计算机科学 ›› 2023, Vol. 50 ›› Issue (3): 23-33.doi: 10.11896/jsjkx.220400255

• 知识图谱赋能的知识工程:理论、技术与系统专题 • 上一篇    下一篇

基于关系约束的上下文感知时态知识图谱补全

汪璟玢, 赖晓连, 林新宇, 杨心逸   

  1. 福州大学计算机与大数据学院 福州350108
  • 收稿日期:2022-04-25 修回日期:2023-01-09 出版日期:2023-03-15 发布日期:2023-03-15
  • 通讯作者: 汪璟玢(wjb@fzu.edu.cn)
  • 基金资助:
    国家自然科学基金(61672159);福建省自然科学基金(2021J01619)

Context-aware Temporal Knowledge Graph Completion Based on Relation Constraints

WANG Jingbin, LAI Xiaolian, LIN Xinyu, YANG Xinyi   

  1. College of Computer and Data Science,Fuzhou University,Fuzhou 350108,China
  • Received:2022-04-25 Revised:2023-01-09 Online:2023-03-15 Published:2023-03-15
  • About author:WANG Jingbin,born in 1973,master,associate professor,is a member of China Computer Federation.Her main research interests include knowledge graph,relation reasoning,distributed data management and knowledge repesen-tation.
  • Supported by:
    National Natural Science Foundation of China(61672159) and Natural Science Foundation of Fujian Province(2021J01619).

摘要: 现有的时间知识图谱补全模型仅考虑四元组自身的结构信息,忽略了实体隐含的邻居信息和关系对实体的约束,导致模型在时态知识图谱补全任务上表现不佳。此外,一些数据集在时间上呈现不均衡的分布,导致模型训练难以达到一个较好的平衡点。针对这些问题,提出了一个基于关系约束的上下文感知模型(CARC)。CARC通过自适应时间粒度聚合模块来解决数据集在时间上分布不均衡的问题,并使用邻居聚合器将上下文信息集成到实体嵌入中,以增强实体的嵌入表示。此外,设计了四元组关系约束模块,使具有相同关系约束的实体嵌入彼此相近,不同关系约束的实体嵌入彼此远离,以进一步增强实体的嵌入表示。在多个公开的时间数据集上进行了大量实验,实验结果证明了所提模型的优越性。

关键词: 时间知识图谱, 链路预测, 时间区间预测, 关系约束, 邻居信息, 时间粒度

Abstract: The existing temporal knowledge graph completion models only consider the structural information of the quadruple itself,ignoring the implicit neighbor information and the constraints of relationships on entities,which leads to the poor perfor-mance of the models on the temporal knowledge graph completion task.In addition,some datasets exhibit unbalanced distribution in time,which makes it difficult for model training to achieve a good balance.To address these problems,the paper proposes a context-aware model based on relation constraints(CARC).CARC solves the problem of an unbalanced distribution of datasets in time through an adaptive time granularity aggregation module and uses a neighbor-aggregator to integrate contextual information into entity embeddings to enhance the embedding representation of the entity.In addition,the quadruple relation constraint mo-dule is designed to make the embeddings of entities with the same relational constraints close to each other,while those with diffe-rent relational constraints are far away from each other,which further enhances the embedding representation of entities.Extensive experiments are conducted on several publicly available temporal datasets,and the experimental results prove the superiority of the proposed model.

Key words: Temporal knowledge graph, Link prediction, Time interval prediction, Relation constraint, Neighbor information, Time granularity

中图分类号: 

  • TP391
[1]XU C,NAYYERI M,ALKHOURY F,et al.TeRo:A Time-aware Knowledge Graph Embedding via Temporal Rotation[C]//Proceedings of the 28th International Conference on Computational Linguistics.Barcelona:International Committee on Computational Linguistics,2020:1583-1593.
[2]VASHISHTH S,SANYAL S,NITIN V,et al.Composition-based Multi-Relational Graph Convolutional Networks[C]//8th International Conference on Learning Representations.Addis Ababa:OpenReview.net,2020:1-16.
[3]HONG J D,CHEN W,ZHAO L.Knowledge RepresentationModel That Combining Entity Neighbor Information[J].Journal of Chinese Computer Systems,2020,41(8):1596-1601.
[4]XIE R,LIU Z,SUN M.Representation Learning of Knowledge Graphs with Hierarchical Types[C]//Proceedings of the 25th International Joint Conference on Artificial Intelligence.New York:Morgan Kaufmann,2016:2965-2971.
[5]MA S,DING J,JIA W,et al.Transt:Type-based multiple embedding representations for knowledge graph completion[C]//Joint European Conference on Machine Learning and Knowledge Discovery in Databases.Skopje:Cham:Springer,2017:717-733.
[6]NIU G,LI B,ZHANG Y,et al.AutoETER:Automated Entity Type Representation for Knowledge Graph Embedding[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing.Punta Cana:ACL,2020:1172-1181.
[7]LACROIX T,OBOZINSKI G,USUNIER N.Tensor Decompositions for temporal knowledge base completion[C]//8th International Conference on Learning Representations.Addis Ababa:OpenReview.net,2020:1-12.
[8]JAIN P,RATHI S,CHAKRABARTI S.Temporal Knowledge Base Completion:New Algorithms and Evaluation Protocols[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing.Punta Cana:ACL,2020:3733-3747.
[9]TROUILLON T,WELBL J,RIEDEL S,et al.Complex embeddings for simple link prediction[C]//Proceedings of Interna-tional Conference on Machine Learning.Sydney:PMLR Press,2016:2071-2080.
[10]MARCHEGGIANI D,TITOV I.Encoding Sentences with GraphConvolutional Networks for Semantic Role Labeling[C]//Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing.Brussels:ACL,2017:1506-1515.
[11]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 Matural Language Processing.Brussels:ACL,2018:2001-2011.
[12]BORDES A,USUNIER N,GARCIA-DURAN A,et al.Translating embeddings for modeling multi-relational data[C]//Ad-vances in Neural Information Processing Systems 26.Cam-bridge:The MIT Press,2013:2787-2795.
[13]GARCÍA-DURÁN A,DUMANČIĆ S,NIEPERT M.Learning sequence encoders for temporal knowledge graph completion[C]//Proceedings of the 2018 Conference on Empirical Methods in Matural Language Processing.Brussels:ACL,2018.
[14]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.Palo Alto:AAAI Press,2020:3988-3995.
[15]SUN Z,DENG Z,NIE J,et al.RotatE:Knowledge Graph Embedding by Relational Rotation in Complex Space[C]//In 8th International Conference on Learning Representations.New Orleans:OpenReview.net,2019:1-18.
[16]MIKOLOV T,SUTSKEVER I,CHEN K,et al.Distributed rep-resentations of words and phrases and their compositionality[C]//Advances in Neural Information Processing Systems.Cambridge:The MIT Press,2013:3111-3119.
[1] 李勇, 吴京鹏, 张钟颖, 张强.
融合快速注意力机制的节点无特征网络链路预测算法
Link Prediction for Node Featureless Networks Based on Faster Attention Mechanism
计算机科学, 2022, 49(4): 43-48. https://doi.org/10.11896/jsjkx.210800276
[2] 赵学磊, 季新生, 刘树新, 李英乐, 李海涛.
基于路径连接强度的有向网络链路预测方法
Link Prediction Method for Directed Networks Based on Path Connection Strength
计算机科学, 2022, 49(2): 216-222. https://doi.org/10.11896/jsjkx.210100107
[3] 龚追飞, 魏传佳.
基于改进AdaBoost算法的复杂网络链路预测
Link Prediction of Complex Network Based on Improved AdaBoost Algorithm
计算机科学, 2021, 48(3): 158-162. https://doi.org/10.11896/jsjkx.200600075
[4] 李鑫超, 李培峰, 朱巧明.
一种基于层级信息优化的有向网络表示学习方法
Directed Network Representation Method Based on Hierarchical Structure Information
计算机科学, 2021, 48(2): 100-104. https://doi.org/10.11896/jsjkx.191200033
[5] 龚追飞, 魏传佳.
基于拓扑相似和XGBoost的复杂网络链路预测方法
Complex Network Link Prediction Method Based on Topology Similarity and XGBoost
计算机科学, 2021, 48(12): 226-230. https://doi.org/10.11896/jsjkx.200800026
[6] 黄寿孟.
一种基于监督学习的异构网链路预测模型
Heterogeneous Network Link Prediction Model Based on Supervised Learning
计算机科学, 2021, 48(11A): 111-116. https://doi.org/10.11896/jsjkx.210300030
[7] 赵曼, 赵加坤, 刘金诺.
基于自我中心网络结构特征和网络表示学习的链路预测算法
Link Prediction Algorithm Based on Ego Networks Structure and Network Representation Learning
计算机科学, 2021, 48(11A): 211-217. https://doi.org/10.11896/jsjkx.201200231
[8] 王慧, 乐孜纯, 龚轩, 武玉坤, 左浩.
基于特征分类的链路预测方法综述
Review of Link Prediction Methods Based on Feature Classification
计算机科学, 2020, 47(8): 302-312. https://doi.org/10.11896/jsjkx.190700136
[9] 袁榕, 宋玉蓉, 孟繁荣.
一种基于加权网络拓扑权重的链路预测方法
Link Prediction Method Based on Weighted Network Topology Weight
计算机科学, 2020, 47(5): 265-270. https://doi.org/10.11896/jsjkx.190600031
[10] 富坤, 仇倩, 赵晓梦, 高金辉.
基于节点演化分阶段优化的事件检测方法
Event Detection Method Based on Node Evolution Staged Optimization
计算机科学, 2020, 47(5): 96-102. https://doi.org/10.11896/jsjkx.190400072
[11] 李鑫超, 李培峰, 朱巧明.
一种基于改进向量投影距离的知识图谱表示方法
Knowledge Graph Representation Based on Improved Vector Projection Distance
计算机科学, 2020, 47(4): 189-193. https://doi.org/10.11896/jsjkx.190300024
[12] 马扬, 程光权, 梁星星, 李妍, 杨雨灵, 刘忠.
有向加权网络中的改进SDNE算法
Improved SDNE in Weighted Directed Network
计算机科学, 2020, 47(4): 233-237. https://doi.org/10.11896/jsjkx.190600151
[13] 王慧, 乐孜纯, 龚轩, 左浩, 武玉坤.
基于特征学习的链路预测模型TNTlink
TNTlink Prediction Model Based on Feature Learning
计算机科学, 2020, 47(12): 245-251. https://doi.org/10.11896/jsjkx.190700020
[14] 吴勇, 王斌君, 翟一鸣, 仝鑫.
共引增强有向网络嵌入研究
Study on Co-citation Enhancing Directed Network Embedding
计算机科学, 2020, 47(12): 279-284. https://doi.org/10.11896/jsjkx.191000199
[15] 杨旭华, 俞佳, 张端.
基于局部社团和节点相关性的链路预测算法
Link Prediction Method Based on Local Community and Nodes’ Relativity
计算机科学, 2019, 46(1): 155-161. https://doi.org/10.11896/j.issn.1002-137X.2019.01.024
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!