计算机科学 ›› 2022, Vol. 49 ›› Issue (6A): 74-85.doi: 10.11896/jsjkx.210100122

• 智能计算 • 上一篇    下一篇

知识图谱推理研究综述

马瑞新, 李泽阳, 陈志奎, 赵亮   

  1. 大连理工大学软件学院 辽宁 大连 116620
  • 出版日期:2022-06-10 发布日期:2022-06-08
  • 通讯作者: 赵亮(liangzhao@dlut.edu.cn)
  • 作者简介:(maruixin@dlut.edu.cn)
  • 基金资助:
    国家重点研发计划(2018YFC0830203);国家自然科学基金(61906030);辽宁省自然科学基金(2020-BS-063);装备预先研究领域基金(80904010301);中央高校基本科研业务费专项资金(DUT20RC(4)009)

Review of Reasoning on Knowledge Graph

MA Rui-xin, LI Ze-yang, CHEN Zhi-kui, ZHAO Liang   

  1. School of Software Technology,Dalian University of Technology,Dalian,Liaoning 116620,China
  • Online:2022-06-10 Published:2022-06-08
  • About author:MA Rui-xin,born in 1975,Ph.D,asso-ciate professor,is a member of China Computer Federation.His main research interests include big data and cloud computing.
    ZHAO Liang,born in 1988,Ph.D,associate professor.His main research inte-rests include big data and artificial intelligence.
  • Supported by:
    National Key Research and Development Program of China(2018YFC0830203),National Natural Science Foundation of China (61906030),Natural Science Foundation of Liaoning Province(2020-BS-063),Equipment Advance Research Fund(80904010301) and Fundamental Research Funds for the Central Universities(DUT20RC(4)009).

摘要: 近年来,随着互联网技术以及引用模式的快速发展,计算机世界的数据规模呈指数型增长,这些数据中蕴含着大量有价值的信息,如何从中筛选出知识并将这些知识进行有效组织和表达引起了广泛关注。知识图谱由此而生,面向知识图谱的知识推理就是知识图谱研究的热点之一,已经在语义搜索、智能问答等领域取得了重大成就。然而,由于样本数据存在各种缺陷,例如样本数据缺少头尾实体、查询路径过长、样本数据错误等,因此面对上述特点的零样本、单样本、少样本和多样本知识图谱推理更受瞩目。文中将从知识图谱的基本概念和基础知识出发,介绍近年来知识图谱推理方法的最新研究进展。具体而言,根据样本数据量大小的不同,将知识图谱推理方法分为多样本推理、少样本推理和零与单样本推理。模型使用超过5个实例数进行推理的为多样本推理,模型使用2~5实例数进行推理的为少样本推理,模型使用零个或者一个实例数进行推理的为零与单样本推理。根据方法的不同,将多样本知识图谱推理细分为基于规则的推理、基于分布式的推理、基于神经网络的推理以及基于其他的推理,将少样本知识图谱推理细分为基于元学习的推理与基于相邻实体信息的推理,具体分析总结这些方法。此外,进一步讲述了知识图谱推理的典型应用,并探讨了知识图谱推理现存的问题、未来的研究方向和前景。

关键词: 单样本推理, 多样本推理, 零样本推理, 少样本推理, 知识图谱, 知识推理

Abstract: In recent years,the rapid development of Internet technology and reference models has led to an exponential growth in the scale of computer world data,which contains a lot of valuable information.How to select knowledge from it,and organize and express this knowledge effectively attract wide attention.Knowledge graphs are also born from this.Knowledge reasoning for knowledge graphs is one of the hotspots of knowledge graph research,and important achievements are obtained in the fields of semantic search and intelligent question answering.However,due to various defects in the sample data,such as the lack of head and tail entities in sample data,the long query path,as well as the wrong sample data.In the face of the above characteristics,the knowledge graph reasoning of zero-shot,one-shot,few-shot and multi-shot get more attention.Based on the basic concepts and basic knowledge of knowledge graph,this paper introduces the latest research progress of knowledge graph reasoning methods in recent years.Specifically,according to the size of sample data,the knowledge graph reasoning method is divided into multi-shot reasoning,few-shot reasoning,zero-shot and single-shot reasoning.Models that use more than five instances for reasoning are multi-sample reasoning,models that use two to five instances for reasoning are few-shot reasoning,and those use zero or one instance number for reasoning are zero-shpt and one-shot reasoning.The multi-shot knowledge graph reasoning is subdivided into rule-based reasoning,distributed-based reasoning,neural network-based reasoning,and other reasoning.The few-shot knowledge graph reasoning is subdivided into meta-learning-based reasoning and neighboring entity information-based reasoning.And these methods are analyzed and summarized.In addition,this paper further describes the typical application of knowledge graph reaso-ning,and discusses the existing problems,future research directions and prospects of knowledge graph reasoning.

Key words: Few-shot reasoning, Knowledge graph, Knowledge reasoning, Multi-shot reasoning, One-shot reasoning, Zero-shot reasoning

中图分类号: 

  • TP391
[1] GUAN SP,JIN X L,JIA Y T,et al.Knowledge reasoning over knowledge graph:A survey[J].Journal of Software,2018,29(10):2966-2994.
[2] AUER S,BIZER C,KOBILAROV G,et al.Dbpedia:A nucleus for a web of open data[M]//The Semantic Web.Berlin:Springer,2007:722-735.
[3] 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.
[4] CARLSON A,BETTERIDGE J,KISIEL B,et al.Toward an architecture for never-ending language learning[C]//Twenty-Fourth AAAI Conference on Artificial Intelligence.2010:1306-1313.
[5] WU W,LI H,WANG H,et al.Probase:A probabilistic taxonomy for text understanding[C]//Proceedings of the 2012 ACM SIGMOD International Conference on Management of Data.2012:481-492.
[6] 自底向上构建知识图谱全过程[OL].[2018-07-03].https://zhuanlan.zhihu.com/p/38891715.
[7] MILLER G A.WordNet:An electronic lexical database[M].MIT press,1998.
[8] YOU B,LIU X R,LI N,et al.Using information content to evaluate semantic similarity on HowNet[C]//2012 Eighth International Conference on Computational Intelligence and Security.IEEE,2012:142-145.
[9] ERXLEBEN F,GÜNTHER M,KRÖTZSCH M,et al.Introducing Wikidata to the linked data web[C]//International Semantic Web Conference.Cham:Springer,2014:50-65.
[10] HUANG H Q,YU J,LIAO X,et al.Review on KnowledgeGraphs.Computer Systems & Applications,2019,28(6):1-12.
[11] CARLSON A,BETTERIDGE J,KISIELB,et al.Toward an architecture for never-ending language learning[C]//Twenty-Fourth AAAI Conference on Artificial Intelligence.2010:1306-1313.
[12] WANG W Y,MAZAITIS K,COHEN W W.Programming with personalized pagerank:a locally groundable first-order probabilistic logic[C]//Proceedings of the 22nd ACM International Conference on Information & Knowledge Management.2013:2129-2138.
[13] COHEN W W.Tensorlog:A differentiable deductive database[J].arXiv:1605.06523,2016.
[14] PAULHEIM H,BIZER C.Improving the quality of linked data using statistical distributions[J].International Journal on Semantic Web and Information Systems,2014,10(2):63-86.
[15] JANG S,MEGAWATI M,CHOI J,et al.Semi-Automatic Qua-lity Assessment of Linked Data without Requiring Ontology[C]//NLP-DBPEDIA@ ISWC.2015:45-55.
[16] LAO N,COHEN W W.Relational retrieval using a combination of path-constrained random walks[J].Machine Learning,2010,81(1):53-67.
[17] LAO N,MITCHELL T,COHEN W.Random walk inference and learning in a large scale knowledge base[C]//Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing.2011:529-539.
[18] ZHAO Z,JIA Y,WANG Y.Content-structural relation infer-ence in knowledge base[C]//Twenty-Eighth AAAI Conference on Artificial Intelligence.2014:3154-3155.
[19] KOTNIS B,BANSAL P,TALUKDAR P.Knowledge base inference using bridging entities[C]//Proceedings of the 2015 Conference on Empirical Methods in Natural Language Proces-sing.2015:2038-2043.
[20] GALÁRRAGA L A,TEFLIOUDI C,HOSE K,et al.AMIE:association rule mining under incomplete evidence in ontological knowledge bases[C]//Proceedings of the 22nd International Conference on World Wide Web.2013:413-422.
[21] GALÁRRAGA L,TEFLIOUDI C,HOSEK,et al.Fast rulemining in ontological knowledge bases with AMIE $$+$$+[J].The International Journal on Very Large Data Bases,2015,24(6):707-730.
[22] GARDNER M,MITCHELL T.Efficient and expressive knowledge base completion using subgraph feature extraction[C]//Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing.2015:1488-1498.
[23] LIU Q,JIANG L,HAN M,et al.Hierarchical random walk inference in knowledge graphs[C]//Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval.2016:445-454.
[24] BORDES A,USUNIER N,GARCIA-DURAN A,et al.Translating embeddings for modeling multi-relational data[J].Advances in Neural Information Processing Systems,2013,26:2787-2795.
[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] WEN J,LI J,MAO Y,et al.On the Representation and Embedding of Knowledge Bases beyond Binary Relations[C]//Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence.2016:1300-1307.
[27] JIA Y,WANG Y,LIN H,et al.Locally adaptive translation for knowledge graph embedding[C]//Thirtieth AAAI Conference on Artificial Intelligence.2016:992-998.
[28] XIAO H,HUANG M,HAO Y,et al.TransG:A generativemixture model for knowledge graph embedding[J].arXiv:1509.05488,2015.
[29] LIN Y,LIU Z,SUN M,et al.Learning entity and relation embeddings for knowledge graph completion[C]//Twenty-ninth AAAI Conference on Artificial Intelligence.2015:2181-2187.
[30] JI G,HE S,XU L,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(Long Papers).2015:687-696.
[31] 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.2014:328-337.
[32] JI G,LIU K,HE S,et al.Knowledge graph completion witha daptive sparse transfer matrix[C]//Thirtieth AAAI Confe-rence on Artificial Intelligence.2016:985-991.
[33] GUO S,WANG Q,WANG B,et al.Semantically smooth know-ledge graph embedding[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing(Long Papers).2015:84-94.
[34] NGUYEN D Q,SIRTS K,QU L,et al.Neighborhood mixture model for knowledge base completion[C]//Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning.2016:40-50.
[35] NICKEL M,TRESP V,KRIEGELH P.A three-way model for collective learning on multi-relational data[C]//Proceedings of the 28th Int'l Conf.on Machine Learning.New York:ACM Press,2011:809-816.
[36] CHANG K W,YIH W,YANG B,et al.Typed tensor decomposition of knowledge bases for relation extraction[C]//Procee-dings of the 2014 Conference on Empirical Methods in Natural Language Processing(EMNLP).2014:1568-1579.
[37] NICKEL M,JIANG X,TRESP V.Reducing the Rank in Relational Factorization Models by Including Observable Patterns[C]//Advances in Neural Information Processing Systems 27:Annual Conference on Neural Information Processing Systems.2014:1179-1187.
[38] TROUILLON T,WELBL J,RIEDEL S,et al.Complex embeddings for simple link prediction[C]//International Conference on Machine Learning.PMLR,2016:2071-2080.
[39] TAY Y,LUU A T,HUI S C,et al.Random semantic tensor ensemble for scalable knowledge graph link prediction[C]//Proceedings of the Tenth ACM International Conference on Web Search and Data Mining.2017:751-760.
[40] HE S,LIU K,JI G,et al.Learning to represent knowledgegraphs with gaussian embedding[C]//Proceedings of the 24th ACM International on Conference on Information and Know-ledge Management.2015:623-632.
[41] XIAO H,HUANG M,ZHU X.From one point to a manifold:Knowledge graph embedding for precise link prediction[C]//Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence.2016:1315-1321.
[42] LIN Y,LIU Z,LUAN H,et al.Modeling relation paths for representation learning of knowledge bases[C]//Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing.2015:705-714.
[43] LIN X,LIANG Y,GIUNCHIGLIA F,et al.CompositionalLearning of Relation Path Embedding for Knowledge Base Completion[J].arXiv:1611.07232,2016.
[44] FENG J,HUANG M,YANG Y,et al.GAKE:Graph awareknowledge embedding[C]//Proceedings of COLING 2016,the 26th International Conference on Computational Linguistics:Technical Papers.2016:641-651.
[45] WANG Z,LI L,ZENG D D,et al.Attention-based multi-hopreasoning for knowledge graph[C]//2018 IEEE International Conference on Intelligence and Security Informatics(ISI).IEEE,2018:211-213.
[46] CHEN H,LI G,SUN Y,et al.A multi-hop link prediction approach based on reinforcement learning in knowledge graphs[C]//2018 11th International Symposium on Computational Intelligence and Design(ISCID).IEEE,2018:165-169.
[47] 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.
[48] CHEN D,SOCHER R,MANNING C D,et al.Learning newfacts from knowledge bases with neural tensor networks and semantic word vectors[J].arXiv:1301.3618,2013.
[49] SHI B,WENINGER T.ProjE:Embedding projection for knowledge graph completion[C]//Proceedings of the AAAI Confe-rence on Artificial Intelligence.2017:1236-1242.
[50] 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 2018 Confe-rence of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.2018:327-333.
[51] NEELAKANTAN A,ROTH B,MCCALLUM A.Compositional vector space models for knowledge base completion[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing.2015:156-166.
[52] DAS R,NEELAKANTAN A,BELANGER D,et al.Chains of reasoning over entities,relations,and text using recurrent neural networks[C]//Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics.2017:132-141.
[53] GRAVES A,WAYNE G,REYNOLDS M,et al.Hybrid computing using a neural network with dynamic external memory[J].Nature,2016,538(7626):471-476.
[54] WANG Q,YIN H,WANG W,et al.Multi-hop path queries overknowledge graphs with neural memory networks[C]//International Conference on Database Systems for Advanced Applications.Cham:Springer,2019:777-794.
[55] HAN X,SUN L.Context-Sensitive inference rule discovery:Agraph-based method[C]//Proceedings of COLING 2016,the 26th International Conference on Computational Linguistics:Technical Papers.2016:2902-2911.
[56] WANG W Y,COHEN W W.Learning First-Order Logic Embeddings via Matrix Factorization[C]//Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence.2016:2132-2138.
[57] GUO S,WANG Q,WANG L,et al.Jointly embedding know-ledge graphs and logical rules[C]//Proceedings of the 2016 Conference on Empirical Methods in Natural Language Proces-sing.2016:192-202.
[58] SCHLICHTKRULL M,KIPF T N,BLOEM P,et al.Modeling relational data with graph convolutional networks[C]//Euro-pean Semantic Web Conference.Cham:Springer,2018:593-607.
[59] YANG F,YANG Z,COHEN W W.Differentiable learning oflogical rules for knowledge base reasoning[C]//Annual Confe-rence on Neural Information Processing Systems.2017:2319-2328.
[60] XIONG W,YU M,CHANG S,et al.One-shot relational lear-ning for knowledge graphs[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.2018:1980-1990.
[61] CHEN M,ZHANG W,ZHANG W,et al.Meta relational lear-ning for few-shot link prediction in knowledge graphs[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Confe-rence on Natural Language Processing.2019:4216-4225.
[62] LV X,GU Y,HAN X,et al.Adapting meta knowledge graph information for multi-hop reasoning over few-shot relations[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing.2019:3374-3379.
[63] LIN X V,SOCHER R,XIONG C.Multi-hop knowledge graph reasoning with reward shaping[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Proces-sing.2018:3243-3253.
[64] FINN C,ABBEEL P,LEVINE S.Model-agnostic meta-learning for fast adaptation of deep networks[C]//International Confe-rence on Machine Learning.PMLR,2017:1126-1135.
[65] WANG H,XIONG W,YU M,et al.Meta reasoning over know-ledge graphs[J].arXiv:1908.04877,2019.
[66] ZHANG C,YAO H,HUANG C,et al.Few-shot knowledgegraph completion[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2020:3041-3048.
[67] YIN W,YAGHOOBZADEH Y,SCHÜTZE H.Recurrent one-hop predictions for reasoning over knowledge graphs[C]//Proceedings of the 27th International Conference on Computational Linguistics.2018:2369-2378.
[68] SHENG J,GUO S,CHEN Z,et al.Adaptive Attentional Network for Few-Shot Knowledge Graph Completion[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing.2020:1681-1691.
[69] DU Z,ZHOU C,DING M,et al.Cognitive knowledge graph reasoning for one-shot relational learning[J].arXiv:1906.05489,2019.
[70] MIRTAHERI M,ROSTAMI M,REN X,et al.One-shot Lear-ning for Temporal Knowledge Graphs[J].arXiv:2010.12144,2020.
[1] 饶志双, 贾真, 张凡, 李天瑞.
基于Key-Value关联记忆网络的知识图谱问答方法
Key-Value Relational Memory Networks for Question Answering over Knowledge Graph
计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277
[2] 吴子仪, 李邵梅, 姜梦函, 张建朋.
基于自注意力模型的本体对齐方法
Ontology Alignment Method Based on Self-attention
计算机科学, 2022, 49(9): 215-220. https://doi.org/10.11896/jsjkx.210700190
[3] 孔世明, 冯永, 张嘉云.
融合知识图谱的多层次传承影响力计算与泛化研究
Multi-level Inheritance Influence Calculation and Generalization Based on Knowledge Graph
计算机科学, 2022, 49(9): 221-227. https://doi.org/10.11896/jsjkx.210700144
[4] 徐涌鑫, 赵俊峰, 王亚沙, 谢冰, 杨恺.
时序知识图谱表示学习
Temporal Knowledge Graph Representation Learning
计算机科学, 2022, 49(9): 162-171. https://doi.org/10.11896/jsjkx.220500204
[5] 秦琪琦, 张月琴, 王润泽, 张泽华.
基于知识图谱的层次粒化推荐方法
Hierarchical Granulation Recommendation Method Based on Knowledge Graph
计算机科学, 2022, 49(8): 64-69. https://doi.org/10.11896/jsjkx.210600111
[6] 王杰, 李晓楠, 李冠宇.
基于自适应注意力机制的知识图谱补全算法
Adaptive Attention-based Knowledge Graph Completion
计算机科学, 2022, 49(7): 204-211. https://doi.org/10.11896/jsjkx.210400129
[7] 邓凯, 杨频, 李益洲, 杨星, 曾凡瑞, 张振毓.
一种可快速迁移的领域知识图谱构建方法
Fast and Transmissible Domain Knowledge Graph Construction Method
计算机科学, 2022, 49(6A): 100-108. https://doi.org/10.11896/jsjkx.210900018
[8] 杜晓明, 袁清波, 杨帆, 姚奕, 蒋祥.
军事指控保障领域命名实体识别语料库的构建
Construction of Named Entity Recognition Corpus in Field of Military Command and Control Support
计算机科学, 2022, 49(6A): 133-139. https://doi.org/10.11896/jsjkx.210400132
[9] 熊中敏, 舒贵文, 郭怀宇.
融合用户偏好的图神经网络推荐模型
Graph Neural Network Recommendation Model Integrating User Preferences
计算机科学, 2022, 49(6): 165-171. https://doi.org/10.11896/jsjkx.210400276
[10] 钟将, 尹红, 张剑.
基于学术知识图谱的辅助创新技术研究
Academic Knowledge Graph-based Research for Auxiliary Innovation Technology
计算机科学, 2022, 49(5): 194-199. https://doi.org/10.11896/jsjkx.210400195
[11] 朱敏, 梁朝晖, 姚林, 王翔坤, 曹梦琦.
学术引用信息可视化方法综述
Survey of Visualization Methods on Academic Citation Information
计算机科学, 2022, 49(4): 88-99. https://doi.org/10.11896/jsjkx.210300219
[12] 梁静茹, 鄂海红, 宋美娜.
基于属性图模型的领域知识图谱构建方法
Method of Domain Knowledge Graph Construction Based on Property Graph Model
计算机科学, 2022, 49(2): 174-181. https://doi.org/10.11896/jsjkx.210500076
[13] 徐进.
面向工业装配的知识图谱构建与应用研究
Construction and Application of Knowledge Graph for Industrial Assembly
计算机科学, 2021, 48(6A): 285-288. https://doi.org/10.11896/jsjkx.200600116
[14] 黄梅根, 刘川, 杜欢, 刘佳乐.
基于知识图谱的认知诊断模型及其在教辅中的应用研究
Research on Cognitive Diagnosis Model Based on Knowledge Graph and Its Application in Teaching Assistant
计算机科学, 2021, 48(6A): 644-648. https://doi.org/10.11896/jsjkx.200700163
[15] 李嘉明, 赵阔, 屈挺, 刘晓翔.
基于知识图谱的区块链物联网领域研究分析
Research and Analysis of Blockchain Internet of Things Based on Knowledge Graph
计算机科学, 2021, 48(6A): 563-567. https://doi.org/10.11896/jsjkx.200600071
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!