In this paper, we propose a fine-grained relational learning framework IDEAL for few-shot knowledge graph completion task. Moreover, many of those models directly use the concatenation of the entity embeddings as the relation representations, and neglect the valuable interaction between relations. However, most of these models take the entity's neighbor relations and entities as the same hierarchy and do not make fine-grained distinctions, resulting in entity embeddings with low expressiveness, which may further decrease the quality of learned few-shot relation embeddings. Existing FKGC methods focus on the learning of few-shot relation representations, which are obtained by aggregating the neighbor information of each entity. Few-shot knowledge graph completion (FKGC) task aims to infer missing entities or relations by using few-shot support instances in the knowledge graph.
0 Comments
Leave a Reply. |