华南理工大学学报(自然科学版) >

2022 , Vol. 50 >Issue 12: 13 - 19

DOI: https://doi.org/10.12141/j.issn.1000-565X.220384

计算机科学与技术

基于交互式连接图注意力网络的知识图谱补全方法

  • 陆以勤 ,
  • 潘周双 ,
  • 张洋 ,
  • 覃健诚 ,
  • 黄方
展开
  • 1.华南理工大学 电子与信息学院，广东 广州 510640
    2.华南理工大学 计算机科学与工程学院，广东 广州 510006
陆以勤（1968-），男，教授，博士生导师，主要从事知识图谱、深度学习、网络安全研究。

收稿日期: 2022-06-17

  网络出版日期: 2022-08-12

基金资助

广东省重点领域研发计划项目(2019B010137001)

收起

Knowledge Graph Completion Method Based on Interactively Connected Graph Attention Network

  • Yiqin LU ,
  • Zhoushuang PAN ,
  • Yang ZHANG ,
  • Jiancheng QIN ,
  • Fang HUANG
Expand
  • 1.School of Electronic and Information Engineering，South China University of Technology，Guangzhou 510640，Guangdong，China
    2.School of Computer Science and Engineering，South China University of Technology，Guangzhou 510006，Guangdong，China
陆以勤（1968-），男，教授，博士生导师，主要从事知识图谱、深度学习、网络安全研究。

Received date: 2022-06-17

  Online published: 2022-08-12

Supported by

the Key-Area R&D Project of Guangdong Province(2019010137001)

Fold

摘要

知识图谱为许多智能信息服务应用提供了底层支持，包括智能搜索、公共安全、金融、医疗等领域，但现有的知识图谱通常是不完整的，知识图谱补全已经成为亟需解决的问题。现有的知识图谱补全方法忽略了邻居节点以及关系所富含的重要信息，往往只是简单地将邻居节点和关系拼接起来，忽略了不同关系和邻居节点对于节点有着不同的重要性。为此，文中提出了一种基于交互式连接图注意力网络的知识图谱补全方法（ICGAT）。该方法首先通过寻找两跳邻居节点，挖掘出潜在可能的关系，扩充每个节点的三元组；然后将每个三元组中的关系与节点的特征融合，并且采用节点与邻居节点交互式连接的方法，用4个空间向量来表示交互式连接的关系；最后将交互式连接的向量输入图注意力网络，得到关系和邻居节点对该节点的权重，以此说明其重要性。为了有效地表示一对多、多对多等复杂关系的三元组，该方法使用RotatE模型作为预训练模型。在链接预测任务中的实验结果表明，ICGAT方法在WN18RR和FB15k-237数据集中的平均排名（MR）和排名前10命中率（HR@10）均有一定的提升，说明ICGAT能够提高链接预测任务的准确性。

关键词： 知识图谱; 图注意力网络; 图神经网络; 交互式连接

本文引用格式

陆以勤 , 潘周双 , 张洋 , 覃健诚 , 黄方 . 基于交互式连接图注意力网络的知识图谱补全方法[J]. 华南理工大学学报(自然科学版), 2022 , 50(12) : 13 -19 . DOI: 10.12141/j.issn.1000-565X.220384

Abstract

Knowledge graph provides underlying support for many intelligent information service applications, including intelligent search, public safety, finance, medical care and other fields. However, the existing knowledge graph is usually incomplete, and knowledge graph completion has become an urgent problem to be solved. The existing knowledge graph completion method models ignore the important information rich in neighbor nodes and relationships, and often simply splice neighbor nodes and relationships together, ignoring the different importance of different relationships and neighbor nodes to nodes. To solve this problem, this paper proposed a knowledge graph completion method (ICGAT) based on the interactive connection graph attention network. The method firstly finds out the potential relationship by finding two-hop neighbor nodes, and expands the triples of each node. Then it fuses the relationship in each triplet with the features of the node, and adopts the method of interactive connection between nodes and neighbor nodes, using 4 space vectors to represent the interactively connected relationship. Finally, the vector of interactive connection was input into the graph attention network to obtain the weight of relations and neighbor nodes to the node, so as to illustrate its importance. In order to effectively represent triples of complex relationships such as one-to-many, many-to-many, etc., this method used the RotatE model as a pre-training model. The experimental results in the link prediction task show that the performance of the mean rank and HR@10indicators of the ICGAT method in the WN18RR and FB15k-237 datasets have been improved to a certain extent, indicating that ICGAT can improve the accuracy of the link prediction task.

Key words： knowledge graph; graph attention network; graph neural network; interactive connectivity

参考文献

1 LEHMANN J， ISELE R， JAKOB M，et al ．DBpedia：a large-scale，multilingual knowledge base extracted from Wikipedia ［J］．Semantic Web，2015，6（2）：167-195．
2 BOLLACKER K， EVANS C， PARITOSH P，et al ．Freebase：a collaboratively created graph database for structuring human knowledge ［C］∥ Proceedings of 2008 ACM SIGMOD International Conference on Management of Data．Vancouver：ACM，2008：1247-1250．
3 MILLER G A ．WordNet：a lexical database for English ［J］．Communications of the ACM，1995，38（11）：39-41．
4 QI T， WU F， WU C，et al ．Personalized news recommendation with knowledge-aware interactive matching ［C］∥ Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval．New York：ACM，2021：61-70．
5 HAO Y， ZHANG Y， LIU K，et al ．An end-to-end model for question answering over knowledge base with cross-attention combining global knowledge ［C］∥ Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics．Vancouver：ACL，2017：221-231．
6 王屹超，朱慕华，许晨，等 ．利用图像描述与知识图谱增强表示的视觉问答 ［J］．清华大学学报（自然科学版），2022，62（5）：900-907．
6 WANG Yichao， ZHU Muhua， XU Chen，et al ．Exploiting image captions and external knowledge as representation enhancement for VQA ［J］．Journal of Tsinghua University （Science and Technology），2022，62（5）：900-907．
7 GAVALI S， ROSS K， CHEN C，et al ．A knowledge graph representation learning approach to predict novel kinase-substrate interactions［EB/OL］．（2022-06-05） ［2022-06-10］．．
8 NGUYEN D Q ．A survey of embedding models of entities and relationships for knowledge graph completion ［EB/OL］． （2017-03-23）［2022-06-10］．．
9 BORDES A， USUNIER N， GARCIA-DURAN A，et al ．Translating embeddings for modeling multi-relational data ［M］∥ BURGES C J C，BOTTOU L，WELLING M，et al．Advances in neural information processing systems．Red Hook：Curran Associates Inc.，2013：2787-2795．
10 CHURCH K W ．Word2Vec ［J］．Natural Language Engineering，2017，23（1）：155-162．
11 WANG Z， ZHANG J， FENG J，et al ．Knowledge graph embedding by translating on hyperplanes ［C］∥Proceedings of the 28th AAAI Conference on Artificial Intelligence．Quebec：AAAI，2014：1112-1119．
12 LIN Y， LIU Z， SUN M，et al ．Learning entity and relation embeddings for knowledge graph completion ［C］∥ Proceedings of the 29th AAAI Conference on Artificial Intelligence．Austin：AAAI，2015：2181-2187．
13 SUN Z， DENG Z H， NIE J Y，et al ．RotatE：know-ledge graph embedding by relational rotation in complex space ［EB/OL］． （2019-02-26）［2022-06-10］．．
14 DEVLIN J， CHANG M W， LEE K，et al ．BERT：pre-training of deep bidirectional transformers for language understanding ［EB/OL］． （2018-10-11）［2022-06-10］．．
15 YAO L， MAO C， LUO Y ．KG-BERT：BERT for knowledge graph completion ［EB/OL］． （2019-09-07） ［2022-06-10］．．
16 WANG B， SHEN T， LONG G，et al ．Structure-augmented text representation learning for efficient knowledge graph completion ［C］∥ Proceedings of the 30th Web Conference．Ljubljana：ACM，2021：1737-1748．
17 WANG K， LIU Y， XU X，et al ．Enhancing knowledge graph embedding by composite neighbors for link prediction ［J］．Computing，2020，102（12）：2587-2606．
18 KIPF T N， WELLING M ．Semi-supervised classification with graph convolutional networks ［J］． （2016-09-09）［2022-06-10］．．
19 VELI?KOVI? P， CUCURULL G， CASANOVA A，et al ．Graph attention networks ［EB/OL］．（2017-10-30） ［2022-06-10］．．
20 ZHANG R， TRISEDYA B D， LI M，et al ．A benchmark and comprehensive survey on knowledge graph entity alignment via representation learning ［J］．VLDB Journal，2022，31（5）：1143-1168．
21 NATHANI D， CHAUHAN J， SHARMA C，et al ．Learning attention-based embeddings for relation prediction in knowledge graphs ［EB/OL］．（2019-06-04）［2022-06-10］．．
22 CHEN L， CUI J， TANG X，et al ．RMNA：a neighbor aggregation-based knowledge graph representation learning model using rule mining ［EB/OL］． （2021-11-01）［2022-06-10］．．
23 NGUYEN D Q， NGUYEN D Q， NGUYEN T D，et al ．A convolutional neural network-based model for know-ledge base completion and its application to search personalization ［J］．Semantic Web，2019，10（5）：947-960．
24 DETTMERS T， MINERVINI P， STENETORP P，et al ．Convolutional 2D knowledge graph embeddings ［C］∥ Proceedings of the 32nd AAAI Conference on Artificial Intelligence．New Orleans：AAAI，2018：1811-1818．
25 VASHISHTH S， SANYAL S， NITIN V，et al ．Inte-ractE：improving convolution-based knowledge graph embeddings by increasing feature interactions ［C］∥Proceedings of the 34th AAAI Conference on Artificial Intelligence．New York：AAAI，2020：3009-3016．
26 XIE Z， ZHOU G， LIU J，et al ．ReInceptionE：relation-aware inception network with joint local-global structural information for knowledge graph embedding ［C］∥ Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics．Seattle：ACL，2020：5929-5939．
27 ZHOU Z， WANG C， FENG Y，et al ．JointE：jointly utilizing 1D and 2D convolution for knowledge graph embedding ［J］．Knowledge-Based Systems，2022，240：108100/1-9．
28 FAN L J， SUN Y Y， XU F，et al ．Knowledge graph embedding based on semantic hierarchy ［J］．Cognitive Robotics，2022，2：147-154．
Options
文章导航

/

〈 〉


总访问量
今日访问
在线人数
粤ICP备05084312号
版权所有 © 华南理工大学期刊中心（学报编辑部）

地址：广州 五山 华南理工大学17号楼 邮政编码：510640

电话： 020-87111794 邮箱：journal@scut.edu.cn

  • 微信号：Journalscut
  • QQ群：699235083