Context-Enhanced Entity and Relation Embedding for Knowledge Graph Completion
This work aims to improve knowledge graph completion for applications relying on structured knowledge, offering competitive performance against existing models.
This paper addresses the problem of incomplete knowledge graphs by learning context-enhanced embeddings for entities and relations. It proposes AggrE, a model that aggregates multi-hop contextual information from triplets to improve link prediction.
Most researches for knowledge graph completion learn representations of entities and relations to predict missing links in incomplete knowledge graphs. However, these methods fail to take full advantage of both the contextual information of entity and relation. Here, we extract contexts of entities and relations from the triplets which they compose. We propose a model named AggrE, which conducts efficient aggregations respectively on entity context and relation context in multi-hops, and learns context-enhanced entity and relation embeddings for knowledge graph completion. The experiment results show that AggrE is competitive to existing models.