Connecting Embeddings Based on Multiplex Relational Graph Attention Networks for Knowledge Graph Entity Typing

Knowledge graph entity typing (KGET) aims to infer missing entity typing instances in KGs, which is a significant subtask of KG completion. Despite of its progress, however, we observe that it still faces two non-trivial challenges: (i) most existing KGET methods extract features by encoding the existing entity typing tuples, while underutilizing or even ignoring rich relational knowledge. (ii) they typically treat each entity typing tuple in KGs independently, and thus inevitably fail to take account of the inherent and valuable neighborhood information surrounding a tuple. To address these challenges, we build a novel Heterogeneous Relational Graph (HRG), and propose a Multiplex Relational Graph Attention Networks (MRGAT) to learn on HRG, and then utilize a Connecting Embeddings model (ConnectE) to make entity type inference. Specifically, the overall framework contains three significant components. First, to effectively integrate the heterogeneous structural information including the entity typing tuples and entity relation triples in KGs, we construct a heterogeneous relational graph that consists of three semantic subgraphs. Second, we employ MRGAT to learn embeddings on HRG. In MRGAT, each subgraph of HRG is fed to its corresponding model that is capable of capturing neighborhood information by aggregating the surrounding nodes’ features. Finally, given the learned embeddings, we make entity type prediction by the connecting embeddings method ConnectE. Experimental results demonstrate the effectiveness of our proposed model against various state-of-the-art baselines.