知识图谱补全方法研究综述

doi:10.3778/j.issn.1002-8331.2311-0029

摘要/Abstract

摘要： 知识图谱是用来描述世界中存在的各种实体和概念以及他们之间的关系的一种语义网络，近年来被广泛应用于智能问答、智能推荐和信息检索等领域。目前，大多数知识图谱都具有不完整性，因此，知识图谱补全成为一项重要的任务。根据模型构造方法的不同，将知识图谱补全模型分为传统知识图谱补全模型、基于神经网络的知识图谱补全模型和基于元学习的知识图谱补全模型三类，对这三种知识图谱补全模型的分类情况进行介绍；总结知识图谱补全方法所使用的数据集和评价指标，并从各个模型优点和不足等方面对各类模型进行详细的对比分析。最后，对知识图谱补全进行归纳与总结，并展望未来的研究方向。

关键词: 知识图谱, 翻译模型, 张量分解, 神经网络, 元学习, 知识图谱补全

Abstract: Knowledge graph is a semantic network used to describe various entities and concepts that exist in the world, as well as their relationships. In recent years, it has been widely used in fields such as intelligent question answering, intelligent recommendation, and information retrieval. At present, most knowledge graphs are incomplete, therefore, knowledge graph completion has become an important task. Firstly, based on the different methods of model construction, knowledge graph completion models are divided into three categories: traditional knowledge graph completion models, knowledge graph completion models based on neural networks, and knowledge graph completion models based on meta learning. The classification of these three knowledge graph completion models is introduced. Then, the dataset and evaluation indicators used in the knowledge graph completion method are summarized, and detailed comparative analysis is conducted on various models from the perspectives of their advantages and disadvantages. Finally, the knowledge graph completion is summarized and summarized, and future research directions are prospected.

Key words: knowledge graph, translation model, tensor decomposition, neural network, meta learning, knowledge graph completion (KGC)

张文豪, 徐贞顺, 刘纳, 王振彪, 唐增金, 王正安. 知识图谱补全方法研究综述[J]. 计算机工程与应用, 2024, 60(12): 61-73.

ZHANG Wenhao, XU Zhenshun, LIU Na, WANG Zhenbiao, TANG Zengjin, WANG Zheng’an. Overview of Knowledge Graph Completion Methods[J]. Computer Engineering and Applications, 2024, 60(12): 61-73.

参考文献

[1] MAHDISOLTANI F, BIEGA J, SUCHANEK F. YAGO3: a knowledge base from multilingual wikipedias[C]//Proceedings of the 7th Biennial Conference on Innovative Data Systems Research, 2015.
[2] XU L, CHEN T, HOU Z, et al. Knowledge graph-based reinforcement federated learning for Chinese question and answering[J]. IEEE Transactions on Computational Social Systems, 2024, 11(1): 1035-1045.
[3] TANG C M, ZHAO Y G, YU X. Intelligent stock recommendation system based on generalized financial knowledge graph[C]//Proceedings of the 3rd International Conference on Intelligent Computing and Human-Computer Interaction, 2023: 332-338.
[4] XIAO Y, YANG G, ZHANG X. A new learning resource retrieval method based on multi-knowledge association mining[J]. International Journal of Emerging Technologies in Learning, 2023, 18(4): 104-119.
[5] AUER S, BIZER C, KOBILAROV G, et al. DBPedia: a nucleus for a Web of open data[C]//Proceedings of the 6th International Semantic Web Conference, 2nd Asian Semantic Web Conference, Busan, Korea, November 11-15, 2007: 722-735.
[6] BOLLACKER K, EVANS C, PARITOSH P, et al. Freebase: a collaboratively created graph database for structuring human knowledge[C]//Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data, 2008: 1247-1250.
[7] CHRISTIANE F. WordNet: an electronic lexical database[J]. Computational Linguistics, 1998, 5: 292-296.
[8] VRANDE?I? D, KR?TZSCH M. Wikidata: a free collaborative knowledgebase[J]. Communications of the ACM, 2014, 57(10): 78-85.
[9] SHEN T, ZHANG F, CHENG J. A comprehensive overview of knowledge graph completion[J]. Knowledge-Based Systems, 2022, 255: 109597.
[10] CHEN Z, WANG Y, ZHAO B, et al. Knowledge graph completion: a review[J]. IEEE Access, 2020, 8: 192435-192456.
[11] ZAMINI M, REZA H, RABIEI M. A review of knowledge graph completion[J]. Information, 2022, 13(8): 396.
[12] 吴国栋, 刘涵伟, 何章伟, 等. 知识图谱补全技术研究综述[J]. 小型微型计算机系统, 2023, 44(3): 471-482.
WU G D, LIU H W, HE Z W, et al. Review of knowledge graph completion technology[J]. Journal of Chinese Computer Systems, 2023, 44(3): 471-482.
[13] MIKOLOV T, CHEN K, CORRADO G, et al. Efficient estimation of word representations in vector space[J]. arXiv:1301.3781, 2013.
[14] BORDES A, USUNIER N, GARCIA-DURAN A, et al. Translating embeddings for modeling multi-relational data[C]//Advances in Neural Information Processing Systems, 2013.
[15] WANG Z, ZHANG J, FENG J, et al. Knowledge graph embedding by translating on hyperplanes[C]//Proceedings of the National Conference on Artificial Intelligence, 2014: 1112-1119.
[16] LIN Y, LIU Z, SUN M, et al. Learning entity and relation embeddings for knowledge graph completion[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2015: 2181-2187.
[17] 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.
[18] ZHANG Z, CAI J, ZHANG Y, et al. Learning hierarchy-aware knowledge graph embeddings for link prediction[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2020: 3065-3072.
[19] ZHANG J, YU H. Hierarchy-aware temporal knowledge graph embedding[C]//Proceedings of the 2022 IEEE International Conference on Knowledge Graph (ICKG), 2022: 373-380.
[20] LI J, SU X. TransERR: translation-based knowledge graph completion via efficient relation rotation[J]. arXiv:2306.14580, 2023.
[21] WANG Z, LI L, LI Q, et al. Multimodal data enhanced representation learning for knowledge graphs[C]//Proceedings of the 2019 International Joint Conference on Neural Networks (IJCNN), 2019: 1-8.
[22] NICKEL M, TRESP V, KRIEGEL H P. A three-way model for collective learning on multi-relational data[C]//Proceedings of the International Conference on Machine Learning, 2011 : 809-816.
[23] BALA?EVI? I, ALLEN C, HOSPEDALES T M. TuckER: tensor factorization for knowledge graph completion[J]. arXiv:1901.09590, 2019.
[24] TUCKER L R. Some mathematical notes on three-mode factor analysis[J]. Psychometrika, 1966, 31(3): 279-311.
[25] YANG B, YIH W, HE X, et al. Embedding entities and relations for learning and inference in knowledge bases[J]. arXiv:1412.6575, 2014.
[26] TROUILLON T, WELBL J, RIEDEL S, et al. Complex embeddings for simple link prediction[C]//Proceedings of the International Conference on Machine Learning, 2016: 2071-2080.
[27] KAZEMI S M, POOLE D. Simple embedding for link prediction in knowledge graphs[C]//Advances in Neural Information Processing Systems, 2018: 4289-4300.
[28] ZHANG Z, CAI J, WANG J. Duality-induced regularizer for tensor factorization based knowledge graph completion[C]//Advances in Neural Information Processing Systems, 2020: 21604-21615.
[29] YU M, GUO J, YU J, et al. BDRI: block decomposition based on relational interaction for knowledge graph completion[J]. Data Mining and Knowledge Discovery, 2023, 37(2): 767-787.
[30] 陈跃鹤, 谈川源, 陈文亮, 等. 结合多重嵌入表示的中文知识图谱补全[J]. 中文信息学报, 2023, 37(1): 54-63.
CHEN Y H, TAN C Y, CHEN W L, et al. Chinese knowledge graph complementation with multiple embeddings[J]. Journal of Chinese Information Processing, 2023,37 (1): 54-63.
[31] DETTMERS T, MINERVINI P, STENETORP P, et al. Convolutional 2D knowledge graph embeddings[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2018: 1811-1818.
[32] VASHISHTH S, SANYAL S, NITIN V, et al. Interacte: improving convolution-based knowledge graph embeddings by increasing feature interactions[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2020: 3009-3016.
[33] 周新, 郭敬楠, 宁博, 等. IntSE: 特征增强的知识图谱补全方法[J]. 小型微型计算机系统, 2023, 44(9): 1961-1965.
ZHOU X, GUO J N, NING B, et al. IntSE: feature enhanced knowledge graph completion method[J]. Journal of Chinese Computer Systems, 2023, 44(9): 1961-1965.
[34] YANG X, WANG N. A confidence-aware and path-enhanced convolutional neural network embedding framework on noisy knowledge graph[J]. Neurocomputing, 2023, 545: 126261.
[35] 邹长龙, 安敬民, 李冠宇. 基于邻域聚合与CNN的知识图谱实体类型补全[J]. 计算机工程, 2023, 49(3): 134-141.
ZOU C L, AN J M, LI G Y. Knowledge graph entity type completion based on neighborhood aggregation and CNN[J]. Computer Engineering, 2023, 49(3): 134-141.
[36] SCHLICHTKRULL M, KIPF T N, BLOEM P, et al. Modeling relational data with graph convolutional networks[C]//Proceedings of the 15th Extended Semantic Web Conference(ESWC?2018), Heraklion, Greece, June 3-7, 2018: 593-607.
[37] YE R, LI X, FANG Y, et al. A vectorized relational graph convolutional network for multi-relational network alignment[C]//Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), 2019: 4135-4141.
[38] VASHISHTH S, SANYAL S, NITIN V, et al. Composition-based multi-relational graph convolutional networks[J]. arXiv:1911.03082, 2019.
[39] ZEB A, SAIF S, CHEN J, et al. Complex graph convolutional network for link prediction in knowledge graphs[J]. Expert Systems with Applications, 2022, 200: 116796.
[40] 张贞港, 余传明. 基于实体与关系融合的知识图谱补全模型研究[J]. 数据分析与知识发现, 2023, 7(2): 15-25.
ZHANG Z G, YU C M. Knowledge graph completion model based on entity and relation fusion[J]. Data Analysis and Knowledge Discovery, 2023, 7(2): 15-25.
[41] ZHANG X, ZHANG C, GUO J, et al. Graph attention network with dynamic representation of relations for knowledge graph completion[J]. Expert Systems with Applications, 2023, 219: 119616.
[42] ZHAI H, LV X, HOU Z, et al. MLSFF: multi-level structural features fusion for multi-modal knowledge graph completion[J]. Mathematical Biosciences and Engineering, 2023, 20(8): 14096-14116.
[43] VU T, NGUYEN T D, NGUYEN D Q, et al. A capsule network-based embedding model for knowledge graph completion and search personalization[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1:Long and Short Papers), 2019: 2180-2189.
[44] CHENG J, YANG Z, DANG J, et al. Representation learning of knowledge graphs with multi-scale capsule network[C]//Proceedings of the 20th International Conference on Intelligent Data Engineering and Automated Learning, Manchester, UK, November 14-16, 2019: 282-290.
[45] CHENG J, ZHANG F, YANG Z. Knowledge graph representation learning with multi-scale capsule-based embedding model incorporating entity descriptions[J]. IEEE Access, 2020, 8: 203028-203038.
[46] LI J, HOU J, ZHOU C. An improved capsule network-based embedding model for knowledge graph completion[C]//Proceedings of the 33rd Chinese Control and Decision Conference (CCDC), 2021: 2247-2251.
[47] MA H, JIANG X, WEI X, et al. A Multi-scale disperse dynamic routing capsule network knowledge graph embedding model based on relational memory[C]//Proceedings of the 2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2022: 2540-2545.
[48] XIONG W, YU M, CHANG S, et al. One-shot relational learning for knowledge graphs[J]. arXiv:1808.09040, 2018.
[49] ZHANG C, YAO H, HUANG C, et al. Few-shot knowledge graph completion[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2020: 3041-3048.
[50] YUAN X, XU C, LI P, et al. Relational learning with hierarchical attention encoder and recoding validator for few-shot knowledge graph completion[C]//Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing, 2022: 786-794.
[51] LI Y, YU K, ZHANG Y, et al. Learning relation-specific representations for few-shot knowledge graph completion[J]. arXiv:2203.11639, 2022.
[52] LI Z, GENG P, CAO S, et al. Few-shot knowledge graph completion based on data enhancement[C]//Proceedings of the 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2022: 1607-1611.
[53] SHENG J, GUO S, CHEN Z, et al. Adaptive attentional network for few-shot knowledge graph completion[J]. arXiv:2010.09638, 2020.
[54] LI Q, YAO J, TANG X, et al. Capsule neural tensor networks with multi-aspect information for few-shot knowledge graph completion[J]. Neural Networks, 2023, 164: 323-334.
[55] ZHANG X, LIANG X, ZHENG X, et al. MULTIFORM: few-shot knowledge graph completion via multi-modal contexts[C]//Proceedings of theJoint European Conference on Machine Learning and Knowledge Discovery in Databases, 2022: 172-187.
[56] QIN P, WANG X, CHEN W, et al. Generative adversarial zero-shot relational learning for knowledge graphs[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2020: 8673-8680.
[57] GENG Y, CHEN J, CHEN Z, et al. OntoZSL: ontology-enhanced zero-shot learning[C]//Proceedings of the Web Conference (WWW’21), 2021: 3325-3336.
[58] WANG Z, CHEN C, TANG K. Zero-shot knowledge graph completion for recommendation system[C]//Proceedings of the 23rd International Conference on Intelligent Data Engineering and Automated Learning (IDEAL 2022), Manchester, UK, November 24-26, 2022: 188-198.
[59] DU Z. Zero or few shot knowledge graph completions by text enhancement with multi-grained attention[C]//Proceedings of the IEEE 33rd International Conference on Tools with Artificial Intelligence (ICTAI), 2021: 1050-1058.
[60] LI X, MA J, YU J, et al. A structure-enhanced generative adversarial network for knowledge graph zero-shot relational learning[J]. Information Sciences, 2023, 629: 169-183.
[61] CAI Y, LI Y, FANG Z, et al. Entity completion for industrial knowledge graph based on zero-shot learning[J]. Available at SSRN 4450233.
[62] YAO L, PENG J, MAO C, et al. Exploring large language models for knowledge graph completion[J]. arXiv:2308. 13916, 2023.
[63] ZHANG Y, CHEN Z, ZHANG W, et al. Making large language models perform better in knowledge graph completion[J]. arXiv:2310.06671, 2023.
[64] ZHAO W X, ZHOU K, LI J, et al. A survey of large language models[J]. arXiv:2303.18223, 2023.
[65] XIE X, LI Z, WANG X, et al. Lambdakg: a library for pre-trained language model-based knowledge graph embeddings[J]. arXiv:2210.00305, 2022.