On the Effectiveness of Knowledge Graph Embeddings: a Rule Mining Approach
This work addresses the reliability of KGE methods for knowledge graph completion, which is important for researchers and practitioners in AI and data integration, but it is incremental as it builds on existing KGE techniques.
The study investigated the effectiveness of Knowledge Graph Embeddings (KGE) for knowledge graph completion by comparing rules mined from original and KGE-completed graphs, finding that different KGE approaches like TransE, DistMult, and ComplEx lead to significant differences in extracted rules, with TransE introducing spurious rules.
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.