Survey on Temporal Knowledge Graph Completion Research

doi:10.3778/j.issn.1002-8331.2404-0331

Abstract

Abstract: Currently, temporal knowledge graphs widely suffer from incompleteness, which severely restricts their application and development in downstream tasks. Temporal knowledge graph completion (TKGC) techniques aim to predict the missing links within these graphs to address the incompleteness issue. By incorporating the time dimension, TKGC seeks to capture temporal information, thus understanding how entities and relationships change over time, which helps in more accurately completing the temporal knowledge graph. This paper reviews the latest research advancements in TKGC based on different strategies for applying temporal information. Firstly, it provides a detailed explanation of the research background of TKGC, including problem definitions and key benchmark datasets. Secondly, it introduces and summarizes existing TKGC methods based on the proposed classification approach, and discusses the applications of TKGC in downstream tasks. Finally, this paper proposes current challenges and future research directions.

Key words: temporal knowledge graph, temporal knowledge graph completion (TKGC), knowledge graph embedding, link prediction

摘要： 目前时序知识图谱广泛存在不完备性等问题，这种不完备性问题严重制约了时序知识图谱在下游任务中的应用及发展。时序知识图谱补全（temporal knowledge graph completion，TKGC）技术能够预测其中缺失的链接，以解决不完备性问题。时序知识图谱补全通过考虑事实的时间维度，以期在捕捉时间信息的基础上获取实体及关系随时间推移发生的变化，这样有助于更准确地完成时序知识图谱补全任务。根据时间信息应用策略的不同对TKGC的最新研究进展进行综述。详尽阐述了TKGC的研究背景，包括问题定义、关键的基准数据集。基于所提出的分类方法介绍了现有的TKGC方法，总结了TKGC在下游任务中的应用。最后提出当前面临的挑战，同时展望未来可能的研究方向。

关键词: 时序知识图谱, 时序知识图谱补全（TKGC）, 知识图谱嵌入, 链接预测

XU Kaijia, LIU Lin, WANG Hailong, LIU Jing. Survey on Temporal Knowledge Graph Completion Research[J]. Computer Engineering and Applications, 2024, 60(22): 38-57.

许凯嘉, 柳林, 王海龙, 刘静. 时序知识图谱补全研究综述[J]. 计算机工程与应用, 2024, 60(22): 38-57.

References

[1] CAO Y, WANG X, HE X, et al. Unifying knowledge graph learning and recommendation: towards a better understanding of user preferences[C]//Proceedings of the 2019 World Wide Web Conference, 2019: 151-161.
[2] 赵晔辉, 柳林, 王海龙, 等. 知识图谱推荐系统研究综述[J]. 计算机科学与探索, 2023, 17(4): 771-791.
ZHAO Y H, LIU L, WANG H L, et al. Survey of knowledge graph recommendation system research[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(4): 771-791.
[3] HUANG X, ZHANG J, LI D, et al. Knowledge graph embedding based question answering[C]//Proceedings of the 12th ACM International Conference on Web Search and Data Mining, 2019: 105-113.
[4] DIETZ L, KOTOV A, MEIJ E. Utilizing knowledge graphs for text-centric information retrieval[C]//Proceedings of the 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, 2018: 1387-1390.
[5] 吴玉洁, 奚雪峰, 崔志明. 嵌入式静态知识图谱补全研究进展[J]. 计算机工程与应用, 2024, 60(12): 34-47.
WU Y J, XI X F, CUI Z M, et al. Advancements in embedded static knowledge graph completion research[J]. Computer Engineering and Applications, 2024, 60(12): 34-47.
[6] LI W, ZHOU H, DONG J, et al. Constructing low-redundant and high-accuracy knowledge graphs for education[C]//Proceedings of the 2022 International Conference on Web-Based Learning. Cham: Springer, 2022: 148-160.
[7] TRAN T K, GAD-ELRAB M H, STEPANOVA D, et al. Fast computation of explanations for inconsistency in large-scale knowledge graphs[C]//Proceedings of the Web Conference 2020, 2020: 2613-2619.
[8] LEBLAY J, CHEKOL M W. Deriving validity time in knowledge graph[C]//Companion Proceedings of the Web Conference 2018, 2018: 1771-1776.
[9] 徐涌鑫, 赵俊峰, 王亚沙, 等. 时序知识图谱表示学习[J]. 计算机科学, 2022, 49(9): 162-171.
XU Y X, ZHAO J F, WANG Y S, et al. Temporal knowledge graph representation learning[J]. Computer Science, 2022, 49(9): 162-171.
[10] JIN W, QU M, JIN X, et al. Recurrent event network: auto-
regressive structure inference over temporal knowledge graphs[J]. arXiv:1904.05530, 2019.
[11] TRIVEDI R, DAI H, WANG Y, et al. Know-evolve: deep temporal reasoning for dynamic knowledge graphs[C]//Proceedings of the 34th International Conference on Machine Learning, 2017: 3462-3471.
[12] 申宇铭, 杜剑峰. 时态知识图谱补全的方法及其进展[J]. 大数据, 2021, 7(3): 30-41.
SHEN Y M, DU J F. Temporal knowledge graph completion: methods and progress[J]. Big Data Research, 2021, 7(3): 30-41.
[13] 肖蕾, 李琪. 时序知识图谱补全方法研究综述[J]. 计算机工程与应用, 2024, 60(6): 43-54.
XIAO L, LI Q. Survey of temporal knowledge graph completion methods[J]. Computer Engineering and Applications, 2024, 60(6): 43-54.
[14] YANG Z, DING M, ZHOU C, et al. Understanding negative sampling in graph representation learning[C]//Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2020: 1666-1676.
[15] BORDES A, USUNIER N, GARCIA-DURAN A, et al. Translating embeddings for modeling multi-relational data[C]//Advances in Neural Information Processing Systems 26, 2013.
[16] SADEGHIAN A, ARMANDPOUR M, COLAS A, et al. Chronor: rotation based temporal knowledge graph embedding[C]//Proceedings of the 35th AAAI Conference on Artificial Intelligence, 2021: 6471-6479.
[17] LACROIX T, USUNIER N, OBOZINSKI G. Canonical tensor decomposition for knowledge base completion[C]//Proceedings of the 35th International Conference on Machine Learning, 2018: 2863-2872.
[18] LACROIX T, OBOZINSKI G, USUNIER N. Tensor decompositions for temporal knowledge base completion[J]. arXiv:2004.04926, 2020.
[19] XU C, CHEN Y Y, NAYYERI M, et al. Temporal knowledge graph completion using a linear temporal regularizer and multivector embeddings[C]//Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2021: 2569-2578.
[20] WANG J, WANG B, GAO J, et al. QDN: a quadruplet distributor network for temporal knowledge graph completion[J]. IEEE Transactions on Neural Networks and Learning Systems, 2023. DOI:10.1109/TNNLS.2023.3274230.
[21] LAUTENSCHLAGER J, SHELLMAN S, WARD M. ICEWS event aggregations[J]. Harvard Dataverse, 2015, 3(595): 28.
[22] LEETARU K, SCHRODT P A. GDELT: global data on events, location, and tone, 1979—2012[J]. ISA Annual Convention, 2013, 2(4): 1-49.
[23] HAN Z, DING Z, MA Y, et al. Learning neural ordinary equations for forecasting future links on temporal knowledge graphs[C]//Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021: 8352-8364.
[24] LI Z, JIN X, LI W, et al. Temporal knowledge graph reasoning based on evolutional representation learning[C]//Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2021: 408-417.
[25] LI Z, LIU X, WANG X, et al. TransO: a knowledge-driven representation learning method with ontology information constraints[J]. World Wide Web, 2023, 26(1): 297-319.
[26] GOEL R, KAZEMI S M, BRUBAKER M, et al. Diachronic embedding for temporal knowledge graph completion[C]//Proceedings of the 34th AAAI Conference on Artificial Intelligence, 2020: 3988-3995.
[27] HAN Z, MA Y, CHEN P, et al. DyERNIE: dynamic evolution of Riemannian manifold embeddings for temporal knowledge graph completion[J]. arXiv:2011.03984, 2020.
[28] WU J, CAO M, CHEUNG J C K, et al. TeMP: temporal message passing for temporal knowledge graph completion[J]. arXiv:2010.03526, 2020.
[29] XU C, NAYYERI M, ALKHOURY F, et al. TeRo: a time-aware knowledge graph embedding via temporal rotation[J]. arXiv:2010.01029, 2020.
[30] SUN H, ZHONG J, MA Y, et al. TimeTraveler: reinforcement learning for temporal knowledge graph forecasting[J]. arXiv:2109.04101, 2021.
[31] PENG C C, SHI X, YU R, et al. Multi-timescale history modeling for temporal knowledge graph completion[C]//Proceedings of the 2022 18th International Conference on Mobility, Sensing and Networking, 2022: 477-484.
[32] WANG Z, DU H T, YAO Q M, et al. ?Search to pass messages for temporal knowledge graph completion[C]//Findings of the Association for Computational Linguistics: EMNLP 2022, Abu Dhabi, 2022: 6160-6172.
[33] BAI L, ZHANG M, ZHANG H, et al. FTMF: few-shot temporal knowledge graph completion based on meta-optimization and fault-tolerant mechanism[J]. World Wide Web, 2023, 26(3): 1243-1270.
[34] ZUO Y, LIU Z, ZHOU Y, et al. Query-specific temporal knowledge graph representation learning model[C]//Proceedings of the 2022 IEEE Smartworld, Ubiquitous Intelligence & Computing, Scalable Computing & Communications, Digital Twin, Privacy Computing, Metaverse, Autonomous & Trusted Vehicles, 2022: 1316-1321.
[35] DING Z, MA Y, HE B, et al. A simple but powerful graph encoder for temporal knowledge graph completion[C]//Proceedings of the 2023 Intelligent Systems Conference. Cham: Springer, 2023: 729-747.
[36] NIE H, ZHAO X, YAO X, et al. Temporal-structural importance weighted graph convolutional network for temporal knowledge graph completion[J]. Future Generation Computer Systems, 2023, 143: 30-39.
[37] LI Z, WANG C, WANG X, et al. HJE: joint convolutional representation learning for knowledge hypergraph completion[J]. IEEE Transactions on Knowledge and Data Engineering, 2024.
[38] LEE Y C, LEE J H, LEE D, et al. Learning to compensate for lack of information: extracting latent knowledge for effective temporal knowledge graph completion[J]. Information Sciences, 2024, 654: 119857.
[39] GARCíA-DURáN A, DUMAN?I? S, NIEPERT M. Learning sequence encoders for temporal knowledge graph completion[J]. arXiv:1809.03202, 2018.
[40] CHEN X, JIA S, DING L, et al. Reasoning over temporal knowledge graph with temporal consistency constraints[J]. Journal of Intelligent & Fuzzy Systems, 2021, 40(6): 11941-11950.
[41] MONTELLA S, ROJAS-BARAHONA L, HEINECKE J. Hyperbolic temporal knowledge graph embeddings with relational and time curvatures[J]. arXiv:2106.04311, 2021.
[42] NIU G, LI B. Logic and commonsense-guided temporal knowledge graph completion[C]//Proceedings of the 37th AAAI Conference on Artificial Intelligence, 2023: 4569-4577.
[43] HOU X, MA R, YAN L, et al. T-GAE: a timespan-aware graph attention-based embedding model for temporal knowledge graph completion[J]. Information Sciences, 2023, 642: 119225.
[44] ZHANG H, BAI L. Few-shot link prediction for temporal knowledge graphs based on time-aware translation and attention mechanism[J]. Neural Networks, 2023, 161: 371-381.
[45] YU R, LIU T, YU J, et al. Combination of translation and rotation in dual quaternion space for temporal knowledge graph completion[C]//Proceedings of the 2023 International Joint Conference on Neural Networks, 2023: 1-8.
[46] BAI L, MA X, MENG X, et al. RoAN: a relation-oriented attention network for temporal knowledge graph completion[J]. Engineering Applications of Artificial Intelligence, 2023, 123: 106308.
[47] SINGH I, KAUR N, GAUR G. NeuSTIP: a novel neuro-symbolic model for link and time prediction in temporal knowledge graphs[J]. arXiv:2305.11301, 2023.
[48] 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.
[49] ZHANG F, CHEN H, SHI Y, et al. Joint framework for tensor decomposition-based temporal knowledge graph completion[J]. Information Sciences, 2024, 654: 119853.
[50] MENG X, BAI L, HU J, et al. Multi-hop path reasoning over sparse temporal knowledge graphs based on path completion and reward shaping[J]. Information Processing & Management, 2024, 61(2): 103605.
[51] PAN S, LUO L, WANG Y, et al. Unifying large language models and knowledge graphs: a roadmap[J]. IEEE Transactions on Knowledge and Data Engineering, 2024, 36(7): 3580-3599.
[52] LEE D H, AHRABIAN K, JIN W, et al. Temporal knowledge graph forecasting without knowledge using in-context learning[J]. arXiv:2305.10613, 2023.
[53] LIAO R, JIA X, MA Y, et al. GenTKG: generative forecasting on temporal knowledge graph[J]. arXiv:2310.07793, 2023.
[54] LUO R, GU T, LI H, et al. Chain of history: learning and forecasting with LLMs for temporal knowledge graph completion[J]. arXiv:2401.06072, 2024.
[55] NI R, MA Z, YU K, et al. Specific time embedding for temporal knowledge graph completion[C]//Proceedings of the 2020 IEEE 19th International Conference on Cognitive Informatics & Cognitive Computing, 2020: 105-110.
[56] XU Y, E HH, SONG M, et al. RTFE: a recursive temporal fact embedding framework for temporal knowledge graph completion[J]. arXiv:2009.14653, 2020.
[57] CAI L, JANOWICZ K, YAN B, et al. Time in a box: advancing knowledge graph completion with temporal scopes[C]//Proceedings of the 11th Knowledge Capture Conference, 2021: 121-128.
[58] LIU Y, HUA W, QU J, et al. Temporal knowledge completion with context-aware embeddings[J]. World Wide Web, 2021, 24: 675-695.
[59] MESSNER J, ABBOUD R, CEYLAN I I. Temporal knowledge graph completion using box embeddings[C]//Proceedings of the 36th AAAI Conference on Artificial Intelligence, 2022: 7779-7787.
[60] ABBOUD R, CEYLAN I, LUKASIEWICZ T, et al. BoxE: a box embedding model for knowledge base completion[C]//Advances in Neural Information Processing Systems 33, 2020: 9649-9661.
[61] LEE Y C, LEE J H, LEE D, et al. THOR: self-supervised temporal knowledge graph embedding via three-tower graph convolutional networks[C]//Proceedings of the 2022 IEEE International Conference on Data Mining, 2022: 1035-1040.
[62] DIKEOULIAS I, AMIN S, NEUMANN G. Temporal knowledge graph reasoning with low-rank and model-agnostic representations[J]. arXiv:2204.04783, 2022.
[63] DASGUPTA S S, RAY S N, TALUKDAR P. HyTE: hyperplane-based temporally aware knowledge graph embedding[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 2018: 2001-2011.
[64] LIU K, ZHANG Y. A temporal knowledge graph completion method based on balanced timestamp distribution[J]. arXiv:2108.13024, 2021.
[65] HE P, ZHOU G, LIU H, et al. Hyperplane-based time-aware knowledge graph embedding for temporal knowledge graph completion[J]. Journal of Intelligent & Fuzzy Systems, 2022, 42(6): 5457-5469.
[66] LI M, SUN Z, ZHANG W, et al. Leveraging semantic property for temporal knowledge graph completion[J]. Applied Intelligence, 2023, 53(8): 9247-9260.
[67] ZHANG F, ZHANG Z, AO X, et al. Along the time: timeline-traced embedding for temporal knowledge graph completion[C]//Proceedings of the 31st ACM International Conference on Information & Knowledge Management, 2022: 2529-2538.
[68] LI J, SU X, GAO G. TeAST: temporal knowledge graph embedding via archimedean spiral timeline[C]//Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023: 15460-15474.
[69] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Advances in Neural Information Processing Systems 30, 2017.
[70] HU S, WANG B, WANG J, et al. Transformer-based temporal knowledge graph completion[C]//Proceedings of the 2023 IEEE 3rd International Conference on Computer Communication and Artificial Intelligence, 2023: 443-448.
[71] ISLAKOGLU D S, CHEKOL M, VELEGRAKIS Y. Leveraging pre-trained language models for time interval prediction in text-enhanced temporal knowledge graphs[J]. arXiv:2309.16357, 2023.
[72] CHEN Z, XU C, SU F, et al. Incorporating structured sentences with time-enhanced BERT for fully-inductive temporal relation prediction[J]. arXiv:2304.04717, 2023.
[73] XU W, LIU B, PENG M, et al. Pre-trained language model with prompts for temporal knowledge graph completion[J]. arXiv:2305.07912, 2023.
[74] SOUZA COSTA T, GOTTSCHALK S, DEMIDOVA E. Event-QA: a dataset for event-centric question answering over knowledge graphs[C]//Proceedings of the 29th ACM International Conference on Information & Knowledge Management, 2020: 3157-3164.
[75] SHARMA A, SAXENA A, GUPTA C, et al. TwiRGCN: temporally weighted graph convolution for question answering over temporal knowledge graphs[J]. arXiv:2210.06281, 2022.
[76] ONG R, SUN J, ?ERBAN O, et al. TKGQA dataset: using question answering to guide and validate the evolution of temporal knowledge graph[J]. Data, 2023, 8(3): 61.
[77] SHANG C, WANG G, QI P, et al. Improving time sensitivity for question answering over temporal knowledge graphs[J]. arXiv:2203.00255, 2022.
[78] MAVROMATIS C, SUBRAMANYAM P L, IOANNIDIS V N, et al. TempOQR: temporal question reasoning over knowledge graphs[C]//Proceedings of the 36th AAAI Conference on Artificial Intelligence, 2022: 5825-5833.
[79] JIAO S, ZHU Z, WU W, et al. An improving reasoning network for complex question answering over temporal knowledge graphs[J]. Applied Intelligence, 2023, 53(7): 8195-8208.
[80] ZHANG W, GU T, SUN W, et al. Travel attractions recommendation with travel spatial-temporal knowledge graphs[C]//Proceedings of the 4th International Conference of Pioneering Computer Scientists, Engineers and Educators, Zhengzhou, Sep 21-23, 2018. Singapore: Springer, 2018: 213-226.
[81] MEZNI H. Temporal knowledge graph embedding for effective service recommendation[J]. IEEE Transactions on Services Computing, 2021, 15(5): 3077-3088.
[82] CHEN W, WAN H, GUO S, et al. Building and exploiting spatial-temporal knowledge graph for next POI recommendation[J]. Knowledge-Based Systems, 2022, 258: 109951.
[83] ZHANG X, CHENG Y, BI X, et al. TKMBR: temporal knowledge graph-based multi-behavior recommendation for e-commerce[J]. Research Square; 2023. DOI:10.21203/rs.3.rs-3144279/v1.
[84] ZONG C, ZHUANG Y, LU W, et al. Citation trajectory prediction via publication influence representation using temporal knowledge graph[J]. arXiv:2210.00450, 2022.
[85] WANG H, YU Q, LIU Y, et al. Spatio-temporal urban knowledge graph enabled mobility prediction[J]. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 2021, 5(4): 1-24.