Computer Science

Computer Science ›› 2021, Vol. 48 ›› Issue (5): 225-231.doi: 10.11896/jsjkx.200300093

• Artificial Intelligence • Previous Articles     Next Articles

Knowledge Graph Completion Model Using Quaternion as Relational Rotation

CHEN Heng1,2, WANG Wei-mei1, LI Guan-yu1, SHI Yi-ming1   

  1. 1 Faculty of Information Science & Technology,Dalian Maritime University,Dalian,Liaoning 116026,China
    2 Research Center for Language Intelligence,Dalian University of Foreign Languages,Dalian,Liaoning 116044,China
  • Received:2020-03-16 Revised:2020-07-08 Online:2021-05-15 Published:2021-05-09
  • About author:CHEN Heng,born in 1982,Ph.D,asso-ciate professor.His main research in-terests include intelligent information processing and so on.(chenheng@dlufl.edu.cn)
    LI Guan-yu,born in 1963,Ph.D,professor.His main research interests include intelligent information processing and so on.
  • Supported by:
    National Natural Science Foundation of China(61976032,61806038,61602076,61702072),Basic Scientific Research Projects of Liaoning University(2017JYT09) and Research and Innovation Team of Dalian University of Foreign Languages(2016CXTD06).

PDF (PC)

999

Abstract: Knowledge graph is a structured representation of real-world triples.Typically,triples are represented in the form of head entity,relationship entity and tail entity.Aiming at the data sparse problem widely existing in knowledge graph,this paper proposes a knowledge graph completion method using quaternions as relational rotation.In this paper,we model entities and relations in the expressive hyper-complex representations for link prediction.This hyper-complex embedding is used to represent entities,and relations are modelled as rotations in quaternion space.Specifically,we define each relation as a rotation from the head entity to the tail entity in the hyper-complex space,which could be used to infer and model diverse relation patterns,including symmetry/anti-symmetry,reversal and combination.In the experiment,the public datasets WN18RR and FB15K-237 are used for the related link prediction experiment.Experimental results show that on the WN18RR dataset,its mean reciprocal rank (MRR) is 4.6% higher than RotatE,and its Hit@10 is 1.7% higher than RotatE.On the FB15K-237 dataset,its MRR is 5.6% higher than RotatE,its Hit@3 is 1.4% higher than RotatE.Experiments show that the knowledge graph completion method using quaternions as relational rotation can effectively improve the prediction accuracy of triples.

Key words: Hyper-complex representation, Knowledge graph, Knowledge graph completion, Link prediction, Quaternion

CLC Number: 

  • TP181
[1]SUCHANEK F M,KASNECI G,WEIKUM G.Yago:a core of semantic knowledge[C]//Proceedings of the 16th International Conference on World Wide Web.2007:697-706.
[2]BOLLACKER K,EVANS C,PARITOSH P,et al.Freebase:acollaboratively created graph database for structuring human knowledge[C]//Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data.2008:1247-1250.
[3]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.
[4]ZHANG F,YUAN N J,LIAN D,et al.Collaborative knowledge base embedding for recommender systems[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2016:353-362.
[5]HAO Y,ZHANG Y,LIU K,et al.An end-to-end model forquestion answering over knowledge base with cross-attention combining global knowledge[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1:Long Papers).2017:221-231.
[6]XIONG C,POWER R,CALLAN J.Explicit semantic rankingfor academic search via knowledge graph embedding[C]//Proceedings of the 26th International Conference on World Wide Web.2017:1271-1279.
[7]YANG B,MITCHELL T.Leveraging knowledge bases in lstms for improving machine reading[J].arXiv:1902.09091,2019.
[8]WANG W M,SHI Y M,LI G Y.Improved capsule networkknowledge graph completion method[J/OL].Computer Engineering:1-7.[2020-03-13].https://doi.org/10.19678/j.issn.1000-3428.0055 390.
[9]LI Z X,REN S Y,WANG H M,et al.Knowledge inference method based on unstructured text enhanced association rules[J].Computer Science,2019,46(11):209-215.
[10]SOCHER R,CHEN D,MANNING C D,et al.Reasoning with neural tensor networks for knowledge base completion[C]//Advances in Neural Information Processing Systems.2013:926-934.
[11]WEST R,GABRILOVICH E,MURPHYK,et al.Knowledgebase completion via search-based question answering[C]//Proceedings of the 23rd International Conference on World Wide Web.ACM,2014:515-526.
[12]BORDES A,USUNIER N,GARCIA-DURAN A,et al.Translating embeddings for modeling multi-relational data[C]//Processings of the NIPS.Cambridge,MA:MIT Press,2013:2787-2795.
[13]WANG Z,ZHANG J,FENG J,et al.Knowledge graph embedding by translating on hyperplanes[C]//Processings of the AAAI.Menlo Park,CA:AAAI,2014:1112-1119.
[14]LIN Y,LIU Z,SUN M,et al.Learning entity and relation embeddings for knowledge graph completion[C]//Processings of the AAAI.Menlo Park,CA:AAAI,2014:2181-2187.
[15]WANG Q,MAO Z,WANG B,et al.Knowledge graph embedding:A survey of approaches and applications[J].IEEE Transactions on Knowledge and Data Engineering,2017,29(12):2724-2743.
[16]SUN Z,DENG Z H,NIE J Y,et al.Rotate:Knowledge graph embedding by relational rotation in complex space[J].arXiv:1902.10197,2019.
[17]BORDES A,WESTON J,COLLOBERT R,et al.Learningstructured embeddings of knowledge bases[C]//National Conference on Artificial Intelligence.2011:301-306.
[18]MBORDES A,GLOROT X,WESTON J,et al.A semanticmatching energy function for learning with multi-relational data[J].Neural Information Processing Systems,2014,94(2):233-259.
[19]MIKOLOV T,SUTSKEVER I,CHEN K,et al.Distributed representations of words and phrases and their compositionality[C]//Advances in Neural Information Processing Systems.2013:3111-3119.
[20]JI G,HE S,XU L,et al.Knowledge graph embedding via dynamic mapping matrix[C]//Processings of the ACL.Stroudsburg,PA:ACL,2015:687-696.
[21]YANG B,YIH W,HE X,et al.Embedding entities and rela-tions for learning and inference in knowledge bases[J].arXiv:1412.6575,2014.
[22]TROUILLON T,WELBL J,RIEDEL S,et al.Complex embeddings for simple link prediction[C]//International Conference on Machine Learning.2016:2071-2080.
[23]ZHANG S,TAY Y,YAO L,et al.Quaternion knowledge graph embeddings[C]//Advances in Neural Information Processing Systems.2019:2735-2745.
[24]LIN H L,WANG Y Z,JIAY T,et al.Overview of knowledge fusion methods for network big data [J].Journal of Computer,2017,40(1):1-27.
[25]GUAN S P,JIN X L,JIA Y T,et al.Research progress ofknowledge reasoning for knowledge graph [J].Journal of Software,2018,29(10):2966-2994.
[26]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.2015:57-66.
[27]DETTMERS T,MINERVINI P,STENETORP P,et al.Convolutional 2D knowledge graph embeddings[C]//Processings of the AAAI.2018:1811-1818.
[28]KINGMA D P,BA J.Adam:A method for stochastic optimization[J].arXiv:1412.6980,2014.
[29]NICKEL M,ROSASCO L,POGGIO T A.Holographic embeddings of knowledge graphs[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2016:1955-1961.
[30]KADLEC R,BAJGAR O,KLEINDIENST J.Knowledge base completion:Baselines strike back[J].arXiv:1705.10744,2017.
[31]NGUYEN D Q,NGUYEN T D,NGUYEN D Q,et al.A novel embedding model for knowledge base completion based on convolutional neural network[J].arXiv:1712.02121,2017.
[1] SONG Jie, LIANG Mei-yu, XUE Zhe, DU Jun-ping, KOU Fei-fei. Scientific Paper Heterogeneous Graph Node Representation Learning Method Based onUnsupervised Clustering Level [J]. Computer Science, 2022, 49(9): 64-69.
[2] HUANG Li, ZHU Yan, LI Chun-ping. Author’s Academic Behavior Prediction Based on Heterogeneous Network Representation Learning [J]. Computer Science, 2022, 49(9): 76-82.
[3] XU Yong-xin, ZHAO Jun-feng, WANG Ya-sha, XIE Bing, YANG Kai. Temporal Knowledge Graph Representation Learning [J]. Computer Science, 2022, 49(9): 162-171.
[4] RAO Zhi-shuang, JIA Zhen, ZHANG Fan, LI Tian-rui. Key-Value Relational Memory Networks for Question Answering over Knowledge Graph [J]. Computer Science, 2022, 49(9): 202-207.
[5] WU Zi-yi, LI Shao-mei, JIANG Meng-han, ZHANG Jian-peng. Ontology Alignment Method Based on Self-attention [J]. Computer Science, 2022, 49(9): 215-220.
[6] KONG Shi-ming, FENG Yong, ZHANG Jia-yun. Multi-level Inheritance Influence Calculation and Generalization Based on Knowledge Graph [J]. Computer Science, 2022, 49(9): 221-227.
[7] QIN Qi-qi, ZHANG Yue-qin, WANG Run-ze, ZHANG Ze-hua. Hierarchical Granulation Recommendation Method Based on Knowledge Graph [J]. Computer Science, 2022, 49(8): 64-69.
[8] WANG Jie, LI Xiao-nan, LI Guan-yu. Adaptive Attention-based Knowledge Graph Completion [J]. Computer Science, 2022, 49(7): 204-211.
[9] MA Rui-xin, LI Ze-yang, CHEN Zhi-kui, ZHAO Liang. Review of Reasoning on Knowledge Graph [J]. Computer Science, 2022, 49(6A): 74-85.
[10] DENG Kai, YANG Pin, LI Yi-zhou, YANG Xing, ZENG Fan-rui, ZHANG Zhen-yu. Fast and Transmissible Domain Knowledge Graph Construction Method [J]. Computer Science, 2022, 49(6A): 100-108.
[11] DU Xiao-ming, YUAN Qing-bo, YANG Fan, YAO Yi, JIANG Xiang. Construction of Named Entity Recognition Corpus in Field of Military Command and Control Support [J]. Computer Science, 2022, 49(6A): 133-139.
[12] XIONG Zhong-min, SHU Gui-wen, GUO Huai-yu. Graph Neural Network Recommendation Model Integrating User Preferences [J]. Computer Science, 2022, 49(6): 165-171.
[13] ZHONG Jiang, YIN Hong, ZHANG Jian. Academic Knowledge Graph-based Research for Auxiliary Innovation Technology [J]. Computer Science, 2022, 49(5): 194-199.
[14] LI Yong, WU Jing-peng, ZHANG Zhong-ying, ZHANG Qiang. Link Prediction for Node Featureless Networks Based on Faster Attention Mechanism [J]. Computer Science, 2022, 49(4): 43-48.
[15] LIANG Jing-ru, E Hai-hong, Song Mei-na. Method of Domain Knowledge Graph Construction Based on Property Graph Model [J]. Computer Science, 2022, 49(2): 174-181.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
Add:18# Honghu West Rd., Yubei ,Chongqing,China    Post Code: 401121
Tel: 023-63500828/023-67039612/023-67039623
E-mail: jsjkx12@163.com
Powered by Beijing Magtech Co., Ltd.