计算机科学 ›› 2022, Vol. 49 ›› Issue (9): 162-171.doi: 10.11896/jsjkx.220500204

• 人工智能 • 上一篇    下一篇

时序知识图谱表示学习

徐涌鑫1,2, 赵俊峰1,2,3, 王亚沙1,2,3, 谢冰1,2,3, 杨恺1,2,3   

  1. 1 北京大学计算机学院 北京 100871
    2 高可信软件技术教育部重点实验室 北京 100871
    3 北京大学(天津滨海)新一代信息技术研究院 天津 300450
  • 收稿日期:2021-10-22 修回日期:2022-05-16 出版日期:2022-09-15 发布日期:2022-09-09
  • 通讯作者: 赵俊峰(zhaojf@pku.edu.cn)
  • 作者简介:(xuyx@stu.pku.edu.cn)
  • 基金资助:
    国家自然科学基金(62172011)

Temporal Knowledge Graph Representation Learning

XU Yong-xin1,2, ZHAO Jun-feng1,2,3, WANG Ya-sha1,2,3, XIE Bing1,2,3, YANG Kai1,2,3   

  1. 1 School of Computer Science,Peking University,Beijing 100871,China
    2 Key Laboratory of High Confidence Software Technologies,Ministry of Education,Beijing 100871,China
    3 Peking University Information Technology Institute(Tianjin Binhai),Tianjin 300450,China
  • Received:2021-10-22 Revised:2022-05-16 Online:2022-09-15 Published:2022-09-09
  • About author:XU Yong-xin,born in 1998,postgraduate.His main research interests include knowledge graph and so on.
    ZHAO Jun-feng,born in 1974,Ph.D,research professor,is a member of China Computer Federation.Her main research interests include big data analysis,knowledge graph,urban computing and so on.
  • Supported by:
    National Natural Science Foundation of China(62172011).

摘要: 知识图谱作为一种结构化的人类知识形式,对海量多源异构异质的数据语义互通起到了很好的支撑作用,并有效地支持了数据分析等任务,成为了近年来学术界和工业界的研究热点。目前大多数知识图谱都是根据非实时的静态数据构建,没有考虑实体和关系的时间特性。然而社交网络通信、金融贸易、疫情传播网络等应用场景的数据具有实时动态的特点以及复杂的时间特性,如何利用时序数据构建知识图谱并且对该知识图谱进行有效建模是一个具有挑战性的问题。目前,有许多研究工作利用时序数据中的时间信息丰富知识图谱的特征,赋予知识图谱动态特征,将事实三元组拓展为(头实体,关系,尾实体,时间)的四元组表示,使用时间相关四元组进行知识表示的知识图谱被统称为时序知识图谱。文中对时序知识图谱相关文献进行整理和分析,并对时序知识图谱表示学习的工作进行了全面综述。具体地,首先简单介绍了时序知识图谱的背景与定义;其次总结了时序知识图谱表示学习方法相比传统知识图谱表示学习方法的优点;然后从事实的建模方法角度详细阐述了时序知识图谱表示学习的主要方法,并且介绍了上述方法使用到的数据集;最后对该技术的主要挑战进行了总结,并对其未来研究方向进行了展望。

关键词: 知识图谱, 深度学习, 表示学习, 时间信息, 动态过程

Abstract: As a structured form of human knowledge,knowledge graphs have played a great supportive role in supporting the semantic intercommunication of massive,multi-source,heterogeneous data,and effectively support tasks such as data analysis,attracting the attention of academia and industry.At present,most knowledge graphs are constructed based on non-real-time static data,without considering the temporal characteristics of entities and relationships.However,data in application scenarios such as social network communication,financial trade,and epidemic spreading network are highly dynamic and exhibit complex temporal properties.How to use time series data to build knowledge graphs and effectively model them is a challenging problem.Recently,numerous studies use temporal information in time series data to enrich the characteristics of knowledge graphs,endowing know-ledge graphs with dynamic features,expanding fact triples into quadruple representation(head entity,relationship,tail entity,time).The knowledge graph which utilizes time-related quadruples to represent knowledge are collectively referred to as temporal knowledge graph.This paper summarizes the research work of temporal knowledge graph representation learning by sorting out and analyzing the corresponding literature.Specifically,it first briefly introduce the background and definition of temporal know-ledge graph.Next,it summarizes the advantages of the temporal knowledge graph representation learning method compared with the traditional knowledge graph representation learning method.Then it elaborates on the recent method of temporal knowledge graph representation learning from the perspective of the method modeling facts,introduces the dataset used by the above method and summarizes the main challenges of this technology.Finally,the future research direction is prospected.

Key words: Knowledge graph, Deep learning, Representation learning, Temporal information, Dynamic process

中图分类号: 

  • TP311
[1]NOY N,GAO Y,JAIN A,et al.Industry-scale knowledgegraphs:lessons and challenges[J].Communications of the ACM,2019,62(8):36-43.
[2]SINGHAL A.Introducing the Knowledge Graph:things,notstrings[EB/OL].Google Blog.https://www.blog.google/products/search/introducing-knowledge-graph-things-not/.
[3]PITTMAN R J,SRIVASTAVA A,HEWAVITHARANA S,et al.2017.Cracking the Code on Conversational Commerce[EB/OL].eBay Blog.https://www.ebayinc.com/stories/news/cracking-the-code-on-conversationalcommerce/.
[4]HAMAD F,LIU I,ZHANG X X.Food Discovery with UberEats:Building a Query Understanding Engine[EB/OL].Uber Engineering Blog.https://eng.uber.com/uber-eats-query-understanding/.
[5]KRISHNAN A.Making search easier:How Amazon's Product Graph is helping customers find products more easily[EB/OL].Amazon Blog.https://blog.aboutamazon.com/innovation/making-search-easier.
[6]LIU Z Y,SUN M S,LIN Y K,et al.Knowledge Representation Learning:A Review[J].Journal of Computer Research and Development,2016,53(2):247-261.
[7]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 Proces-sing.2016:2350-2354.
[8]BORDES A,USUNIER N,GARCIA-DURAN A,et al.Translating embeddings for modeling multi-relational data[C]//Neural Information Processing Systems(NIPS).2013:1-9.
[9]WANG Z,ZHANG J,FENG J,et al.Knowledge graph embedding by translating on hyperplanes[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2014:1112-1119.
[10]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.
[11]JI G,LIU K,HE S,et al.Knowledge graph completion withadaptive sparse transfer matrix[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2016:985-991.
[12]ZHANG W,PAUDEL B,WANG L,et al.Iteratively learningembeddings and rules for knowledge graph reasoning[C]//The World Wide Web Conference.2019:2366-2377.
[13]NICKEL M,TRESP V,KRIEGEL H P.A three-way model for collective learning on multi-relational data[C]//ICML.2011:809-816.
[14]YANG B,YIH W,HE X,et al.Embedding entities and relations for learning and inference in knowledge bases[J].arXiv:1412.6575,2014.
[15]TROUILLON T,WELBL J,RIEDEL S,et al.Complex embeddings for simple link prediction[C]//International Conference on Machine Learning.PMLR,2016:2071-2080.
[16]GARCÍA-DURÁN A,DUMANČIĆS,NIEPERT M.Learning sequence encoders for temporal knowledge graph completion[J].arXiv:1809.03202,2018.
[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]SADEGHIAN A,ARMANDPOUR M,COLAS A,et al.ChronoR:Rotation Based Temporal Knowledge Graph Embedding[J].arXiv:2103.10379,2021.
[19]HAWKES A G.Point spectra of some mutually exciting point processes[J].Journal of the Royal Statistical Society:Series B(Methodological),1971,33(3):438-443.
[20]HAWKES A G.Spectra of some self-exciting and mutually exciting point processes[J].Biometrika,1971,58(1):83-90.
[21]HAWKES A G,OAKES D.A cluster process representation of a self-exciting process[J].Journal of Applied Probability,1974,11(3):493-503.
[22]OGATA Y.Space-time point-process models for earthquake occurrences[J].Annals of the Institute of Statistical Mathematics,1998,50(2):379-402.
[23]BACRY E,IUGA A,LASNIER M,et al.Market impacts and the life cycle of investors orders[J].Market Microstructure and Liquidity,2015,1(2):1550009.
[24]BACRY E,JAISSON T,MUZY J F.Estimation of slowly de-creasing hawkes kernels:application to high-frequency order book dynamics[J].Quantitative Finance,2016,16(8):1179-1201.
[25]CHANDRA R,ZHANG M.Cooperative coevolution of Elman recurrent neural networks for chaotic time series prediction[J].Neurocomputing,2012,86:116-123.
[26]TRIVEDI R,FARAJTABAR M,WANG Y,et al.Know-evolve:Deep reasoning in temporal knowledge graphs[J].arXiv:1705.05742,2017.
[27]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 Processing(EMNLP).2020:6669-6683.
[28]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.
[29]KIPF T N,WELLING M.Semi-supervised classification withgraph convolutional networks[J].arXiv:1609.02907,2016.
[30]VELICKOVIC P,CUCURULL G,CASANOVA A,et al.Graph attention networks[J].arXiv:1710.10903,2017.
[31]LI Z,JIN X,LI W,et al.Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning[J].arXiv:2104.10353,2021.
[32]CHUNG J,GULCEHRE C,CHO K H,et al.Empirical evaluation of gated recurrent neural networks on sequence modeling[J].arXiv:1412.3555,2014.
[33]ZHU C,CHEN M,FAN C,et al.Learning from History:Mode-ling Temporal Knowledge Graphs with Sequential Copy-Generation Networks[J].arXiv:2012.08492,2020.
[34]DASGUPTA S S,RAY S N,TALUKDAR P.Hyte:Hyper-plane-based temporally aware knowledge graph embedding[C]//Proceedings of the 2018 Conference on Empirical Me-thods in Natural Language Processing.2018:2001-2011.
[35]JAIN P,RATHI S,CHAKRABARTI S.Temporal Knowledge Base Completion:New Algorithms and Evaluation Protocols[J].arXiv:2005.05035,2020.
[36]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.
[37]GARG S,SHARMA N,JIN W,et al.Temporal attribute prediction via joint modeling of multi-relational structure evolution[J].arXiv:2003.03919,2020.
[38]LIN Y,LIU Z,LUAN H,et al.Modeling relation paths for representation learning of knowledge bases[J].arXiv:1506.00379,2015.
[39]GUO S,WANG Q,WANG L,et al.Knowledge graph embedding with iterative guidance from soft rules[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2018:4816-4823.
[40]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.
[41]WANG H,ZHANG F,HOU M,et al.SHINE:signed heterogeneous information network embedding for sentiment link prediction[C]//Proceedings of the 11th ACM International Confe-rence on Web Search and Data Mining.2018:592-600.
[42]HUANG J,ZHAO W X,DOU H,et al.Improving sequential recommendation with knowledge-enhanced memory networks[C]//Proceedings of the 41st International ACM SIGIR Confe-rence on Research & Development in Information Retrieval.2018:505-514.
[43]WANG H,ZHANG F,WANG J,et al.RippleNet:propagating user preferences on the knowledge graph for recommender systems[C]//Proceedings of the 27th ACM International Confe-rence on Information and Knowledge Management.2018:417-426.
[44]YU X,REN X,SUN Y,et al.Personalized entity recommendation:a heterogeneous information network approach[C]//Proceedings of the 7th ACM International Conference on Web Search and Data Mining.2014:283-292.
[45]SUN Z,YANG J,ZHANG J et al.Recurrent knowledge graph embedding for effffective recommendation[C]//Proceedings of the 12th ACM Conference on Recommender Systems.2018:297-305.
[46]WANG X,WANG D,XU C,et al.Explainable reasoning over knowledge graphs for recommendation[C]//Proceedings of the AAAI Conference on Artifificial Intelligence.2019:5329-5336.
[47]SONG W,DUAN Z,YANG Z,et al.Explainable knowledgegraph-based recommendation via deep reinforcement learning[J].arXiv:1906.09506,2019.
[48]HUANG X,FANG Q,QIAN S,et al.Explainable interaction-driven user modeling over knowledge graph for sequential reco-mmendation[C]//Proceedings of the 27th ACM International Conference on Multimedia.2019:548-556.
[49]WANG H,ZHANG F,WANG J,et al.Exploring high-orderuser preference on the knowledge graph for recommender systems[J].ACM Transactions on Information Systems,2019,37:1-26.
[50]WANG M,LIU M,LIU J,et al.Safe medicine recommendation via medical knowledge graph embedding[J].arXiv:1710.05980,2017.
[51]PALUMBO E,RIZZO G,TRONCY R.Entity2rec:learninguser-item relatedness from knowledge graphs for top-n item re-commendation[C]//Proceedings of the 11th ACM Conference on Recommender Systems.2017:32-36.
[1] 宋杰, 梁美玉, 薛哲, 杜军平, 寇菲菲.
基于无监督集群级的科技论文异质图节点表示学习方法
Scientific Paper Heterogeneous Graph Node Representation Learning Method Based onUnsupervised Clustering Level
计算机科学, 2022, 49(9): 64-69. https://doi.org/10.11896/jsjkx.220500196
[2] 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
[3] 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
[4] 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
[5] 汤凌韬, 王迪, 张鲁飞, 刘盛云.
基于安全多方计算和差分隐私的联邦学习方案
Federated Learning Scheme Based on Secure Multi-party Computation and Differential Privacy
计算机科学, 2022, 49(9): 297-305. https://doi.org/10.11896/jsjkx.210800108
[6] 王剑, 彭雨琦, 赵宇斐, 杨健.
基于深度学习的社交网络舆情信息抽取方法综述
Survey of Social Network Public Opinion Information Extraction Based on Deep Learning
计算机科学, 2022, 49(8): 279-293. https://doi.org/10.11896/jsjkx.220300099
[7] 郝志荣, 陈龙, 黄嘉成.
面向文本分类的类别区分式通用对抗攻击方法
Class Discriminative Universal Adversarial Attack for Text Classification
计算机科学, 2022, 49(8): 323-329. https://doi.org/10.11896/jsjkx.220200077
[8] 姜梦函, 李邵梅, 郑洪浩, 张建朋.
基于改进位置编码的谣言检测模型
Rumor Detection Model Based on Improved Position Embedding
计算机科学, 2022, 49(8): 330-335. https://doi.org/10.11896/jsjkx.210600046
[9] 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
[10] 孙奇, 吉根林, 张杰.
基于非局部注意力生成对抗网络的视频异常事件检测方法
Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection
计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061
[11] 胡艳羽, 赵龙, 董祥军.
一种用于癌症分类的两阶段深度特征选择提取算法
Two-stage Deep Feature Selection Extraction Algorithm for Cancer Classification
计算机科学, 2022, 49(7): 73-78. https://doi.org/10.11896/jsjkx.210500092
[12] 程成, 降爱莲.
基于多路径特征提取的实时语义分割方法
Real-time Semantic Segmentation Method Based on Multi-path Feature Extraction
计算机科学, 2022, 49(7): 120-126. https://doi.org/10.11896/jsjkx.210500157
[13] 侯钰涛, 阿布都克力木·阿布力孜, 哈里旦木·阿布都克里木.
中文预训练模型研究进展
Advances in Chinese Pre-training Models
计算机科学, 2022, 49(7): 148-163. https://doi.org/10.11896/jsjkx.211200018
[14] 周慧, 施皓晨, 屠要峰, 黄圣君.
基于主动采样的深度鲁棒神经网络学习
Robust Deep Neural Network Learning Based on Active Sampling
计算机科学, 2022, 49(7): 164-169. https://doi.org/10.11896/jsjkx.210600044
[15] 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
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!