ISSN 1000-1239 CN 11-1777/TP

计算机研究与发展 ›› 2018, Vol. 55 ›› Issue (8): 1773-1784.doi: 10.7544/issn1000-1239.2018.20180248

所属专题: 2018数据挖掘前沿进展专题

• 人工智能 • 上一篇    下一篇



  1. 1(电子科技大学信息与软件工程学院 成都 610054);2(中电科大数据研究院有限公司 贵阳 550008) (
  • 出版日期: 2018-08-01
  • 基金资助: 
    国家自然科学基金项目(61772117,61133016);装备预研领域基金项目(61403120102);四川省科技厅高新技术及产业化面上项目(2017GZ0308) This work was supported by the National Natural Science Foundation of China (61772117, 61133016), the General Equipment Department Foundation (61403120102), and the Sichuan Hi-Tech Industrialization Program (2017GZ0308).

Semantical Symbol Mapping Embedding Learning Algorithm for Knowledge Graph

Yang Xiaohui1,2, Wan Rui1, Zhang Haibin1, Zeng Yifu1,Liu Qiao1   

  1. 1(School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054);2(CETC Big Data Research Institute Co., Ltd., Guiyang 550008)
  • Online: 2018-08-01

摘要: 图的分布式表示对于知识图谱的构建与应用任务至关重要.通过对当前流行的图表示学习模型进行比较,分析了现有模型存在的不合理之处,据此提出了一个基于符号语义映射的神经网络模型用于学习图的分布式表示,基本思想是依据知识图谱中已有的实体关系数据,采用循环神经网络对符号组合(实体-关系组合)进行语义编码,并将其映射到目标符号(实体)上.此外,通过为图中的每个关系类型引入一个逆关系镜像,解决了关系的非对称性问题,使模型能够适应多种不同类型的(同构或异构)网络的关系推理任务.该模型适用于大规模知识图谱的表示学习任务.在公开数据集上的实验结果表明,该模型在知识图谱扩容任务和基于图的多标签分类任务上的性能表现优于相关工作.

关键词: 表示学习, 图嵌入学习, 推理, 链路预测, 多标签分类, 知识图谱

Abstract: Learning graph embedding is a crucial research issue in the field of statistical relational learning and knowledge graph population, and it is important for the construction and application of knowledge graph in recent years. In this paper, we perform a comparative study of the prevalent knowledge representation based reasoning models, with detailed discussion of the general potential problems contained in their basic assumptions. A semantical symbol sensory projection based neural network model is proposed in order to learn graph embedding, whose basic idea is to utilize the recurrent neural network for encoding the compositional representation of symbol strings (composition of entity-relation) onto their target grounded symbol according to the existing relational data in knowledge. In addition, we introduce the inverse image of the relations into the system to deal with the symmetricasymmetric properties of the relations, which makes the proposed model more adaptable to different types of reasoning tasks on a variety of homogeneous and heterogeneous networks than other solutions. The proposed model is suitable for large scale knowledge graph representation learning. Experimental results on benchmark datasets show that the proposed model achieves state-of-the-art performance on both of the knowledge based completion benchmark tests and the graph based multi-label classification tasks.

Key words: representation learning, graph embedding learning, reasoning, link prediction, multi-label classification, knowledge graphs