On the Effectiveness of Knowledge Graph Embeddings: a Rule Mining Approach

2022/06/02 by Johanna Jøsang, Jøsang, Johanna, Ricardo José de Paula Souza e Guimarães +3
Computer Science · #Artificial Intelligence (cs.AI) #Data Mining Algorithms and Applications #FOS: Computer and information sciences #Machine Learning (cs.LG) #Rough Sets and Fuzzy Logic #Semantic Web and Ontologies

paper · pdf · doi:10.48550/arxiv.2206.00983

openalex publication_date 2022/06/02 · openalex created_date 2022/06/13 · openalex updated_date 2026/07/28

Abstract

We study the effectiveness of Knowledge Graph Embeddings (KGE) for knowledge graph (KG) completion with rule mining. More specifically, we mine rules from KGs before and after they have been completed by a KGE to compare possible differences in the rules extracted. We apply this method to classical KGEs approaches, in particular, TransE, DistMult and ComplEx. Our experiments indicate that there can be huge differences between the extracted rules, depending on the KGE approach for KG completion. In particular, after the TransE completion, several spurious rules were extracted.

Related

• A Hybrid Model for Learning Embeddings and Logical Rules Simultaneously from Knowledge Graphs
• RulE: Knowledge Graph Reasoning with Rule Embedding
• What is Learned in Knowledge Graph Embeddings?
• Knowledge Reasoning via Jointly Modeling Knowledge Graphs and Soft Rules
• A Comprehensive Study on Knowledge Graph Embedding over Relational Patterns Based on Rule Learning