arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2002.02406cs.AIcs.CLcs.LG
收藏

消息传递查询嵌入

Message Passing Query Embedding

Vrije Universiteit Amsterdam(阿姆斯特丹自由大学);University of Amsterdam(阿姆斯特丹大学);Elsevier(爱思唯尔)

Daniel Daza, Michael Cochez

摘要:

知识图谱的表示学习的最新工作已经超越了链接预测的问题,以回答任意结构的查询。现有的方法是基于ad-hoc机制,需要训练与一组不同的查询结构。我们提出了一个更通用的架构,采用图神经网络编码的查询,其中节点对应于实体和变量的图形表示。我们的方法的一般性允许它编码一个更多样化的查询类型集相比,以前的工作。我们的方法表现出竞争力的性能对以前的模型,复杂的查询,并与这些模型相比,它可以回答复杂的查询时,训练链接预测。我们表明,该模型学习实体嵌入,捕捉实体类型的概念,而无需明确的监督。

英文摘要:

Recent works on representation learning for Knowledge Graphs have moved beyond the problem of link prediction, to answering queries of an arbitrary structure. Existing methods are based on ad-hoc mechanisms that require training with a diverse set of query structures. We propose a more general architecture that employs a graph neural network to encode a graph representation of the query, where nodes correspond to entities and variables. The generality of our method allows it to encode a more diverse set of query types in comparison to previous work. Our method shows competitive performance against previous models for complex queries, and in contrast with these models, it can answer complex queries when trained for link prediction only. We show that the model learns entity embeddings that capture the notion of entity type without explicit supervision.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑