Improved Knowledge Graph Completion Method for Capsule Network

doi:10.19678/j.issn.1000-3428.0055390

Abstract

Abstract: In order to complete the missing relations between entities of knowledge graph,this paper proposes an improved knowledge graph completion method for capsule network.First,the triplets are presented as a 3-column matrix,which is convolved with multiple filters to produce different feature maps.Secondly,these feature maps are reconstructed into corresponding capsules,each capsule composed of a group of neurons.The capsules with a lower dimension are produced through routing operation,and then a continuous vector is generated.Finally,the vector and the weight vector are subjected to a dot product operation to construct a ranking function to determine the correctness of the given triple.Experiments for link prediction and triplet classification are carried out on the public data sets including WN18RR,FB15K-237 and FB15K.The experimental results show that the proposed algorithm outperforms DistMult,ComplEx,ConvE and other models in link prediction.Also,it outperforms TransE,TransH,TransR and other models in triple classification,increasing the accuracy to 91.5%.

Key words: knowledge graph, capsule network, knowledge graph completion, link prediction, triad classification

摘要： 为准确表征知识图谱中实体与关系属性的关系，提出一种改进的胶囊网络知识图谱补全方法。将表示多关系数据的三元组转换为矩阵的形式与多个过滤器进行卷积，产生不同特征图并重构为相应的胶囊，每个胶囊代表一组神经元。在此基础上，通过路由操作产生维度较小的胶囊，生成连续向量并将其与权重向量做点积运算，构建评分函数用于判断三元组的正确性。采用公开数据集WN18RR、FB15K-237、FB15K分别进行链接预测和三元组分类实验，结果表明，与DistMult、ComplEx、ConvE等模型相比，该算法链接预测性能较优，与TransE、TransH、TransR等模型相比，其三元组分类准确率达到91.5%，具有显著优势。

关键词: 知识图谱, 胶囊网络, 知识图谱补全, 链接预测, 三元组分类

CLC Number:

TP18

WANG Weimei, SHI Yimin, LI Guanyu. Improved Knowledge Graph Completion Method for Capsule Network[J]. Computer Engineering, 2020, 46(8): 21-26.

王维美, 史一民, 李冠宇. 改进的胶囊网络知识图谱补全方法[J]. 计算机工程, 2020, 46(8): 21-26.

/ / Recommend / Download Citations

URL: http://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0055390

http://www.ecice06.com/EN/Y2020/V46/I8/21

Figures/Tables 7

References

[1] LIU Zhiyuan,SUN Maosong,LIN Yankai,et al.Knowledge representation learning:a review[J].Journal of Computer Research and Development,2016,53(2):247-261.(in Chinese)刘知远,孙茂松,林衍凯,等.知识表示学习研究进展[J].计算机研究与发展,2016,53(2):247-261.
[2] XIE Ruobing,LIU Zhiyuan,JIA Jia,et al.Representation learning of knowledge graphs with entity descriptions[C]//Proceedings of the 30th AAAI Conference on Artificial Intelligence.[S.l.]:AAAI Press,2016:1-7.
[3] DING Jianhui,JIA Weijia.The research advances of knowledge graph completion algorithm[J].Information and Communications Technologies,2018(1):56-62.(in Chinese)丁建辉,贾维嘉.知识图谱补全算法综述[J].信息通信技术,2018(1):56-62.
[4] ZHAI Sheping,GUO Lin,GAO Shan,et al.Method for knowledge graph completion based on Bayesian reasoning[J].Journal of Chinese Computer Systems,2018,39(5):995-999.(in Chinese)翟社平,郭琳,高山,等.一种采用贝叶斯推理的知识图谱补全方法[J].小型微型计算机系统,2018,39(5):995-999.
[5] SOCHER R,CHEN D,MANNING C D,et al.Reasoning with neural tensor networks for knowledge base completion[C]//Proceedings of NIPS'13.Cambridge,USA:MIT Press,2013:926-934.
[6] WEST R,GABRILOVICH E,MURPHY K,et al.Knowledge base completion via search-based question answering[C]//Proceedings of the 23rd International Conference on World Wide Web.New York,USA:ACM Press,2014:515-526.
[7] BORDES A,USUNIER N,GARCIA-DURAN A,et al.Translating embeddings for modeling multi-relational data[C]//Proceedings of NIPS'13.Cambridge,USA:MIT Press,2013:2787-2795.
[8] WANG Zhen,ZHANG Jianwen,FENG Jianlin,et al.Knowledge graph embedding by translating on hyperplanes[C]//Proceedings of the 28th AAAI Conference on Artificial Intelligence.Menlo Park,USA:AAAI,2014:1112-1119.
[9] LIN Yankai,LIU Zhiyuan,SUN Maosong,et al.Learning entity and relation embeddings for knowledge graph completion[C]//Proceedings of the 29th AAAI Conference on Artificial Intelligence.Austin,USA:AAAI,2015:2181-2187.
[10] YANG B,YIH W,HE X,et al.Embedding entities and relations for learning and inference in knowledge bases[EB/OL].[2019-05-10].https://arxiv.org/pdf/1412.6575.pdf.
[11] TROUILLON T,WELBL J,RIEDEL S,et al.Complex embeddings for simple link prediction[C]//Proceedings of the 33rd International Conference on International Conference on Machine Learning.New York,USA:ACM Press,2016:2071-2080.
[12] NGUYEN D Q,VU T,NGUYEN T D,et al.A capsule network-based embedding model for knowledge graph completion and search personalization[C]//Proceedings of NAACL'19.New Orleans,USA:Association for Computational Linguistics,2019:2180-2189.
[13] NGUYEN D Q,NGUYEN T D,NGUYEN D Q,et al.A novel embedding model for knowledge base completion based on convolutional neural network[C]//Proceedings of NAACL'18.New Orleans,USA:Association for Computational Linguistics,2018:327-333.
[14] SABOUR S,FROSST N,HINTON G E.Dynamic routing between capsules[C]//Proceedings of NIPS'17.Cambridge,USA:MIT Press,2017:3856-3866.
[15] LIN Hailun,WANG Yuanzhuo,JIA Yantao,et al.Network big data oriented knowledge fusion methods:a survey[J].Chinese Journal of Computers,2017,40(1):3-29.(in Chinese)林海伦,王元卓,贾岩涛,等.面向网络大数据的知识融合方法综述[J].计算机学报,2017,40(1):3-29.
[16] GUAN Saiping,JIN Xiaolong,JIA Yantao,et al.Knowledge reasoning over knowledge graph:a survey[J].Journal of Software,2018,29(10):2966-2994.(in Chinese). 官赛萍,靳小龙,贾岩涛,等.面向知识图谱的知识推理研究进展[J].软件学报,2018,29(10):2966-2994.
[17] JI Guoliang,HE Shizhu,XU Liheng,et al.Knowledge graph embedding via dynamic mapping matrix[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing.New Orleans,USA:Association for Computational Linguistics,2015:687-696.
[18] DETTMERS T,MINERVINI P,STENETORP P,et al.Convolutional 2D knowledge graph embeddings[C]//Proceedings of the 32nd AAAI Conference.Austin,USA:AAAI,2018:1811-1818.
[19] KINGMA D,BA J.Adam:a method for stochastic optimization[C]//Proceedings of International Conference on Learning Representations.San Diego,USA:[s.n.],2015:1-15.
[20] TOUTANOVA K,CHEN D.Observed versus latent features for knowledge base and text inference[C]//Proceedings of the 3rd Workshop on Continuous Vector Space Models and their Compositionality.Beijing,China:[s.n.],2015:57-66.

Please choose a citation manager

Content to export