Knowledge Graph Embedding with Entity Neighbors and Deep Memory Network
This addresses noise issues in knowledge graph completion for AI applications, representing an incremental improvement over existing methods.
The paper tackles the problem of noise in additional information for Knowledge Graph Embedding by proposing entity neighbors as a new type of information and developing a deep memory network with a gating mechanism to integrate it, achieving state-of-the-art metrics on 4 datasets.
Knowledge Graph Embedding (KGE) aims to represent entities and relations of knowledge graph in a low-dimensional continuous vector space. Recent works focus on incorporating structural knowledge with additional information, such as entity descriptions, relation paths and so on. However, common used additional information usually contains plenty of noise, which makes it hard to learn valuable representation. In this paper, we propose a new kind of additional information, called entity neighbors, which contain both semantic and topological features about given entity. We then develop a deep memory network model to encode information from neighbors. Employing a gating mechanism, representations of structure and neighbors are integrated into a joint representation. The experimental results show that our model outperforms existing KGE methods utilizing entity descriptions and achieves state-of-the-art metrics on 4 datasets.