A Comprehensive Study on Knowledge Graph Embedding over Relational Patterns Based on Rule Learning
This work addresses a gap in understanding how theoretical support for relational patterns affects Knowledge Graph Completion performance, providing insights for researchers in knowledge representation and graph learning, though it is incremental in nature.
The paper tackles the lack of comprehensive quantitative analysis on Knowledge Graph Embedding (KGE) models over relational patterns by evaluating 7 models on 4 patterns across 2 benchmarks, and introduces a training-free method, Score-based Patterns Adaptation (SPA), which enhances performance over specific relational patterns.
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.