Knowledge Graph Embedding with Entity Neighbors and Deep Memory Network

Abstract

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.

arXiv comment9 pages, 4 figures

References in corpus (6)

• Complex Embeddings for Simple Link Prediction
• Dynamic Memory Networks for Visual and Textual Question Answering
• Analogical Inference for Multi-Relational Embeddings
• DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning
• Traversing Knowledge Graphs in Vector Space
• Modeling Relation Paths for Representation Learning of Knowledge Bases

Cited by in corpus (3)

• Quaternion Knowledge Graph Embeddings
• Heterogeneous Network Representation Learning: A Unified Framework with Survey and Benchmark
• Embedding Heterogeneous Networks into Hyperbolic Space Without Meta-path