Exploring Hierachical Neighbor Information Interaction for Few-Shot Knowledge Graph Completion

Few-shot knowledge graph completion (FKGC) aims to use a few-shot reference entity pairs to infer unknown facts and complete triple information. Typically, existing methods solely learn entity embeddings from their respective neighborhoods, resulting in inadequately differentiated entity pair representations. And they only use the updated entities to represent the relations, which leads to relation overfitting. To address the issues, we propose a FKGC model based on hierarchical neighborhood information interaction (HNII). Specifically, the model first considers the interaction between head and tail entities. It obtains enhanced entity embedding representations from the task-relation-level and entity-pair-level by using a hierarchical neighborhood entity encoder. Then, a bi-directional LSTM relation encoder is introduced to output the relation embedding representations. Finally, an attention mixed matching processor is used to compute the semantic similarity. This is conducive to fully exploring the deep semantic information of entities and relations. Extensive related experiments on two public datasets show that HNII performs excellent in the task of FKGC.