Patterns Based on Rule Learning

TL;DR

This paper provides a comprehensive quantitative analysis of how different relational patterns affect the performance of various knowledge graph embedding models, and introduces a training-free method to improve their pattern-specific performance.

Contribution

It offers the first extensive evaluation of KGE models over relational patterns and proposes SPA, a simple method to enhance pattern-specific performance without retraining.

Findings

KGE models' performance varies across relational patterns.

Entity frequency and pattern analysis reveal counterintuitive insights.

SPA improves KGE performance over specific patterns without additional training.

Abstract

Knowledge Graph Embedding (KGE) has proven to be an effective approach to solving the Knowledge Graph Completion (KGC) task. Relational patterns which refer to relations with specific semantics exhibiting graph patterns are an important factor in the performance of KGE models. Though KGE models' capabilities are analyzed over different relational patterns in theory and a rough connection between better relational patterns modeling and better performance of KGC has been built, a comprehensive quantitative analysis on KGE models over relational patterns remains absent so it is uncertain how the theoretical support of KGE to a relational pattern contributes to the performance of triples associated to such a relational pattern. To address this challenge, we evaluate the performance of 7 KGE models over 4 common relational patterns on 2 benchmarks, then conduct an analysis in theory, entity frequency, and part-to-whole three aspects and get some counterintuitive conclusions. Finally, we introduce a training-free method Score-based Patterns Adaptation (SPA) to enhance KGE models' performance over various relational patterns. This approach is simple yet effective and can be applied to KGE models without additional training. Our experimental results demonstrate that our method generally enhances performance over specific relational patterns. Our source code is available from GitHub at https://github.com/zjukg/Comprehensive-Study-over-Relational-Patterns.