面向关系特性建模的知识图谱表示学习研究综述

doi:10.11896/jsjkx.240100113

摘要/Abstract

摘要： 知识图谱表示学习技术可以将符号化的知识图谱转换为实体和关系的数值化表示,进而有效结合各类深度学习模型以赋能知识增强的下游应用。相较于实体,关系充分体现了知识图谱中的语义信息,建模关系的各类特性对知识图谱表示学习的性能非常关键。首先,针对一对一、一对多、多对一和多对多的复杂映射特性,梳理基于关系感知映射的模型、基于特定表示空间的模型、基于张量分解的模型和基于神经网络的模型;接着,面向建模对称、反对称、逆反和组合特性的多种关系模式,总结基于改进张量分解的模型、基于改进关系感知映射的模型和基于旋转操作的模型;其次,面向建模实体间隐含的层次关系,介绍基于辅助信息的模型、基于双曲空间的模型和基于极坐标系的模型。最后,针对稀疏知识图谱和动态知识图谱等更加复杂的情况,从融合多模态信息的知识图谱表示学习、规则增强的关系模式建模和针对动态知识图谱表示学习的关系特性建模等方面,讨论该领域研究的未来发展方向。

关键词: 知识图谱, 表示学习, 复杂映射关系, 关系模式, 层次关系

Abstract: Knowledge graph representation learning techniques can transform symbolic knowledge graphs into numerical representations of entities and relations,and then effectively combine various deep learning models to facilitate downstream applications of knowledge enhancement.In contrast to entities,relations fully embody semantics in knowledge graphs.Thus,modeling various characteristics of relations significantly influences the performance of knowledge graph representation learning.Firstly,aiming at the complex mapping properties of one-to-one,one-to-many,many-to-one,and many-to-many relations,relation-aware mapping-based models,specific representation space-based models,tensor decomposition-based models,and neural network-based models are reviewed.Next,focusing on modeling various relation patterns such as symmetry,asymmetry,inversion,and composition,we summarize models based on modified tensor decomposition,models based on modified relation-aware mapping,and models based on rotation operations.Subsequently,considering the implicit hierarchical relations among entities,we introduce auxiliary information-based models,hyperbolic spaces-based models,and polar coordinate system-based models.Finally,for more complex scenarios such as sparse knowledge graphs and dynamic knowledge graphs,this paper discusses some future research directions.It explores ideas like integrating multimodal information into knowledge graph representation learning,rule-enhanced relation patterns mo-deling,and modeling relation characteristics for dynamic knowledge graph representation learning.

Key words: Knowledge graph, Representation learning, Complex mapping relations, Relation patterns, Hierarchical relations

中图分类号:

TP391

牛广林, 蔺震. 面向关系特性建模的知识图谱表示学习研究综述[J]. 计算机科学, 2024, 51(9): 182-195. https://doi.org/10.11896/jsjkx.240100113

NIU Guanglin, LIN Zhen. Survey of Knowledge Graph Representation Learning for Relation Feature Modeling[J]. Computer Science, 2024, 51(9): 182-195. https://doi.org/10.11896/jsjkx.240100113

参考文献

[1]LIU Z Y,SUN M S,LIN Y K,et al.Research progress onknowledge representation learning[J].Journal of Computer Research and Development,2016,53(2):247-261.
[2]ZHANG T C,TIAN X,SUN X H,et al.A comprehensive review of knowledge graph embedding techniques[J].Journal of Software,2023,34(1):277-311.
[3]GE X,WANG Y C,WANG B,et al.Knowledge graph embedding:an overview[J].arXiv:2309.12501,2023.
[4]ZHANG N,DENG S,SUN Z,et al.Long-tail relation extraction via knowledge graph embeddings and graph convolution networks[C]//Proceedings of the 17th Annual Conference of the North American Chapter of the Association for Computational Linguistics.2019:3016-3025.
[5]WANG Z,YANG J,YE X.Knowledge graph alignment with en-tity-pair embedding[C]//Procedings of the 2020 Conference on Empirical Methods in Natural Language Processing.2020:1672-1680.
[6]LI G,SUN Z,HU W,et al.Position-aware relational transfor-mer for knowledge graph embedding[J/OL].https://ieeexplore.ieee.org/document/10092525.
[7]LIN B Y,CHEN X,CHEN J,et al.KagNet:Knowledge aware graph networks for commonsense reasoning[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing(EMNLP-IJCNLP).2019:2829-2839.
[8]WANG Y,LI A,ZHANG J,et al.Enhanced knowledge graphembedding for multi-task recommendation via integrating attri-bute information and high-order connectivity[C]//Proceedings of the 10th International Joint Conference on Knowledge Graphs.2022:140-144.
[9]PAN S,LUO L.Unifying large language models and knowledge graphs:A roadmap[J].arXiv:2306.08302,2023.
[10]YAN Q,FAN J,LI M,et al.A survey on knowledge graph em-bedding[C]//2022 7th IEEE International Conference on Data Science in Cyberspace(DSC).2022:576-583.
[11]CAO J,FANG J,MENG Z,et al.Knowledge graph embedding:A survey from the perspective of representation spaces[J].ar-Xiv:2211.03536,2022.
[12]SHEN Q,ZHANG H,XU Y,et al.Comprehensive survey of loss functions in knowledge graph embedding models[J].Computer Science,2023,50(4):149-158.
[13]LI Z,ZHAO Y,ZHANG Y.Survey of knowledge graph reaso-ning based on representation learning[J].Computer Science,2023,50(3):94-113.
[14]YU M B,DU J Q,LUO J G,et al.Research progress of know-ledge graph completion based on knowledge representation lear-ning[J].Computer Engineering and Applications,2023,59(18):59-73.
[15]DU X,LIU M,SHEN L,et al.A survey of knowledge graph representation learning methods for link prediction[J].Journal of Software,2024,35(1):87-117.
[16]NGUYEN D Q.A survey of embedding models of entities and relationships for knowledge graph com-pletion[C]//Proceedings of the Graph-based Methods for Natural Language Processing(TextGraphs).2020:1-14.
[17]WANG Q,MAO Z,WANG B,et al.Knowledge graph embedding:A survey of approaches and applications[J].IEEE Tran-sactions on Knowledge and Data Engineering,2017,29(12):2724-2343.
[18]DAI Y,WANG S,XIONG N,et al.A survey on knowledgegraph embedding:Approaches,applications,and benchmarks[J].Electronics,2020,9(5):750.
[19]GESESE G A,BISWAS R,SACK H.A comprehen-sive survey of knowledge graph embeddings with literals:Techniques and applications[C]//Workshop at ESWC 2020 on Deep Learning for Knowledge Graph.2019.
[20]WANG M,QIU L,WANG X.A survey on knowledge graphembeddings for link prediction[J].Symmetry,2021,13(3):485.
[21]WANG H,QI G,CHEN H.Knowledge graph methods,practices,and applications[M].Electronic Industry Press,2019.
[22]JI S,PAN S,CAMBRIA E,el al.A survey on knowledgegraphs:Representation,acquisition,and applications[J].IEEE Transactions on Neural Networks and Learning Systems,2022,33(2):494-514.
[23]ALAM M M,R R M,NAYYERI M,et al.Language modelguided knowledge graph embeddings[J].IEEE Access,2022,10:76008-76020.
[24]BORDES A,USUNIER N,GARCIA D,et al.Translating em-beddings for modeling multi-relational data[C]//Proceedings of the 26th International Conference on Neural Information Processing Systems.2013:2787-2795.
[25]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.2014:1112-1119.
[26]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.2015:2181-2187.
[27]NGUYEN D Q,SIRTS K,QU L Z,et al.STransE:A novel embedding model of entities and relationships in knowledge bases[C]//Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics(NAACL).2016:460-466.
[28]JI G L,HE S Z,XU L H,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.Beijing:Association for Computational Linguistics(ACL),2015:687-696.
[29]JI G L,LIU K,HE S Z,et al.Knowledge graph completion with adaptive sparse transfer matrix[C]//Proceedings of the 30th AAAI Conference on Artificial Intelligence(AAAI).2016:985-991.
[30]FENG J,HUANG M L,WANG M D,et al.Knowledge graph embedding by flexible translation[C]//Proceedings of the 15th International Conference on Principles of Knowledge Representation and Reasoning(KR).2016:557-560.
[31]XIAO H,HUANG M L,HAO Y,et al.TransA:An adaptive approach for knowledge graph embedding[J].arXiv:1509.05490,2015.
[32]FAN M,ZHOU Q,CHANG E,et al.Transition-based know-ledge graph embedding with relational mapping properties[C]//Proceedings of the 28th Pacific Asia Conference on Language,Information and Computing(PACLIC).2014:328-337.
[33]HE S,LIU K,JI G,et al.Learning to represent knowledgegraphs with Gaussian embedding[C]//Proceedings of the 24th ACM International Conference on Information and Knowledge Management.2015:623-632.
[34]XIAO H,HUANG M,ZHU X.From one point to a manifold:Knowledgegraph embedding for precise link prediction[C]//Proceedings of the 25th International Joint Conference on Artificial Intelligence.2016:1315-1321.
[35]EBISU T,ICHISE R.TorusE:Knowledge graph embedding on a lie group[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence(AAAI).2018:1819-1826.
[36]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 Machine Learning.2011:809-816.
[37]YANG B,YIH W T,HE X,et al.Embedding entities and rela-tions for learning and inference in knowledge bases[C]//Proceedings of the 3rd International Conference on Learning Representations.2015.
[38]BALAZEVIC I,ALLEN C,HOSPEDALES T.TuckER:Tensor factorization for knowledge graph completion[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing(EMNLP).2019:5185-5194.
[39]BORDES A,GLOROT X,WESTON J,et al.A semantic ma-tching energy function for learning with multi-relational data[J].Machine Learning,2014,94(2):233-259.
[40]SOCHER R,CHEN D,MANNING C D,et al.Reasoning withneural tensor networks for knowledge base completion[C]//Proceedings of the 26th International Conference on Neural Information Processing Systems.2013:926-934.
[41]DETTMERS T,MINERVINI P,STENETORP P.Convolu-tional 2D knowledge graph embeddings[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence.2018:1811-1818.
[42]NGUYEN D Q,NGUYEN T D,NGUYEN D Q,et al.A novel embedding model for knowledge base completion based on con-volutional neural network[C]//Proceedings of the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics.2018:327-333.
[43]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 the 2019 Confe-rence of the North American Chapter of the Association for Computational Linguistics(NAACL).2019:2180-2189.
[44]VASHISHTH S,SANYAL S,NITIN V,et al.InteractE:Im-proving convolution-based knowledge graph embeddings by increasing feature interactions[C]//Proceedings of the 34th AAAI Conference on Artificial Intelligence.2020:3009-3016.
[45]TROUILLON T,WELBL J,RIEDEL S,et al.Complex embeddings for simple link prediction[C]//Proceedings of the 33rd International Conference on Machine Learning.2016:2071-2080.
[46]NICKEL M,ROSASCO L,POGGIO T.Holographic embed-dings of knowledge graphs[C]//Proceedings of the 30th AAAI Conference on Artificial Intelligence.2016:1955-1961.
[47]KAZEMI S M,POOLE D.SimplE embedding for link prediction in knowledge graphs[C]//Proceedings of the 32nd International Conference on Neural Information Processing Systems.2018:4289-4300.
[48]CHAO L,HE J,WANG T,et al.Pairre:Knowledge graph embeddings via paired relation vectors[C]//Annual Meeting of the Association for Computational Linguistics and International Joint Conference on Natural Language Processing.2021:4360-4369.
[49]YU L,LUO Z,LIU H,et al.Triplere:Knowledge graph embeddings via tripled relation vectors[J].arXiv:2209.08271,2022.
[50]ZHANG X,YANG Q,XU D.Trans:Transition-based know-ledge graph embedding with synthetic relation representation[J].arXiv:2204.08301,2022.
[51]SUN Z,DENG Z H,NIE J Y,et al.RotatE:Knowledge graph embedding by relational rotation in complex space[C]//Proceedings of the 7th International Conference on Learning Representations.2019:1-18.
[52]ZHANG S,TAY Y,YAO L,et al.Quaternion knowledge graph embedding[C]//Proceedings of the 33rd International Confe-rence on Neural Information Processing Systems.2019:2731-2741.
[53]CAO Z,XU Q,YANG Z,et al.Dual quaternion knowledgegraph Embeddings[C]//Proceedings of the 35th AAAI Confe-rence on Artificial Intelligence.2021:6894-6902.
[54]GUO J,KOK S.Bique:Biquaternionic embeddings of know-ledge graphs[C]//Conference on Empirical Methods in Natural Language Processing.2021:8338-8351.
[55]XU C,LI R.Relation embedding with dihedral group in know-ledge graph[C]//Annual Meeting of the Association for Computational Linguistics.2019:263-272.
[56]GE X,WANG Y C,WANG B,et al.Compounde:Knowledge graph embedding with translation,rotation and scaling compound operations[J].arXiv:2207.05324,2022.
[57]WANG S,FU K,SUN X,et al.Hierarchical-aware relation rotational knowledge graph embedding for link prediction[J].Neurocomputing,2021,458:259-270.
[58]LI Y,ZHENG R,TIAN T,et al.Joint embedding of hierarchical categories and entities for concept categorization and dataless classification[C]//COLING.2016:2678-2688.
[59]ZHANG Z,ZHUANG F,QU M,et al.Knowledge graph embedding with hierarchical relation structure[C]//Conference on Empirical Methods in Natural Language Processing.2018:3198-3207.
[60]XIE R,LIU Z,SUN M.Representation learning of knowledgegraphs with hierarchical types[C]//Proceedings of the 25th International Joint Conference on Artificial Intelligence.2016:2965-2971.
[61]NICKEL M,KIELA D.Poincare embeddings for learning hierarchical representations[C]//Proceedings of the 31st Interna-tional Conference on Neural Information Processing Systems(NIPS).2017:6341-6350.
[62]BALAŽEVIČI,ALLEN C,HOSPEDALES T.Multi-relational Poincare graph embeddings[C]//Proceedings of the 33rd International Conference on Neural Information Processing Systems.2019:4463-4473.
[63]CHAMI I,WOLF A,JUAN D C,et al.Low-dimensional hyperbolic knowledge graph embeddings[J].arXiv:2005.00545,2020.
[64]SUN Z,CHEN M,HU W,et al.Knowledge association with hyperbolic knowledge graph embeddings[C]//Conference on Empirical Methods in Natural Language Processing.2020:5704-5716.
[65]BRUNA J,ZAREMBA W,SZLAM A,et al.Spectral networks and locally connected networks on graphs[C]//Proceedings of the 2nd International Conference on Learning Representations.2014.
[66]WANG S,WEI X,NOGUEIRA DOS SANTOS C N,et al.Mixed-curvature multi-relational graph neural network for knowledge graph completion[C]//International Conference on World Wide Web.2021:1761-1771.
[67]XIONG B,ZHU S,NAYYERI M,et al.Ultrahyperbolic know-ledge graph embeddings[J].arXiv:2206.00449,2022.
[68]ZHANG Z,CAI J,ZHANG Y,et al.Learning hierarchy-aware knowledge graph embeddings for link prediction[C]//AAAI Conference on Artificial Intelligence.2020:3065-3072.
[69]WANG S,WEI X,DOS SANTOS C N,et al.Knowledge graph representation via hierarchical hyperbolic neural graph embedding[C]//IEEE International Conference on Big Data.2021:540-549.
[70]PAN Z,WANG P.Hyperbolic hierarchy-aware knowledge graph embedding for link prediction[C]//Findings of Conference on Empirical Methods in Natural Language Processing.2021:2941-2948.
[71]XIE R,LIU Z,JIA J,et al.Representation learning of knowledge graphs with entity descriptions[C]//Proceedings of the 30th AAAI Conference on Artificial Intelligence.2016:2659-2665.
[72]YAO L,MAO C,LUO Y.KG-BERT:BERT for knowledgegraph completion[J].arXiv:1909.03193,2019.
[73]XIE R,LIU Z,LUAN H,et al.Image-embodied knowledge representation learning[C]//Proceedings of the 26th International Joint Conference on Artificial Intelligence.2017:3140-3146.
[74]WANG M,WANG S,YANG H,et al.Is visual context reallyhelpful for knowledge graph?A representation learning perspective[C]//Proceedings of the 29th ACM International Conference on Multimedia.2021:2735-2743.
[75]NIU G,ZHANG Y,LI B,et al.Rule-Guided Compositional Representation Learning on Knowledge Graphs[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2020:2950-2958.
[76]NIU G,LI B,ZHANG Y,et al.Perform like an Engine:AClosed-Loop Neural-Symbolic Learning Framework for Know-ledge Graph Inference[C]//Proceedings of the 29th Interna-tionalConference on Computational Linguistics.2022:1391-1400.
[77]NIU G,LI Y,TANG C,et al.Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completion[C]//Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval.2021:213-222.
[78]HAN Z,CHEN P,MA Y,et al.Dyernie:Dynamic evolution of Riemannian manifold embeddings for temporal knowledge graph completion[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing.2020:7301-7316.
[79]LING S,NGUYEN K,ROUX-LANGLOIS A,et al.A lattice-based group signature scheme with verifier-local revocation[J].Theoretical Computer Science,2018,730(19):1-20.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed