Improved Knowledge Graph Embedding using Background Taxonomic Information
This work addresses the challenge of improving knowledge graph completion for domains with taxonomic structures, though it appears incremental as it builds on existing methods.
The paper tackled the problem of incorporating background taxonomic information into knowledge graph embedding models, showing that existing universal models cannot provably respect such information. By making minimal modifications to an existing method, they achieved surprising effectiveness in experiments on public knowledge graphs.
Knowledge graphs are used to represent relational information in terms of triples. To enable learning about domains, embedding models, such as tensor factorization models, can be used to make predictions of new triples. Often there is background taxonomic information (in terms of subclasses and subproperties) that should also be taken into account. We show that existing fully expressive (a.k.a. universal) models cannot provably respect subclass and subproperty information. We show that minimal modifications to an existing knowledge graph completion method enables injection of taxonomic information. Moreover, we prove that our model is fully expressive, assuming a lower-bound on the size of the embeddings. Experimental results on public knowledge graphs show that despite its simplicity our approach is surprisingly effective.