多元关系知识表示学习方法研究综述

doi:10.3778/j.issn.1002-8331.2404-0438

摘要/Abstract

摘要： 知识表示学习旨在将知识库中的实体和关系转化为机器能够理解和处理的形式，从而提升模型的分析与推理能力。针对传统二元关系知识表示学习的局限，如忽略高阶关系、缺乏扩展性和有限的表达力，多元关系知识表示学习方法应运而生。全面综述了多元关系知识表示学习方法。梳理和分析了知识表示学习相关综述工作;阐释了知识表示学习和链接预测的基本概念，并根据超图、角色、超关系这三种表示形式，定义了多元关系知识表示学习任务;从基于平移距离、张量分解、卷积神经网络、图神经网络和其他类型五类方法，展示了该领域的研究进展；介绍了常用的数据集与评价指标，并通过链接预测任务评估了不同模型的性能；探讨了目前方法存在的问题和挑战，并对未来的研究方向提出了展望。

关键词: 知识表示学习, 二元关系, 多元关系, 链接预测

Abstract: Knowledge representation learning aims to transform entities and relationships in knowledge base into a form that machines can understand and process, thereby enhancing the analytical and reasoning capabilities of the model. Addressing the limitations of traditional binary relational knowledge representation learning, such as ignoring higher-order relations, lack of scalability, and limited expressiveness, n-ary relational knowledge representation learning methods have emerged. This paper provides a comprehensive review of n-ary relational knowledge representation learning methods. It organizes and analyzes related survey works on knowledge representation learning. It explains the basic concepts of knowledge representation learning and link prediction, and defines the task of n-ary relational knowledge representation learning based on three forms of representation: hypergraphs, roles, and hyper-relations. It demonstrates the research progress in this field through five categories of methods: translation distance-based, tensor decomposition-based, convolutional neural networks, graph neural networks, and other types. It introduces commonly used datasets and evaluation metrics and evaluates the performance of different models through link prediction tasks. It discusses the current problems and challenges of the methods and proposes prospects for future research directions.

Key words: knowledge representation learning, binary relation, n-ary relation, link prediction

杭婷婷, 丁海超, 郭亚, 冯钧. 多元关系知识表示学习方法研究综述[J]. 计算机工程与应用, 2025, 61(3): 62-83.

HANG Tingting, DING Haichao, GUO Ya, FENG Jun. Review on Knowledge Representation Learning Methods for N-Ary Relation[J]. Computer Engineering and Applications, 2025, 61(3): 62-83.

参考文献

[1] 李德仁, 张过, 蒋永华, 等. 论大数据视角下的地球空间信息学的机遇与挑战[J]. 大数据, 2022, 8(2): 3-14.
LI D R, ZHANG G, JIANG Y H, et al. Opportunities and challenges of geo-spatial information science from the perspective of big data[J]. Big Data Research, 2022, 8(2): 3-14.
[2] 齐金山, 梁循, 李志宇, 等. 大规模复杂信息网络表示学习: 概念, 方法与挑战[J]. 计算机学报, 2018, 41(10): 2394-2420.
QI J S, LIANG X, LI Z Y. et al. Representation learning of large-scale complex information network: concepts, methods and challenges[J]. Chinese Journal of Computers, 2018, 41(10): 2394-2420.
[3] XIONG C, POWER R, CALLAN J. Explicit semantic ranking for academic search via knowledge graph embedding[C]//Proceedings of the 26th International Conference on World Wide Web, 2017: 1271-1279.
[4] XIONG C, CALLAN J, LIU T Y. Word-entity duet representations for document ranking[C]//Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2017: 763-772.
[5] LIU Z, XIONG C, SUN M, et al. Entity-duet neural ranking: understanding the role of knowledge graph semantics in neural information retrieval[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, 2018: 2395-2405.
[6] ZHANG Y, LI P, LIANG H, et al. Fact-tree reasoning for n-ary question answering over knowledge graphs[C]//Findings of the Association for Computational Linguistics, 2022: 788-802.
[7] CHEN X, CHEN F, MENG F, et al. Unsupervised knowledge selection for dialogue generation[C]//Findings of the Association for Computational Linguistics, 2021: 1230-1244.
[8] MENG C, REN P, CHEN Z, et al. Initiative-aware self-supervised learning for knowledge-grounded conversations[C]//Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2021: 522-532.
[9] ZHANG C, WANG H, JIANG F, et al. Adapting to context-aware knowledge in natural conversation for multi-turn response selection[C]//Proceedings of the Web Conference 2021, 2021: 1990-2001.
[10] ZIRUI C, XIN W, LIN W, et al. Survey of open-domain knowledge graph question answering[J]. Journal of Frontiers of Computer Science & Technology, 2021, 15(10): 1843-1869.
[11] 曾宇涛, 林谢雄, 靳小龙, 等. 基于多维信息融合的知识库问答实体链接[J]. 模式识别与人工智能, 2019, 32(7): 642-651.
ZENG Y T, LIN X X, JIN X L, et al. Multi-dimensional information integration based entity linking for knowledge base question answering[J]. Pattern Recognition and Artificial Intelligence, 2019, 32(7): 642-651.
[12] 王智悦, 于清, 王楠, 等. 基于知识图谱的智能问答研究综述[J].计算机工程与应用, 2020, 56(23): 1-11.
WANG Z Y, YU Q, WANG N, et al. Survey of intelligent question answering research based on knowledge graph[J]. Computer Engineering and Applications, 2020, 56(23): 1-11.
[13] HU B, SHI C, ZHAO W X, et al. Leveraging meta-path based context for top-n recommendation with a neural co-attention model[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2018: 1531-1540.
[14] 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.
[15] 黄恒琪, 于娟, 廖晓, 等. 知识图谱研究综述[J]. 计算机系统应用, 2019, 28(6): 1-12.
HUANG H Q, YU J, LIAO X. et al. Review on knowledge graphs[J]. Computer Systems & Applications, 2019, 28(6): 1-12.
[16] 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.
[17] HOFFART J, SUCHANEK F M, BERBERICH K, et al. Yago2: a spatially and temporally enhanced knowledge base from Wikipedia[J]. Artificial Intelligence, 2013, 194: 28-61.
[18] MAHDISOLTANI F, BIEGA J, SUCHANEK F M. Yago3: a knowledge base from multilingual wikipedias[C]//Proceedings of the 7th Biennial Conference on Innovative Data Systems Research, 2015.
[19] AUER S, BIZER C, KOBILAROV G, et al. DBpedia: a nucleus for a web of open data[C]//Proceedings of the International Semantic Web Conference, 2007: 722-735.
[20] 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.
[21] PUJARA J, MIAO H, GETOOR L, et al. Knowledge graph identification[C]//Proceedings of the 12th International Semantic Web Conference, 2013: 542-557.
[22] VRANDE?I? D, KR?TZSCH M. Wikidata: a free collaborative knowledgebase[J]. Communications of the ACM, 2014, 57(10): 78-85.
[23] DONG X, GABRILOVICH E, HEITZ G, et al. Knowledge vault: a web-scale approach to probabilistic knowledge fusion[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2014: 601-610.
[24] WEST R, GABRILOVICH E, MURPHY K, et al. Knowledge base completion via search-based question answering[C]//Proceedings of the 23rd International Conference on World Wide Web, 2014: 515-526.
[25] 张正航, 钱育蓉, 行艳妮, 等. 知识表示学习方法研究综述[J]. 计算机应用研究, 2021, 38(4): 961-967.
ZHANG Z H, QIAN Y R, XING Y N, et al. Survey of knowledge representation learning methods[J]. Application Research of Computers, 2021, 38(4): 961-967.
[26] XU B, CEN K, HUANG J, et al. A survey on graph convolutional neural network[J]. Chinese Journal of Computers, 2020, 43(5): 755-780.
[27] 吴博, 梁循, 张树森, 等. 图神经网络前沿进展与应用[J]. 计算机学报, 2022, 45(1): 35-68.
WU B, LIANG X, ZHANG S S, et al. Advances and applications in graph neural network[J]. Chinese Journal of Computers, 2022, 45(1): 35-68.
[28] WEISS K, KHOSHGOFTAAR T M, WANG D D. A survey of transfer learning[J]. Journal of Big Data, 2016, 1(3): 1-40.
[29] ZHUANG F, QI Z, DUAN K, et al. A comprehensive survey on transfer learning[J]. Proceedings of the IEEE, 2020, 109(1): 43-76.
[30] JING L, TIAN Y. Self-supervised visual feature learning with deep neural networks: a survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 43(11): 4037-4058.
[31] LIN Y, HAN X, XIE R, et al. Knowledge representation learning: a quantitative review[J]. arXiv:1812.10901, 2018.
[32] 官赛萍, 靳小龙, 贾岩涛, 等. 面向知识图谱的知识推理研究进展[J]. 软件学报, 2018, 29(10): 2966-2994.
GUAN S P, JIN X L, JIA Y T, et al. Knowledge reasoning over knowledge graph: a survey[J]. Journal of Software, 2018, 29(10): 2966-2994.
[33] 王子悦, 陈华辉. 知识表示学习综述[J]. 无线通信技术, 2019, 28(4): 55-60.
WANG Z Y, CHEN H H. A review of knowledge representation learning[J]. Wireless Communication Technology, 2019, 28(4): 55-60.
[34] DAI Y, WANG S, XIONG N N, et al. A survey on knowledge graph embedding: approaches, applications and benchmarks[J]. Electronics, 2020, 9(5): 750.
[35] 张正航, 钱育蓉, 行艳妮, 等. 基于TransE的表示学习方法研究综述[J]. 计算机应用研究, 2021, 38(3): 656-663.
ZHANG Z H, QIAN Y R, XING Y N, et al. Survey of representation learning methods based on TransE[J]. Application Research of Computers, 2021, 38(3): 656-663.
[36] 杨大伟, 周刚, 卢记仓, 等. 基于知识表示学习的知识图谱补全研究综述[J]. 信息工程大学学报, 2021, 22(5): 558-565.
YANG D W, ZHOU G, LU J C, et al. Review of knowledge graph completion based on knowledge representation learning[J]. Journal of Information Engineering University, 2021, 22(5): 558-565.
[37] 舒世泰, 李松, 郝晓红, 等. 知识图谱嵌入技术研究进展[J]. 计算机科学与探索, 2021, 15(11): 2048-2062.
SHU S T, LI S, HAO X H, et al. Knowledge graph embedding technology: a review[J]. Journal of Frontiers of Computer Science and Technology, 2021, 15(11): 2048-2062.
[38] 田玲, 张谨川, 张晋豪, 等. 知识图谱综述——表示、构建、推理与知识超图理论[J]. 计算机应用, 2021, 41(8): 2161-2186.
TIAN L, ZHANG J C, ZHANG J H, et al. Knowledge graph survey: representation, construction, reasoning and knowledge hypergraph theory[J]. Journal of Computer Applications, 2021, 41(8): 2161-2186.
[39] 王瑞, 李智杰, 李昌华, 等. 面向链接预测的知识图谱嵌入研究综述[J]. 计算机测量与控制, 2022, 30(9): 8-16.
WANG R, LI Z J, LI C H, et al. A survey of knowledge graph embedding study for link prediction[J]. Computer Measurement & Control, 2022, 30(9): 8-16.
[40] 徐有为, 张宏军, 程恺, 等. 知识图谱嵌入研究综述[J]. 计算机工程与应用, 2022, 58(9): 30-50.
XU Y W, ZHANG H J, CHENG K, et al. Comprehensive survey on knowledge graph embedding[J]. Computer Engineering and Applications, 2022, 58(9): 30-50.
[41] 李志飞, 赵月, 张龑.基于表示学习的知识图谱推理研究综述[J].计算机科学, 2023, 50(3):94-113.
LI Z F, ZHAO Y, ZHANG Y. Survey of knowledge graph reasoning based on representation learning[J]. Computer Science, 2023, 50(3): 94-113.
[42] 杜雪盈, 刘名威, 沈立炜, 等. 面向链接预测的知识图谱表示学习方法研究综述[J]. 软件学报, 2023, 35(1):87-117.
DU X Y, LIU M W, SHEN L W, et al. Survey on representation learning methods of knowledge graph for link prediction[J]. Journal of Software, 2023, 35(1):87-117.
[43] 张祎, 孟小峰. InterTris: 三元交互的领域知识图谱表示学习[J]. 计算机学报, 2021, 44(8): 1535-1548.
ZHANG Y, MENG X F. InterTris：specific domain knowledge graph representation learning by interaction among triple elements[J]. Chinese Journal of Computers, 2021, 44(8): 1535-1548.
[44] MIKOLOV T, CHEN K, CORRADO G, et al. Efficient estimation of word representations in vector space[J]. arXiv:1301.3781, 2013.
[45] WEN J, LI J, MAO Y, et al. On the representation and embedding of knowledge bases beyond binary relations[C]//Proceedings of the 25th International Joint Conference on Artificial Intelligence, 2016: 1300-1307.
[46] 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.
[47] ZHANG R, LI J, MEI J, et al. Scalable instance reconstruction in knowledge bases via relatedness affiliated embedding[C]//Proceedings of the 2018 World Wide Web Conference, 2018: 1185-1194.
[48] ABBOUD R, CEYLAN I, LUKASIEWICZ T, et al. BoxE: a box embedding model for knowledge base completion[C]//Advances in Neural Information Proceedings Systems, 2020: 9649-9661.
[49] XIONG B, NAYYERI M, PAN S, et al. Shrinking embeddings for hyper-relational knowledge graphs[C]//Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, 2023: 13306-13320.
[50] LIU Y, YAO Q, LI Y. Generalizing tensor decomposition for n-ary relational knowledge bases[C]//Proceedings of the Web Conference 2020, 2020: 1104-1114.
[51] 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 Proceedings and 9th International Joint Conference on Natural Language Proceedings (EMNLP-IJCNLP), 2019: 5184-5193.
[52] PAN Y, XU J, WANG M, et al. Compressing recurrent neural networks with tensor ring for action recognition[C]//Proceedings of the 33rd AAAI Conference on Artificial Intelligence, 2019: 4683-4690.
[53] WANG W, SUN Y, ERIKSSON B, et al. Wide compression: tensor ring nets[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 9329-9338.
[54] DI S, YAO Q, CHEN L. Searching to sparsify tensor decomposition for n-ary relational data[C]//Proceedings of the Web Conference 2021, 2021: 4043-4054.
[55] Z?LLER M A, HUBER M F. Benchmark and survey of automated machine learning frameworks[J]. Journal of Artificial Intelligence Research, 2021, 70: 409-472.
[56] YAO Q, WANG M, CHEN Y, et al. Taking human out of learning applications: a survey on automated machine learning[J]. arXiv:1810.13306, 2018.
[57] PANG J, QIN H C, LIU Y, et al. Two birds with one stone: a link prediction model for knowledge hypergraph based on fully-connected tensor decomposition[C]//Proceedings of the International Conference on Advanced Data Mining and Applications, 2023: 78-90.
[58] ZHENG Y B, HUANG T Z, ZHAO X L, et al. Fully-connected tensor network decomposition and its application to higher-order tensor completion[C]//Proceedings of the 35th AAAI Conference on Artificial Intelligence, 2021: 11071-11078.
[59] LIU Y, YAO Q, LI Y. Role-aware modeling for n-ary relational knowledge bases[C]//Proceedings of the Web Conference 2021, 2021: 2660-2671.
[60] WANG C, WANG X, LI Z, et al. HyConvE: a novel embedding model for knowledge hypergraph link prediction with convolutional neural networks[C]//Proceedings of the ACM Web Conference 2023, 2023: 188-198.
[61] NGUYEN T D, NGUYEN D Q, PHUNG D. A novel embedding model for knowledge base completion based on convolutional neural network[C]//Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2018: 327-333.
[62] 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.
[63] GUAN S, JIN X, WANG Y, et al. Link prediction on n-ary relational data[C]//Proceedings of the World Wide Web Conference, 2019: 583-593.
[64] LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015: 3431-3440.
[65] 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.
[66] FATEMI B, TASLAKIAN P, VAZQUEZ D, et al. Knowledge hypergraphs: prediction beyond binary relations[C]//Proceedings of the 29th International Joint Conference on Artificial Intelligence, 2021: 2191-2197.
[67] GUAN S, JIN X, GUO J, et al. Link prediction on n-ary relational data based on relatedness evaluation[J]. IEEE Transactions on Knowledge and Data Engineering, 2021, 35(1): 672-685.
[68] ROSSO P, YANG D, CUDRé-MAUROUX P. Beyond triplets: hyper-relational knowledge graph embedding for link prediction[C]//Proceedings of the Web Conference 2020, 2020: 1885-1896.
[69] GUAN S, JIN X, GUO J, et al. NeuInfer: knowledge inference on n-ary facts[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020: 6141-6151.
[70] LI L, YUAN P, WANG Y, et al. HIAE: hyper-relational interaction aware embedding for link prediction[C]//Proceedings of the 2022 IEEE 34th International Conference on Tools with Artificial Intelligence, 2022: 355-360.
[71] LU Y, YANG D, WANG P, et al. Schema-aware hyper-relational knowledge graph embeddings for link[J]. IEEE Transactions on Knowledge and Data Engineering, 2024, 36(6): 2614-2628.
[72] WANG C, LI X, GAN T, et al. Hyper-relational knowledge graph embedding based on type constraints[C]//Proceedings of the 2023 16th International Conference on Advanced Computer Theory and Engineering, 2023: 54-58.
[73] GALKIN M, TRIVEDI P, MAHESHWARI G, et al. Message passing for hyper-relational knowledge graphs[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Proceedings, 2020: 7346-7359.
[74] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Proceedings of the 31st Conference on Neural Information Proceedings Systems, 2017: 5998-6008.
[75] YU D, YANG Y. Improving hyper-relational knowledge graph completion[J]. arXiv:2104.08167, 2021.
[76] WANG Q, WANG H, LYU Y, et al. Link prediction on n-ary relational facts: a graph-based approach[C]//Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, 2021: 396-407.
[77] SHOMER H, JIN W, LI J, et al. Learning representations for hyper-relational knowledge graphs[C]//Proceedings of the International Conference on Advances in Social Networks Analysis and Mining, 2023: 253-257.
[78] GAO J, LIU X, CHEN Y, et al. MHGCN: multiview highway graph convolutional network for cross-lingual entity alignment[J]. Tsinghua Science and Technology, 2021, 27(4): 719-728.
[79] LIU Y, YANG S, DING J, et al. Two birds, one stone: an equivalent transformation for hyper?relational knowledge graph modeling[EB/OL]. (2023-02-14) [2024-06-23]. https://openreview.net/pdf?id=e3U6bGsfcA.
[80] WANG P, CHEN J, SU L, et al. N-ary relation prediction based on knowledge graphs with important entity detection[J]. Expert Systems with Applications, 2023, 221: 119755.
[81] DI S, CHEN L. Message function search for knowledge graph embedding[C]//Proceedings of the ACM Web Conference, 2023: 2633-2644.
[82] LUO H, HAIHONG E, YANG Y, et al. HAHE: hierarchical attention for hyper-relational knowledge graphs in global and local level[C]//Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, 2023: 8095-8107.
[83] HU Z, GUTIéRREZ-BASULTO V, XIANG Z, et al. HyperFormer: enhancing entity and relation interaction for hyper-relational knowledge graph completion[C]//Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, 2023: 803-812.
[84] LU Y, DENG B, YU W, et al. HELIOS: hyper-relational schema modeling from knowledge graphs[C]//Proceedings of the 31st ACM International Conference on Multimedia, 2023: 4053-4064.
[85] YAN S, ZHANG Z, SUN X, et al. PolygonE: modeling n-ary relational data as gyro-polygons in hyperbolic space[C]//Proceedings of the 36th AAAI Conference on Artificial Intelligence, 2022: 4308-4317.
[86] BRAYNE A, WIATRAK M, CORNEIL D. On masked language models for contextual link prediction[C]//Proceedings of Deep Learning Inside Out (DeeLIO 2022): The 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures, 2022: 87-99.
[87] ZHANG Y, XU H, ZHANG X, et al. TRFR: a ternary relation link prediction framework on knowledge graphs[J]. Ad Hoc Networks, 2021, 113: 102402.
[88] ZHANG Y, YANG Q. A survey on multi-task learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2021, 34(12): 5586-5609.
[89] MILLER T. Explanation in artificial intelligence: insights from the social sciences[J]. Artificial Intelligence, 2019, 267: 1-38.
[90] 侯中妮, 靳小龙, 陈剑赟, 等.知识图谱可解释推理研究综述[J].软件学报, 2022, 33(12): 4644-4667.
HOU Z N, JIN X L, CHEN J Y, et al. Survey of interpretable reasoning on knowledge graphs[J]. Journal of Software, 2022, 33(12): 4644-4667.
[91] XU K, HU W, LESKOVEC J, et al. How powerful are graph neural networks?[J]. arXiv:1810.00826, 2018.
[92] FALOUTSOS M, FALOUTSOS P, FALOUTSOS C. On power-law relationships of the internet topology[J]. ACM SIGCOMM Computer Communication Review, 1999, 29(4): 251-262.
[93] KUMAR A A. Semantic memory: a review of methods, models, and current challenges[J]. Psychonomic Bulletin & Review, 2021, 28(1): 40-80.
[94] KOLYVAKIS P, KALOUSIS A, KIRITSIS D. HyperKG: hyperbolic knowledge graph embeddings for knowledge base completion[J]. arXiv:1908.04895, 2019.