Simple Rule Injection for ComplEx Embeddings
This work addresses the challenge of incorporating prior knowledge into knowledge graph embeddings for researchers in AI and knowledge representation, though it appears incremental as it builds on existing neural knowledge graph inference methods.
The authors tackled the problem of combining logic rules with knowledge graph embeddings by proposing InjEx, a mechanism to inject multiple types of rules through simple constraints, which improved performance in knowledge graph completion and few-shot knowledge graph completion settings.
Recent works in neural knowledge graph inference attempt to combine logic rules with knowledge graph embeddings to benefit from prior knowledge. However, they usually cannot avoid rule grounding, and injecting a diverse set of rules has still not been thoroughly explored. In this work, we propose InjEx, a mechanism to inject multiple types of rules through simple constraints, which capture definite Horn rules. To start, we theoretically prove that InjEx can inject such rules. Next, to demonstrate that InjEx infuses interpretable prior knowledge into the embedding space, we evaluate InjEx on both the knowledge graph completion (KGC) and few-shot knowledge graph completion (FKGC) settings. Our experimental results reveal that InjEx outperforms both baseline KGC models as well as specialized few-shot models while maintaining its scalability and efficiency.