arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.07200cs.LGcs.AI
收藏

基于注意力感知的图卷积网络的知识图谱嵌入

Knowledge Graph Embedding using Graph Convolutional Networks with Relation-Aware Attention

IBM Research - Almaden(IBM阿尔马登研究中心);IBM Research - Zurich(IBM苏黎世研究中心)

Nasrullah Sheikh, Xiao Qin, Berthold Reinwald, Christoph Miksovic, Thomas Gschwind, Paolo Scotton

摘要:

知识图谱嵌入方法学习低维空间中的实体和关系的嵌入,其可用于各种下游机器学习任务,诸如链接预测和实体匹配。已经提出了各种图卷积网络方法,其使用不同类型的信息来学习实体和关系的特征。然而,这些方法在聚合信息时为邻居分配相同的权重(重要性),忽略了与邻居实体的不同关系的作用。为此,我们提出了一个关系感知的图注意力模型,利用关系信息来计算不同的权重到相邻节点学习嵌入的实体和关系。我们评估我们提出的方法上的链接预测和实体匹配任务。我们在三个数据集(一个专有数据集和两个公共数据集)上的链接预测实验结果和在一个专有数据集上的无监督实体匹配实验结果证明了关系感知注意的有效性。

英文摘要:

Knowledge graph embedding methods learn embeddings of entities and relations in a low dimensional space which can be used for various downstream machine learning tasks such as link prediction and entity matching. Various graph convolutional network methods have been proposed which use different types of information to learn the features of entities and relations. However, these methods assign the same weight (importance) to the neighbors when aggregating the information, ignoring the role of different relations with the neighboring entities. To this end, we propose a relation-aware graph attention model that leverages relation information to compute different weights to the neighboring nodes for learning embeddings of entities and relations. We evaluate our proposed approach on link prediction and entity matching tasks. Our experimental results on link prediction on three datasets (one proprietary and two public) and results on unsupervised entity matching on one proprietary dataset demonstrate the effectiveness of the relation-aware attention.

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。

↑