计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (1): 310-315.doi: 10.11896/jsjkx.230300006

• 人工智能 • 上一篇    下一篇

基于生成式对抗网络和正类无标签学习的知识图谱补全算法

胡斌皓1,2, 张建朋2, 陈鸿昶2   

  1. 1 郑州大学网络空间安全学院 郑州450002
    2 信息工程大学信息技术研究所国家数字交换系统工程技术研究中心 郑州450002
  • 收稿日期:2023-03-01 修回日期:2023-06-13 出版日期:2024-01-15 发布日期:2024-01-12
  • 通讯作者: 张建朋(j_zhang_edu@sina.com)
  • 作者简介:(hu15181620732@163.com)
  • 基金资助:
    国家自然科学基金(62002384);嵩山实验室项目(221100210700-3)

Knowledge Graph Completion Algorithm Based on Generative Adversarial Network and Positiveand Unlabeled Learning

HU Binhao1,2, ZHANG Jianpeng2, CHEN Hongchang2   

  1. 1 School of Cyber Science and Engineering,Zhengzhou University,Zhengzhou 450002,China
    2 National Digital Switching System Engineering & Technological R&D Center(NDSC),Institute of Information Technology,University of Information Engineering,Zhengzhou 450002,China
  • Received:2023-03-01 Revised:2023-06-13 Online:2024-01-15 Published:2024-01-12
  • About author:HU Binhao,born in 1996,postgraduate.His main research interests include graph representation,knowledge graph and natural language processing.
    ZHANG Jianpeng,born in 1988,Ph.D,assistant researcher.His main research interest is big data analysis.
  • Supported by:
    National Natural Science Foundation of China(62002384) and Song Shan Laboratory(221100210700-3).

PDF (PC)

1386

摘要： 随着知识图谱的应用越来越广泛,绝大多数真实世界的知识图谱通常具有不完备性,限制了知识图谱的实际应用效果。因此,知识图谱补全成为了知识图谱领域的热点。然而,现有方法大多集中在评分函数的设计上,少部分研究关注了负样本抽样策略。在改善负样本抽样的知识图谱补全算法的研究中,基于生成式对抗网络的方法取得了不错的进展。然而,现有研究并没有关注到负样本存在假阴性标签的问题,即生成的负样本中可能包含真实的事实。为了缓解假阴性标签问题,提出了一种基于生成式对抗网络和正类无标签学习的知识图谱补全算法。该方法利用生成式对抗网络生成无标签样本,并使用正类无标签学习缓解假阴性标签问题。在基准数据集上进行的大量实验证明了所提算法的有效性与准确性。

关键词: 知识图谱补全, 生成式对抗网络, 正类无标签学习, 负样本抽样

Abstract: With the widespread application of knowledge graphs,the majority of real-world knowledge graphs suffer from the problem of incompleteness,which hinders their practical applications.As a result,it makes knowledge graph completion become a hot topic in the field of knowledge graph.However,most existing methods focus on the design of scoring functions,with only a few studies paying attention to negative sampling strategies.In the research of knowledge graph completion algorithms which aims at improving negative sampling,the methods based on generative adversarial networks(GANs) have achieved significant progress.Nonetheless,existing studies have not addressed the false negative issue,meaning that generated negative samples may contain actual facts.To address this issue,this paper proposes a knowledge graph completion algorithm based on GAN and positive-unlabeled learning.In the proposed method,GANs are utilized to generate unlabeled samples,while positive unlabeled lear-ning is employed to alleviate the false negative problem.Extensive experiments on benchmark datasets demonstrate the effectiveness and accuracy of the proposed algorithm.

Key words: Knowledge graph completion, Generative adversarial network, Positive unlabeled learning, Negative sampling

中图分类号: 

  • TP391.1
[1]KROMPASS D,BAIER S,TRESP V.Type-Constrained Representation Learning in Knowledge Graphs[C]//The Semantic Web (ISWC 2015).Cham:Springer International Publishing,2015:640-655.
[2]NICKEL M,TRESP V,KRIEGEL H P.A three-way model for collective learning on multi-relational data[C]//Proceedings of the 28th International Conference on International Conference on Machine Learning.Madison,WI,USA:Omnipress,2011:809-816.
[3]BORDES A,USUNIER N,GARCIA-DURÁN A,et al.Translating embeddings for modeling multi-relational data[C]//Proceedings of the 26th International Conference on Neural Information Processing Systems-Volume 2.Red Hook,NY,USA:Curran Associates Inc.,2013:2787-2795.
[4]TROUILLON T,WELBL J,RIEDEL S,et al.Complex Embeddings for Simple Link Prediction[C]//Proceedings of The 33rd International Conference on Machine Learning.PMLR,2016:2071-2080.
[5]DETTMERS T,MINERVINI P,STENETORP P,et al.Convolutional 2D Knowledge Graph Embeddings[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2018.
[6]SUN Z,DENG Z H,NIE J Y,et al.RotatE:Knowledge Graph Embedding by Relational Rotation in Complex Space[C]//7th International Conference on Learning Representations(ICLR 2019).New Orleans,LA,USA:OpenReview.net,2019.
[7]CHAMI I,WOLF A,JUAN D C,et al.Low-Dimensional Hyperbolic Knowledge Graph Embeddings[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.Association for Computational Linguistics,2020:6901-6914.
[8]YAO L,MAO C,LUO Y.KG-BERT:BERT for knowledgegraph completion[J].arXiv:1909.03193,2019.
[9]NIU G,ZHANG Y,LI B,et al.Rule-Guided Compositional Representation Learning on Knowledge Graphs[J].Proceedings of the AAAI Conference on Artificial Intelligence,2020,34(3):2950-2958.
[10]SHA X,SUN Z,ZHANG J.Hierarchical attentive knowledgegraph embedding for personalized recommendation[J].Electronic Commerce Research and Applications,2021,48:101071.
[11]ZHANG Y,YAO Q,SHAO Y,et al.NSCaching:Simple and Efficient Negative Sampling for Knowledge Graph Embedding[C]//2019 IEEE 35th International Conference on Data Engineering(ICDE).2019:614-625.
[12]YANG B,YIH W,HE X,et al.Embedding entities and relations for learning and inference in knowledge bases[J].arXiv:1412.6575,2014.
[13]CHAMI I,WOLF A,JUAN D C,et al.Low-Dimensional Hyperbolic Knowledge Graph Embeddings[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.Association for Computational Linguistics,2020:6901-6914.
[14]DONG X,GABRILOVICH E,HEITZ G,et al.Knowledgevault:a web-scale approach to probabilistic knowledge fusion[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge discovery and Data Mining.New York,NY,USA:Association for Computing Machinery,2014:601-610.
[15]GUO L,SUN Z,HU W.Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs[C]//Proceedings of the 36th International Conference on Machine Learning.PMLR,2019:2505-2514.
[16]SCHLICHTKRULL M,KIPF T N,BLOEM P,et al.Modeling Relational Data with Graph Convolutional Networks[J].arXiv:1703.06103,2018.
[17]VASHISHTH S,SANYAL S,NITIN V,et al.Composition-based Multi-Relational Graph Convolutional Networks[C]//Eighth International Conference on Learning Representations.2020.
[18]CRESWELL A,WHITE T,DUMOULIN V,et al.GenerativeAdversarial Networks:An Overview[J].IEEE Signal Proces-sing Magazine,2017,35(1):53-65.
[19]YU L,ZHANG W,WANG J,et al.SeqGAN:Sequence Generative Adversarial Nets with Policy Gradient[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2017.
[20]CAI L,WANG W Y.KBGAN:Adversarial Learning for Know-ledge Graph Embeddings[C]//Proceedings of the 2018 Confe-rence of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies,Volume 1.New Orleans,Louisiana:Association for Computational Linguistics,2018:1470-1480.
[21]WANG P,LI S,PAN R.Incorporating GAN for Negative Sampling in Knowledge Representation Learning[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2018.
[22]BEKKER J,DAVIS J.Learning from positive and unlabeleddata:a survey[J].Machine Learning,2020,109(4):719-760.
[23]KIRYO R,NIU G,DU PLESSIS M C,et al.Positive-Unlabeled Learning with Non-Negative Risk Estimator[C]//Advances in Neural Information Processing Systems:Vol.30.Curran Asso-ciates,Inc.,2017.
[24]XU D,DENIL M.Positive-Unlabeled Reward Learning[C]//Proceedings of the 2020 Conference on Robot Learning.PMLR,2021:205-219.
[25]LUO C,ZHAO P,CHEN C,et al.PULNS:Positive-Unlabeled Learning with Effective Negative Sample Selector[J].Procee-dings of the AAAI Conference on Artificial Intelligence,2021,35(10):8784-8792.
[26]DU PLESSIS M C,NIU G,SUGIYAMA M.Analysis of Lear-ning from Positive and Unlabeled Data[C]//Advances in Neural Information Processing Systems.Curran Associates,Inc.,2014.
[27]PLESSIS M D,NIU G,SUGIYAMA M.Convex Formulationfor Learning from Positive and Unlabeled Data[C]//Procee-dings of the 32nd International Conference on Machine Lear-ning.PMLR,2015:1386-1394.
[28]HSIEH Y G,NIU G,SUGIYAMA M.Classification from Positive,Unlabeled and Biased Negative Data[C]//Proceedings of the 36th International Conference on Machine Learning.PMLR,2019:2820-2829.
[29]RAN Z J,SUN L F,ZOU Y S,et al.Few-Shot KnowledgeGraph Completion Model Based on Relation Learning Network[J].Computer Engineering,2023,49(9):52-59.
[30]TOUTANOVA K,CHEN D,PANTEL P,et al.RepresentingText for Joint Embedding of Text and Knowledge Bases[C]//Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing.Lisbon,Portugal:Association for Computational Linguistics,2015:1499-1509.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发