An inductive KG embedding method for OOKG entity type inference and fusion based on neighborhood structure

Puntos clave

• Entity type inference improves significantly using the inductive knowledge graph embedding.
• Key evidence shows enhanced fusion accuracy, observing a 30% increase compared to traditional methods.
• Observational analysis across various datasets highlights the neighbor structure's role in embedding effectiveness.
• Implications suggest potential for better data integration, though further validation is needed.