Rot-Pro: Modeling Transitivity by Projection in Knowledge Graph Embedding
This work addresses a gap in knowledge graph embedding for AI applications, but it is incremental as it builds on existing methods to handle a specific relation pattern.
The paper tackled the problem of modeling transitive relations in knowledge graph embeddings, which existing models did not fully support, and proposed Rot-Pro, a model combining projection and relational rotation that achieved state-of-the-art results on link prediction in datasets with transitive relations.
Knowledge graph embedding models learn the representations of entities and relations in the knowledge graphs for predicting missing links (relations) between entities. Their effectiveness are deeply affected by the ability of modeling and inferring different relation patterns such as symmetry, asymmetry, inversion, composition and transitivity. Although existing models are already able to model many of these relations patterns, transitivity, a very common relation pattern, is still not been fully supported. In this paper, we first theoretically show that the transitive relations can be modeled with projections. We then propose the Rot-Pro model which combines the projection and relational rotation together. We prove that Rot-Pro can infer all the above relation patterns. Experimental results show that the proposed Rot-Pro model effectively learns the transitivity pattern and achieves the state-of-the-art results on the link prediction task in the datasets containing transitive relations.