MSGE: A Multi-step Gated Model for Knowledge Graph Completion.

Knowledge graph embedding models aim to represent entities and relations in continuous low-dimensional vector space, benefiting many research areas such as knowledge graph completion and web searching. However, previous works do not consider controlling information flow, which makes them hard to obtain useful latent information and limits model performance. Specifically, as human beings, predictions are usually made in multiple steps with every step filtering out irrelevant information and targeting at helpful information. In this paper, we first integrate iterative mechanism into knowledge graph embedding and propose a multi-step gated model which utilizes relations as queries to extract useful information from coarse to fine in multiple steps. First gate mechanism is adopted to control information flow by the interaction between entity and relation with multiple steps. Then we repeat the gate cell for several times to refine the information incrementally. Our model achieves state-of-the-art performance on most benchmark datasets compared to strong baselines. Further analyses demonstrate the effectiveness of our model and its scalability on large knowledge graphs.