时序知识图谱补全方法研究综述

doi:10.3778/j.issn.1002-8331.2307-0083

摘要/Abstract

摘要： 知识图谱补全是近年来的研究热点，在下游应用中，如知识问答、推荐系统和智能搜索等都有着广泛的应用前景。然而，大部分补全方法忽略了知识图谱的动态特性，其中许多的事实都会随着时间的变化而发生改变。新兴的时序知识图谱补全方法考虑到了以往补全方法的局限性，在其中加入了时间信息，使得知识图谱随时间的动态变化也能很好地被捕获。针对时序知识图谱补全方法在社交网络、交通运输、金融贸易等动态变化且具有复杂时间依赖特性的研究领域所拥有的巨大潜力，梳理了时序知识图谱补全技术。根据模型主要使用原理的不同，总结了基于逻辑规则、张量分解、平移模型、神经网络、深度强化学习和语言模型的补全方法，归纳了现有方法的常用评价指标、公开数据集、核心思想、优缺点、适用场景以及在对应静态模型上的改进。最后，对时序知识图谱补全方法的未来研究方向进行了展望。

关键词: 知识图谱, 知识推理, 链接预测, 时序知识图谱补全

Abstract: Knowledge graph completion is a research hotspot in recent years, and it has broad application prospects in downstream applications, such as knowledge question answering, recommended system and intelligent search, etc. However, most of the completion methods ignore the dynamic characteristics of the knowledge graphs, many of which the facts will change over time. The new temporal knowledge graph completion methods take into account the limitations of the previous by incorporating time information, enabling the dynamic changes of the knowledge graph over time to be well captured. In response to the big potential of temporal knowledge graph completion methods in research fields such as social networks, transportation, finance and trade with complex time dependent characteristics, this paper summarizes temporal knowledge graph completion techniques. Based on the main different principle of model usage, completion methods based on logical rules, tensor decomposition, translation model, neural networks, deep reinforcement learning, and language model are summarized. The commonly used evaluation indicators, datasets, core ideas, advantages and disadvantages, applicable scenarios, and improvements on corresponding static models of existing methods are summarized. Finally, it looks forward to the future research directions.

Key words: knowledge graph, knowledge reasoning, link prediction, temporal knowledge graph completion

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 Lei, LI Qi. Survey of Temporal Knowledge Graph Completion Methods[J]. Computer Engineering and Applications, 2024, 60(6): 43-54.

参考文献

[1] 宋浩楠, 赵刚, 孙若莹. 基于深度强化学习的知识推理研究进展综述[J]. 计算机工程与应用, 2022, 58(1): 12-25.
SONG H N, ZHAO G, SUN R Y. Developments of knowledge reasoning based on deep reinforcement learning[J]. Computer Engineering and Applications, 2022, 58(1): 12-25.
[2] 杨喆, 许甜, 靳哲, 等. 基于知识图谱的羊群疾病问答系统的构建与实现[J]. 华中农业大学学报, 2023, 42(3): 63-70.
YANG Z, XU T, JIN Z, et al. Construction and application of knowledge graph of sheep & goat disease[J]. Journal of Huazhong Agricultural University, 2023, 42(3): 63-70.
[3] 张雅晴, 单中原, 赵俊峰, 等. 基于智能映射推荐的知识图谱实例构建与演化方法[J]. 计算机科学, 2023, 50(6): 142-150.
ZHANG Y Q, SHAN Z Y, ZHAO J F, et al. Intelligent mapping recommendation-based knowledge graph instance construction and evolution method[J]. Computer Science, 2023, 50(6): 142-150.
[4] 徐蕙, 及洪泉, 姚晓明, 等. 智能电网中基于知识图谱的语义搜索算法[J]. 实验室研究与探索, 2021, 40(4): 71-74.
XU H, JI H Q, YAO X M, et al. Knowledge graph-based semantic search algorithm in smart grid[J]. Research and Exploration in Laboratory, 2021, 40(4): 71-74.
[5] 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.
[6] CAI B, XIANG Y, GAO L, et al. Temporal knowledge graph completion: a survey[J]. arXiv:2201.08236, 2022.
[7] JIN W, QU M, JIN X, et al. Recurrent event network: autoregressive structure inference over temporal knowledge graphs[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Press (EMNLP), 2020: 6669-6683.
[8] TRIVEDI R, DAI H, WANG Y, et al. Know-Evolve: deep temporal reasoning for dynamic knowledge graphs[J]. arXiv:1705.05742, 2017.
[9] 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.
[10] 马瑞新, 李泽阳, 陈志奎, 等. 知识图谱推理研究综述[J]. 计算机科学, 2022, 49(S1): 74-85.
MA R X, LI Z Y, CHEN Z K, et al. Review of reasoning on knowledge graph[J]. Computer Science, 2022, 49(S1): 74-85.
[11] 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.
[12] 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.
[13] 程开原, 姚俊萍, 李晓军, 等. 时态网络中知识图谱推荐: 关键技术与研究进展[J]. 中国电子科学研究院学报, 2021, 16(2): 174-183.
CHENG K Y, YAO J P, LI X J, et al. Recommendation based on knowledge graph in temporal networks: key technologies and progress[J]. Journal of China Academy of Electronics and Information Technology, 2021, 16(2): 174-183.
[14] 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.
[15] 汪雨竹, 彭涛, 朱蓓蓓, 等. 基于元学习的小样本知识图谱补全[J]. 吉林大学学报 (理学版), 2023, 61(3): 623-630.
WANG Y Z, PENG T, ZHU B B, et al. Few-shot knowledge graph completion based on meta learning[J]. Journal of Jilin University (Science Edition), 2023, 61(3): 623-630.
[16] 李凤英, 范伟豪. 基于时序感知的动态知识图谱补全方法[J]. 计算机工程与应用, 2022, 58(15): 202-209.
LI F Y, FAN W H. Temporal aware approach for dynamic knowledge graph completion[J]. Computer Engineering and Applications, 2022, 58(15): 202-209.
[17] ZHU A, OUYANG D, LIANG S, et al. Step by step: a hierar chical framework for multi-hop knowledge graph reasoning with reinforcement learning[J]. Knowledge-Based Systems, 2022, 248: 108843.
[18] LEBLAY J, CHEKOL M W. Deriving validity time in knowledge graph[C]//Companion Proceedings of the Web Conference, 2018: 1771-1776.
[19] GARCíA-DURáN A, DUMAN?I? S, NIEPERT M. Learning sequence encoders for temporal knowledge graph completion[J]. arXiv:1809.03202, 2018.
[20] BORDES A, USUNIER N, GARCIA-DURAN A, et al. Translating embeddings for modeling multi-relational data[C]//Advances in Neural Information Processing Systems, 2013.
[21] SADEGHIAN A, RODRIGUEZ M, WANG D Z, et al. Temporal reasoning over event knowledge graphs[C]//Workshop on Knowledge Base Construction, Reasoning and Mining, 2016.
[22] CHEN Y, GOLDBERG S, WANG D Z, et al. Ontological pathfinding[C]//Proceedings of the 2016 International Conference on Management of Data, 2016: 835-846.
[23] OMRAN P G, WANG K, WANG Z. Learning temporal rules from knowledge graph streams[C]//Proceedings of the AAAI Spring Symposium: Combining Machine Learning with Knowledge Engineering, 2019.
[24] OMRAN P G, WANG K, WANG Z. Scalable rule learning via learning representation[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence, 2018: 2149-2155.
[25] LIU Y, MA Y, HILDEBRANDT M, et al. TLogic: temporal logical rules for explainable link forecasting on temporal knowledge graphs[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2022: 4120-4127.
[26] CHEN J, REN J, DING W, et al. PaTeCon: a pattern-based temporal constraint mining method for conflict detection on knowledge graphs[J]. arXiv:2304.09015, 2023.
[27] XIONG S, YANG Y, FEKRI F, et al. TILP: differentiable learning of temporal logical rules on knowledge graphs[C]//Proceedings of the Eleventh International Conference on Learning Representations, 2022.
[28] 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.
[29] CHEKOL M, PIRRò G, SCHOENFISCH J, et al. Marrying uncertainty and time in knowledge graphs[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2017.
[30] YANG F, YANG Z, COHEN W W. Differentiable learning of logical rules for knowledge base reasoning[C]//Advances in Neural Information Processing Systems, 2017.
[31] HITCHCOCK F L. The expression of a tensor or a polyadic as a sum of products[J]. Journal of Mathematics and Physics, 1927, 6(1/4): 164-189.
[32] GOEL R, KAZEMI S M, BRUBAKER M, et al. Diachronic embedding for temporal knowledge graph completion[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2020: 3988-3995.
[33] KAZEMI S M, POOLE D. Simple embedding for link prediction in knowledge graphs[C]//Advances in Neural Information Processing Systems, 2018.
[34] LIN L, SHE K. Tensor decomposition-based temporal knowledge graph embedding[C]//Proceedings of the 2020 IEEE 32nd International Conference on Tools with Artificial Intelligence (ICTAI), 2020: 969-975.
[35] LACROIX T, OBOZINSKI G, USUNIER N. Tensor decompositions for temporal knowledge base completion[J]. arXiv:2004.04926, 2020.
[36] JAIN P, RATHI S, CHAKRRABARTI S. Temporal knowledge base completion: new algorithms and evaluation protocols[J]. arXiv:2005.05035, 2020.
[37] 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.
[38] TUCKER L R. Some mathematical notes on three-mode factor analysis[J]. Psychometrika, 1966, 31(3): 279-311.
[39] MA Y, TRESP V, DAXBERGER E A. Embedding models for episodic knowledge graphs[J]. Journal of Web Semantics, 2019, 59: 100490.
[40] 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.
[41] NICKEL M, ROSASCO L, POGGIO T. Holographic embeddings of knowledge graphs[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2016.
[42] 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.
[43] YANG B, YIH W, HE X, et al. Embedding entities and relations for learning and inference in knowledge bases[J]. arXiv:1412.6575, 2014.
[44] SHAO P, ZHANG D, YANG G, et al. Tucker decomposition-based temporal knowledge graph completion[J]. Knowledge-Based Systems, 2022, 238: 107841.
[45] YU M, GUO J, YU J, et al. TBDRI: block decomposition based on relational interaction for temporal knowledge graph completion[J]. Applied Intelligence, 2023, 53(5): 5072-5084.
[46] BALA?EVI? I, ALLEN C, HOSPEDALES T M. Tucker: tensor factorization for knowledge graph completion[J]. arXiv:1901.09590, 2019.
[47] De LATHAUWER L. Decompositions of a higher-order tensor in block terms—part II: definitions and uniqueness[J]. SIAM Journal on Matrix Analysis and Applications, 2008, 30(3): 1033-1066.
[48] JIANG T, LIU T, GE T, et al. Encoding temporal information for time-aware link prediction[C]//Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, 2016: 2350-2354.
[49] WANG Z, ZHANG J, FENG J, et al. Knowledge graph embedding by translating on hyperplanes[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2014.
[50] 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.
[51] WANG Z, LI X. Hybrid-te: hybrid translation-based temporal knowledge graph embedding[C]//Proceedings of the 2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI), 2019: 1446-1451.
[52] 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 (Volume 1: Long Papers), 2015: 687-696.
[53] XU C, NAYYERI M, ALKHOURY F, et al. TeRo: a time-aware knowledge graph embedding via temporal rotation[J]. arXiv:2010.01029, 2020.
[54] XU C, NAYYERI M, ALKHOURY F, et al. Temporal knowledge graph completion based on time series gaussian embedding[C]//Proceedings of the 19th International Semantic Web Conference, Athens, November 2-6, 2020: 654-671.
[55] CHO K, VAN MERRI?NBOER B, GULCEHRE C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[J]. arXiv:1406.1078, 2014.
[56] SCHLICHTKRULL M, KIPF T N, BLOEM P, et al. Modeling relational data with graph convolutional networks[J]. arXiv:1703.06103, 2017.
[57] WU J, CAO M, CHEUNG J C K, et al. Temp: temporal message passing for temporal knowledge graph completion[J]. arXiv:2010.03526, 2020.
[58] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Advances in Neural Information Processing Systems, 2017.
[59] 陈浩, 李永强, 冯远静. 基于多关系循环事件的动态知识图谱推理[J]. 模式识别与人工智能, 2020, 33(4): 337-343.
CHEN H, LI Y Q, FENG Y J. Dynamic knowledge graph inference based on multiple relational cyclic events[J]. Pattern Recognition and Artificial Intelligence, 2020, 33(4): 337-343.
[60] 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.
[61] 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.
[62] CHEN R T Q, RUBANOVA Y, BETTENCOURT J, et al. Neural ordinary differential equations[C]//Advances in Neural Information Processing Systems, 2018.
[63] HAN Z, MA Y, WANG Y, et al. Graph hawkes neural network for forecasting on temporal knowledge graphs[J]. arXiv:2003.13432, 2020.
[64] PARK N, LIU F, MEHTA P, et al. EvoKG: jointly modeling event time and network structure for reasoning over temporal knowledge graphs[C]//Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining, 2022: 794-803.
[65] SHANG C, TANG Y, HUANG J, et al. End-to-end structure-aware convolutional networks for knowledge base completion[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2019: 3060-3067.
[66] BAI L, YU W, CHEN M, et al. Multi-hop reasoning over paths in temporal knowledge graphs using reinforcement learning[J]. Applied Soft Computing, 2021, 103: 107144.
[67] HAN Z, CHEN P, MA Y, et al. Explainable subgraph reasoning for forecasting on temporal knowledge graphs[C]//Proceedings of the International Conference on Learning Representations, 2020.
[68] JUNG Jaehun, JUNG Jinhong, KANG U. Learning to walk across time for interpretable temporal knowledge graph completion[C]//Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, 2021: 786-795.
[69] SUN H, ZHONG J, MA Y, et al. Timetraveler: reinforcement learning for temporal knowledge graph forecasting[J]. arXiv:2109.04101, 2021.
[70] XIE Z W, ZHU R J, LIU J, et al. TARGAT: a time-aware relational graph attention model for temporal knowledge graph embedding[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2023, 31: 2246-2258.
[71] XU W, LIU B, PENG M, et al. Pre-trained language model with prompts for temporal knowledge graph completion[J]. arXiv:2305.07912, 2023.
[72] HAN Z, LIAO R, LIU B, et al. Enhanced temporal knowledge embeddings with contextualized language representations[J]. arXiv:2203.09590, 2022.
[73] LEE D H, AHRABIAN K, JIN W, et al. Temporal knowledge graph forecasting without knowledge using in-context learning[J]. arXiv:2305.10613, 2023.
[74] BLACK S, BIDERMAN S, HALLAHAN E, et al. Gpt-neox-20b: an open-source autoregressive language model[J]. arXiv:2204.06745, 2022.
[75] MAVROMATIS C, SUBRAMANYAM P L, IOANNIDIS V N, et al. Tempoqr: temporal question reasoning over knowledge graphs[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2022: 5825-5833.
[76] GAO Y, HE Y, KAN Z, et al. Learning joint structural and temporal contextualized knowledge embeddings for temporal knowledge graph completion[C]//Proceedings of the Findings of the Association for Computational Linguistics, 2023: 417-430.
[77] DEVLIN J, CHANG M W, LEE K, et al. Bert: pre-training of deep bidirectional transformers for language understanding[J]. arXiv:1810.04805, 2018.
[78] CHEN C, WANG Y, SUN A, et al. Dipping PLMs sauce: bridging structure and text for effective knowledge graph completion via conditional soft prompting[J]. arXiv:2307. 01709, 2023.
[79] LI Z, JIN X, GUAN S, et al. Search from history and reason for future: two-stage reasoning on temporal knowledge graphs[J]. arXiv:2106.00327, 2021.
[80] TANG X, YUAN R, LI Q, et al. Timespan-aware dynamic knowledge graph embedding by incorporating temporal evolution[J]. IEEE Access, 2020, 8: 6849-6860.
[81] QIU X, SUN T, XU Y, et al. Pre-trained models for natural language processing: a survey[J]. Science China Technological Sciences, 2020, 63(10): 1872-1897.
[82] WANG X, CHEN Y, ZHU W. A survey on curriculum learning[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 44(9): 4555-4576.
[83] 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.
[84] 何苗惠, 段旭祥, 吴至友. 提高长尾数据知识图谱补全性能的一种新算法[J/OL]. 运筹学学报: 1-14(2022-04-24)[2023-07-06]. http://kns.cnki.net/kcms/detail/31.1732.O1. 20220424.1147.012.html.
HE M H, DUAN X X, WU Z Y. A new algorithm for improving the completion performance of knowledge graph of long-tail data[J/OL]. Operations Research Transactions: 1-14(2022-04-24) [2023-07-06]. http://kns.cnki.net/kcms/detail/31.1732.O1.20220424.1147.012.html.