Learning attention-based representations from multiple patterns for relation prediction in knowledge graphs

doi:10.1016/j.knosys.2022.109232

2022-09-01

Vítor Lourenço *

Aline Paes

DOI：10.1016/j.knosys.2022.109232

原文链接

查看原文

摘要

En 中文

Knowledge bases, and their representations in the form of knowledge graphs (KGs), are naturally incomplete. Since scientific and industrial applications have extensively adopted them, there is a high demand for solutions that complete their information. Several recent works tackle this challenge by learning embeddings for entities and relations, then employing them to predict new relations among the entities. Despite their aggrandizement, most of those methods focus only on the local neighbors of a relation to learn the embeddings. As a result, they may fail to capture the KGs' context information by neglecting long-term dependencies and the propagation of entities' semantics. In this manuscript, we propose /EMP (Attention-based Embeddings from Multiple Patterns), a novel model for learning contextualized representations by: (i) acquiring entities context information through an attention-enhanced message-passing scheme, which captures the entities local semantics while focusing on different aspects of their neighborhood; and (ii) capturing the semantic context, by leveraging the paths and their relationships between entities. Our empirical findings draw insights into how attention mechanisms can improve entities' context representation and how combining entities and semantic path contexts improves the general representation of entities and the relation predictions. Experimental results on several large and small knowledge graph benchmarks show that /EMP either outperforms or competes with state-of-the-art relation prediction methods. (c) 2022 Elsevier B.V. All rights reserved.

Keyword:

Knowledge graphs

Representation learning

Embeddings

Attention mechanism