- Journal Profile
- Editor-in-Chief
- Editorial Board
- Ethics Guidelines
- Open Access
- Subscription
Computer Science ›› 2022 , Vol. 49 ›› Issue (9) : 162-171. doi: 10.11896/jsjkx.220500204
• Artificial Intelligence • Previous Articles Next Articles
Temporal Knowledge Graph Representation Learning
XU Yong-xin 1,2 , ZHAO Jun-feng 1,2,3 , WANG Ya-sha 1,2,3 , XIE Bing 1,2,3 , YANG Kai 1,2,3
- 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).
- 1. 探讨2016版国际胰瘘研究小组定义和分级系统对胰腺术后患者胰瘘分级的影响.PDF (500KB)
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
CLC Number:
Cite this article
XU Yong-xin, ZHAO Jun-feng, WANG Ya-sha, XIE Bing, YANG Kai. Temporal Knowledge Graph Representation Learning[J].Computer Science, 2022, 49(9): 162-171.
share this article
Add to citation manager EndNote | Reference Manager | ProCite | BibTeX | RefWorks
URL: https://www.jsjkx.com/EN/10.11896/jsjkx.220500204
https://www.jsjkx.com/EN/Y2022/V49/I9/162
Related Articles 15
Recommended 0.
- Related Articles
- Recommended
> cs > arXiv:2403.04782
- Other formats
Current browse context:
Change to browse by:, references & citations, dblp - cs bibliography, computer science > computation and language, title: a survey on temporal knowledge graph: representation learning and applications.
Abstract: Knowledge graphs have garnered significant research attention and are widely used to enhance downstream applications. However, most current studies mainly focus on static knowledge graphs, whose facts do not change with time, and disregard their dynamic evolution over time. As a result, temporal knowledge graphs have attracted more attention because a large amount of structured knowledge exists only within a specific period. Knowledge graph representation learning aims to learn low-dimensional vector embeddings for entities and relations in a knowledge graph. The representation learning of temporal knowledge graphs incorporates time information into the standard knowledge graph framework and can model the dynamics of entities and relations over time. In this paper, we conduct a comprehensive survey of temporal knowledge graph representation learning and its applications. We begin with an introduction to the definitions, datasets, and evaluation metrics for temporal knowledge graph representation learning. Next, we propose a taxonomy based on the core technologies of temporal knowledge graph representation learning methods, and provide an in-depth analysis of different methods in each category. Finally, we present various downstream applications related to the temporal knowledge graphs. In the end, we conclude the paper and have an outlook on the future research directions in this area.
Submission history
Link back to: arXiv , form interface , contact .
Subscribe to the PwC Newsletter
Join the community, edit social preview.
Add a new code entry for this paper
Remove a code repository from this paper.
Mark the official implementation from paper authors
Add a new evaluation result row.
- GRAPH REPRESENTATION LEARNING
- REPRESENTATION LEARNING
Remove a task
Add a method
Remove a method, edit datasets, temporal knowledge graph representation learning with local and global evolutions.
Knowledge-Based Systems 2022 · Jiasheng Zhang , Shuang Liang , Yongpan Sheng , Jie Shao · Edit social preview
Temporal knowledge graph (TKG) representation learning aims to project entities and relations in TKG to low-dimensional vector space while preserving the evolutionary nature of TKG. Most existing methods separately treat knowledge that happened at different times, which fails to explore how temporal knowledge graph evolves over time. Actually, TKG should evolve both on local and global structures. The local structure evolution describes the formation process of graph structure in a detailed manner, while the global structure evolution refers to the dynamic topology (e.g., community partition) of graph, which is derived from the continuous formation process. Both of them are key factors for understanding the evolutionary nature of TKG. Unfortunately, seldom attention has been paid to this aspect. In this paper, we propose a new TKG representation learning framework with local and global structure evolutions, named EvoExplore. Specifically, we define the local structure evolution as the establishment process of relations between entities, and propose a hierarchical-attention-based temporal point process to capture the formation process of graph structure in a fine-grained manner. For global structure evolution, we propose a novel soft modularity parameterized by entity representations to capture the dynamic community partition of TKG. Finally, we employ a multi-task loss function to jointly optimize the above two parts, which allows EvoExplore to learn the mutual influences of local and global structure evolutions. Experimental results on three realworld datasets demonstrate the superiority of EvoExplore compared with baseline methods.
Code Edit Add Remove Mark official
Tasks edit add remove, datasets edit, results from the paper edit add remove, methods edit add remove.
Papers on Temporal Knowledge Graph Embedding and Reasoning
Papers on tkge-r.
Some papers on Temporal Knowledge Graph Embedding and Reasoning
Useful research resources
Graph-based Deep Learning Literature, Github
links to conference publications in graph-based deep learning
Reinforcement learning on graphs: A survey, Github
This collection of papers can be used to summarize research about graph reinforcement learning for the convenience of researchers.
Awesome Machine Learning for Combinatorial Optimization Resources, Github
Awesome machine learning for combinatorial optimization papers.
Awesome-TKGC, Github
A collection of papers and resources about temporal knowledge graph completion (TKGC).
AKGR: Awesome Knowledge Graph Reasoning, Github
AKGR: Awesome Knowledge Graph Reasoning is a collection of knowledge graph reasoning works, including papers, codes and datasets.
Awesome Knowledge Graph, Github
A curated list of Knowledge Graph related learning materials, databases, tools and other resources.
Awesome-DynamicGraphLearning, Github
Awesome papers about machine learning (deep learning) on dynamic (temporal) graphs (networks / knowledge graphs).
KGE, Github
Some papers on Knowledge Graph Embedding(KGE)
KGLQ, Github
Some papers about Logical Query on Knowledge Graphs (KGLQ)
ADGC: Awesome Deep Graph Clustering, Github
Awesome Deep Graph Clustering is a collection of SOTA, novel deep graph clustering methods (papers, codes, and datasets).
Graph Adversarial Learning Literature, Github
A curated list of adversarial attacks and defenses papers on graph-structured data.
Survey Papers
Knowledge Graph Embedding: An Overview , APSIPA Transactions on Signal and Information Processing, 2024. paper Ge, X., Wang, Y. C., Wang, B., & Kuo, C. C. J
Survey of Temporal Knowledge Graph Completion Methods , Journal of Computer Engineering & Applications, 2024. paper Lei, X. I. A. O., & Qi, L. I.
Overview of Knowledge Reasoning for Knowledge Graph , Neurocomputing, 2024. paper Liu, X., Mao, T., Shi, Y., & Ren, Y.
Knowledge graph embedding: A survey from the perspective of representation spaces , ACM Computing Surveys, 2024. paper Cao, J., Fang, J., Meng, Z., & Liang, S.
A survey on graph representation learning methods , ACM Transactions on Intelligent Systems and Technology, 2024. paper Khoshraftar, S., & An, A.
Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey , ArXiv, 2024. paper Chen, Z., Zhang, Y., Fang, Y., Geng, Y., Guo, L., Chen, X., … & Chen, H.
A survey for managing temporal data in RDF , Information Systems, 2024. paper Wu, Di, Hsien-Tseng Wang, and Abdullah Uz Tansel
A Survey on Temporal Knowledge Graph: Representation Learning and Applications , ArXiv, 2024. paper Cai, Li, Xin Mao, Yuhao Zhou, Zhaoguang Long, Changxu Wu, and Man Lan.
A Survey on Temporal Knowledge Graph Completion: Taxonomy, Progress, and Prospects , ArXiv, 2023. paper
Jiapu Wang, Boyue Wang, Meikang Qiu, Shirui Pan, Bo Xiong, Heng Liu, Linhao Luo, Tengfei Liu, Yongli Hu, Baocai Yin, Wen Gao
Knowledge Graphs: Opportunities and Challenges , Artificial Intelligence Review, 2023, paper
Ciyuan Peng, Feng Xia, Mehdi Naseriparsa & Francesco Osborne
Generalizing to Unseen Elements: A Survey on Knowledge Extrapolation for Knowledge Graphs , ArXiv, 2023. paper
Mingyang Chen, Wen Zhang, Yuxia Geng, Zezhong Xu, Jeff Z. Pan, Huajun Chen
A Comprehensive Survey on Automatic Knowledge Graph Construction , ArXiv, 2023. paper
Lingfeng Zhong, Jia Wu, Qian Li, Hao Peng, Xindong Wu
Temporal Knowledge Graph Completion: A Survey ArXiv, 2022. paper
Borui Cai, Yong Xiang, Longxiang Gao, He Zhang, Yunfeng Li, Jianxin Li.
Update : Borui Cai, Yong Xiang, Longxiang Gao, He Zhang, Yunfeng Li, Jianxin Li, Temporal Knowledge Graph Completion: A Survey , 2023 Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, Survey Track. Pages 6545-6553. paper
Reasoning over different types of knowledge graphs: Static, temporal and multi-modal , ArXiv, 2022. paper
A Survey on Temporal Knowledge Graphs-Extrapolation and Interpolation Tasks , Advances in Natural Computation, Fuzzy Systems and Knowledge Discovery, paper
Sulin Chen & Jingbin Wang
Generalizing to Unseen Elements: A Survey on Knowledge Extrapolation for Knowledge Graphs . 2023 Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, Survey Track. paper
Survey on Temporal Knowledge Graph , 2021 IEEE Sixth International Conference on Data Science in Cyberspace (DSC). paper
Chong Mo; Ye Wang; Yan Jia; Qing Liao
Knowledge-Based Systems
[1] Yue, L., Ren, Y., Zeng, Y., Zhang, J., Zeng, K., Wan, J., & Zhou, M. (2024). Complex expressional characterizations learning based on block decomposition for temporal knowledge graph completion . Knowledge-Based Systems, 111591.
[2] Zhu, L., Zhang, H., & Bai, L. (2024). Hierarchical pattern-based complex query of temporal knowledge graph . Knowledge-Based Systems, 284, 111301.
Applied Intelligence
[1] Wang, J., Wu, R., Wu, Y., Zhang, F., Zhang, S., & Guo, K. (2024). MPNet: temporal knowledge graph completion based on a multi-policy network . Applied Intelligence, 1-17. Github
[1] Li, X., Zhou, H., Yao, W., Li, W., Liu, B., & Lin, Y. (2024). Intricate Spatiotemporal Dependency Learning for Temporal Knowledge Graph Reasoning . ACM Transactions on Knowledge Discovery from Data.
Information Science
[1] (THOR) Lee, Y. C., Lee, J., Lee, D., & Kim, S. W. (2024). Learning to compensate for lack of information: Extracting latent knowledge for effective temporal knowledge graph completion . Information Sciences, 654, 119857.
Extended version from: Y. -C. Lee, J. Lee, D. Lee and S. -W. Kim, “THOR: Self-Supervised Temporal Knowledge Graph Embedding via Three-Tower Graph Convolutional Networks,” 2022 IEEE International Conference on Data Mining (ICDM), Orlando, FL, USA, 2022, pp. 1035-1040, doi: 10.1109/ICDM54844.2022.00127. Github
[2] (Joint-MTComplEx) Zhang, F., Chen, H., Shi, Y., Cheng, J., & Lin, J. (2024). Joint framework for tensor decomposition-based temporal knowledge graph completion . Information Sciences, 654, 119853.
[3] (DGTL) Liu, Z., Li, Z., Li, W., & Duan, L. (2024). Deep Graph Tensor Learning for Temporal Link Prediction . Information Sciences, 120085. Github
[4] (CRmod) Zhu, L., Chai, D., & Bai, L. (2024). CRmod: Context-Aware Rule-Guided reasoning over temporal knowledge graph . Information Sciences, 120343. Github
[5] Dai, Y., Guo, W., & Eickhoff, C. (2024). Wasserstein adversarial learning based temporal knowledge graph embedding . Information Sciences, 659, 120061.
[6] Xu, X., Jia, W., Yan, L., Lu, X., Wang, C., & Ma, Z. (2024). Spatiotemporal knowledge graph completion via diachronic and transregional word embedding . Information Sciences, 120477.
Information Fusion
[1] (MvTuckER) Wang, H., Yang, J., Yang, L. T., Gao, Y., Ding, J., Zhou, X., & Liu, H. (2024). MvTuckER: Multi-view knowledge graphs represention learning based on tensor tucker model . Information Fusion, 102249.
Information Processing & Management
[1] (STKGR-PR) Meng, X., Bai, L., Hu, J., & Zhu, L. (2024). Multi-hop path reasoning over sparse temporal knowledge graphs based on path completion and reward shaping . Information Processing & Management, 61(2), 103605. Github
Expert Systems with Applications
[1] (CDRGN-SDE) Zhang, D., Feng, W., Wu, Z., Li, G., & Ning, B. (2024). CDRGN-SDE: Cross-Dimensional Recurrent Graph Network with neural Stochastic Differential Equation for temporal knowledge graph embedding . Expert Systems with Applications, 123295. Github
[2] (TPComplEx) Yang, J., Ying, X., Shi, Y., & Xing, B. (2024). Tensor decompositions for temporal knowledge graph completion with time perspective . Expert Systems with Applications, 237, 121267. Github
Frontiers of Computer Science
[1] (EvolveKG) Liu, J., Yu, Z., Guo, B., Deng, C., Fu, L., Wang, X., & Zhou, C. (2024). EvolveKG: a general framework to learn evolving knowledge graphs . Frontiers of Computer Science, 18(3), 183309.
Neural networks
[1] Shao, P., Tao, J., & Zhang, D. (2024). Bayesian hypernetwork collaborates with time-difference evolutional network for temporal knowledge prediction . Neural Networks, 106146.
[2] Bai, L., Li, N., Li, G., Zhang, Z., & Zhu, L. (2024). Embedding-based Entity Alignment of Cross-Lingual Temporal Knowledge Graphs . Neural Networks, 106143.
[3] 🔥 Mei, X., Yang, L., Jiang, Z., Cai, X., Gao, D., Han, J., & Pan, S. (2024). An Inductive Reasoning Model based on Interpretable Logical Rules over temporal knowledge graph . Neural Networks, 106219. Github
Engineering Applications of Artificial Intelligence
[1] Zhu, L., Zhao, W., & Bai, L. (2024). Quadruple mention text-enhanced temporal knowledge graph reasoning . Engineering Applications of Artificial Intelligence, 133, 108058. Github
Journal of Intelligent Information Systems
[1] Du, C., Li, X., & Li, Z. (2024). Semantic-enhanced reasoning question answering over temporal knowledge graphs . Journal of Intelligent Information Systems, 1-23.
Artificial Intelligence
[1] Dong, H., Wang, P., Xiao, M., Ning, Z., Wang, P., & Zhou, Y. (2024). Temporal Inductive Path Neural Network for Temporal Knowledge Graph Reasoning . Artificial Intelligence, 104085. Github
IEEE Transactions on Fuzzy Systems
[1] Ji, H., Yan, L., & Ma, Z. (2023). FSTRE: Fuzzy Spatiotemporal RDF Knowledge Graph Embedding Using Uncertain Dynamic Vector Projection and Rotation . IEEE Transactions on Fuzzy Systems.
Electronics
[1] 🔥 Xu, H., Bao, J., Li, H., He, C., & Chen, F. (2024). A Multi-View Temporal Knowledge Graph Reasoning Framework with Interpretable Logic Rules and Feature Fusion . Electronics, 13(4), 742.
Neurocomputing
[1] He, M., Zhu, L., & Bai, L. (2024). ConvTKG: A query-aware convolutional neural network-based embedding model for temporal knowledge graph completion . Neurocomputing, 127680.
Semantic Web Journal
[1] (TRKGE) Song, B., Amouzouvi, K., Xu, C., Wang, M., Lehmann, J., & Vahdati, S. Temporal Relevance for Representing Learning over Temporal Knowledge Graphs .
[1] (TPRG) Bai, L., Chen, M., Zhu, L., & Meng, X. (2023). Multi-hop temporal knowledge graph reasoning with temporal path rules guidance . Expert Systems with Applications, 223, 119804. Github
The Journal of Supercomputing
[1] (TKGA) Wang, Z., You, X., & Lv, X. (2023). A relation enhanced model for temporal knowledge graph alignment . The Journal of Supercomputing, 1-23.
Information Systems
[1] (RITI) Liu, R., Yin, G., Liu, Z., & Tian, Y. (2023). Reinforcement learning with time intervals for temporal knowledge graph reasoning . Information Systems, 102292.
Information Sciences
[1] (T-GAE) Hou, X., Ma, R., Yan, L., & Ma, Z. (2023). T-GAE: A Timespan-Aware Graph Attention-based Embedding Model for Temporal Knowledge Graph Completion . Information Sciences, 119225.
[2] (TASTER) Wang, X., Lyu, S., Wang, X., Wu, X., & Chen, H. (2023). Temporal knowledge graph embedding via sparse transfer matrix . Information Sciences, 623, 56-69.
[3] (TLmod) Bai, L., Yu, W., Chai, D., Zhao, W., & Chen, M. (2023). Temporal knowledge graphs reasoning with iterative guidance by temporal logical rules . Information Sciences, 621, 22-35.
IEEE/ACM Transactions on Audio, Speech, and Language Processing
[1] (TARGAT) Xie, Z., Zhu, R., Liu, J., Zhou, G., & Huang, J. X. (2023). TARGAT: A Time-Aware Relational Graph Attention Model for Temporal Knowledge Graph Embedding . IEEE/ACM Transactions on Audio, Speech, and Language Processing.
[1] (TBDRI) Yu, M., Guo, J., Yu, J., Xu, T., Zhao, M., Liu, H., … & Yu, R. (2023). TBDRI: block decomposition based on relational interaction for temporal knowledge graph completion . Applied Intelligence, 53(5), 5072-5084.
[2] (GLANet) Wang, J., Lin, X., Huang, H., Ke, X., Wu, R., You, C., & Guo, K. (2023). GLANet: temporal knowledge graph completion based on global and local information-aware network . Applied Intelligence, 1-17.
[3] (ChronoR-CP) Li, M., Sun, Z., Zhang, W., & Liu, W. (2023). Leveraging semantic property for temporal knowledge graph completion . Applied Intelligence, 53(8), 9247-9260.
[4] (TIAR) Mu, C., Zhang, L., Ma, Y., & Tian, L. (2023). Temporal knowledge subgraph inference based on time-aware relation representation . Applied Intelligence, 53(20), 24237-24252.
[5] (TNTSimplE) He, P., Zhou, G., Zhang, M., Wei, J., & Chen, J. (2023). Improving temporal knowledge graph embedding using tensor factorization . Applied Intelligence, 53(8), 8746-8760.
Neural Networks
[1] (TFSC) Zhang, H., & Bai, L. (2023). Few-shot link prediction for temporal knowledge graphs based on time-aware translation and attention mechanism . Neural Networks, 161, 371-381. Github
[2] Shao, P., Liu, T., Che, F., Zhang, D., & Tao, J. (2023). Adaptive pseudo-Siamese policy network for temporal knowledge prediction . Neural Networks.
[1] Shao, P., He, J., Li, G., Zhang, D., & Tao, J. (2023). Hierarchical Graph Attention Network for Temporal Knowledge Graph Reasoning . Neurocomputing, 126390.
[2] (TANGO) Wang, Z., Ding, D., Ren, M., & Conti, M. (2023). TANGO: A Temporal Spatial Dynamic Graph Model for Event Prediction . Neurocomputing, 126249.
IEEE Transactions on Neural Networks and Learning Systems
[1] (QDN) Wang, J., Wang, B., Gao, J., Li, X., Hu, Y., & Yin, B. (2023). QDN: A Quadruplet Distributor Network for Temporal Knowledge Graph Completion . IEEE Transactions on Neural Networks and Learning Systems. Github
Journal of Systems Science and Systems Engineering
[1] Yan, Z., & Tang, X. (2023). Narrative Graph: Telling Evolving Stories Based on Event-centric Temporal Knowledge Graph . Journal of Systems Science and Systems Engineering, 32(2), 206-221.
[1] (RoAN) Bai, L., Ma, X., Meng, X., Ren, X., & Ke, Y. (2023). RoAN: A relation-oriented attention network for temporal knowledge graph completion . Engineering Applications of Artificial Intelligence, 123, 106308. Github
Future Generation Computer Systems
[1] (TAL-TKGC) Nie, H., Zhao, X., Yao, X., Jiang, Q., Bi, X., Ma, Y., & Sun, Y. (2023). Temporal-structural importance weighted graph convolutional network for temporal knowledge graph completion . Future Generation Computer Systems.
Cognitive Computation
[2] (MsCNN) Liu, W., Wang, P., Zhang, Z., & Liu, Q. (2023). Multi-Scale Convolutional Neural Network for Temporal Knowledge Graph Completion . Cognitive Computation, 1-7.
ACM Transactions on Knowledge Discovery from Data
[1] (DuCape) Zhang, S., Liang, X., Tang, H., Zheng, X., Zhang, A. X., & Ma, Y. DuCape: Dual Quaternion and Capsule Network Based Temporal Knowledge Graph Embedding . ACM Transactions on Knowledge Discovery from Data.
IEEE Transactions on Knowledge and Data Engineering
[1] Li, Y., Chen, H., Li, Y., Li, L., Philip, S. Y., & Xu, G. (2023). Reinforcement Learning based Path Exploration for Sequential Explainable Recommendation . IEEE Transactions on Knowledge and Data Engineering. Github
[1] (RLAT) Bai, L., Chai, D., & Zhu, L. (2023). RLAT: Multi-hop temporal knowledge graph reasoning based on Reinforcement Learning and Attention Mechanism . Knowledge-Based Systems, 269, 110514.
Journal of Computational Design and Engineering
[1] (MetaRT) Zhu, L., Xing, Y., Bai, L., & Chen, X. (2023). Few-shot link prediction with meta-learning for temporal knowledge graphs . Journal of Computational Design and Engineering, 10(2), 711-721.
[1] 🔥 (IMF) Du, Z., Qu, L., Liang, Z., Huang, K., Cui, L., & Gao, Z. (2023). IMF: Interpretable Multi-Hop Forecasting on Temporal Knowledge Graphs . Entropy, 25(4), 666. Github
Complex & Intelligent Systems
[1] (FTMO) Zhu, L., Bai, L., Han, S., & Zhang, M. (2023). Few-shot temporal knowledge graph completion based on meta-optimization . Complex & Intelligent Systems, 9(6), 7461-7474. Github
World Wide Web
[1] (FTMF) Bai, L., Zhang, M., Zhang, H., & Zhang, H. (2023). FTMF: Few-shot temporal knowledge graph completion based on meta-optimization and fault-tolerant mechanism . World Wide Web, 26(3), 1243-1270. Github
[1] (OSLT) Ma, R., Mei, B., Ma, Y., Zhang, H., Liu, M., & Zhao, L. (2023). One-shot relational learning for extrapolation reasoning on temporal knowledge graphs . Data Mining and Knowledge Discovery, 1-18.
[1] (EvoExplore) Jiasheng Zhang, Shuang Liang, Yongpan Sheng, Jie Shao. “Temporal knowledge graph representation learning with local and global evolutions” . Knowledge-Based Systems 2022. Github
[2] (TuckERT) Pengpeng Shao, Dawei Zhang, Guohua Yang, Jianhua Tao, Feihu Che, Tong Liu. “Tucker decomposition-based temporal knowledge graph completion” . Knowledge Based Systems 2022. Github
[1] (BTDG) Yujing Lai, Chuan Chen, Zibin Zheng, Yangqing Zhang. “Block term decomposition with distinct time granularities for temporal knowledge graph completion” . Expert Systems with Applications 2022. Github
Applied Soft Computing
[1] (TPath) Luyi Bai, Wenting Yu, Mingzhuo Chen, Xiangnan Ma. “Multi-hop reasoning over paths in temporal knowledge graphs using reinforcement learning” . Applied Soft Computing 2021.
[1] (TPmod) Bai, L., Ma, X., Zhang, M., & Yu, W. (2021). Tpmod: A tendency-guided prediction model for temporal knowledge graph completion . ACM Transactions on Knowledge Discovery from Data, 15(3), 1-17. Github
[2] (Dacha) Chen, L., Tang, X., Chen, W., Qian, Y., Li, Y., & Zhang, Y. (2021). Dacha: A dual graph convolution based temporal knowledge graph representation learning method using historical relation . ACM Transactions on Knowledge Discovery from Data (TKDD), 16(3), 1-18.
IEEE Access
[1] (TDG2E) Tang, X., Yuan, R., Li, Q., Wang, T., Yang, H., Cai, Y., & Song, H. (2020). Timespan-aware dynamic knowledge graph embedding by incorporating temporal evolution . IEEE Access, 8, 6849-6860.
[2] (3DRTE) Wang, J., Zhang, W., Chen, X., Lei, J., & Lai, X. (2020). 3drte: 3d rotation embedding in temporal knowledge graph . IEEE Access, 8, 207515-207523.
Journal of Web Semantics
[1] (ConT) Ma, Y., Tresp, V., & Daxberger, E. A. (2019). Embedding models for episodic knowledge graphs . Journal of Web Semantics, 59, 100490.
Temporal Knowledge Graph Entity Alignment via Representation Learning
- Conference paper
- First Online: 08 April 2022
- Cite this conference paper
- Xiuting Song 16 ,
- Luyi Bai 16 ,
- Rongke Liu 16 &
- Han Zhang 16
Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13246))
Included in the following conference series:
- International Conference on Database Systems for Advanced Applications
3179 Accesses
2 Citations
Entity alignment aims to construct a complete knowledge graph (KG) by matching the same entities in multi-source KGs. Existing methods mainly focused on the static KG, which assumes that the relationship between entities is permanent. However, almost every KG will evolve over time in practical applications, resulting in the need for entity alignment between such temporal knowledge graphs (TKGs). In this paper, we propose a novel entity alignment framework suitable for TKGs, namely Tem-EA. To incorporate temporal information, we use recurrent neural networks to learn temporal sequence representations. Furthermore, we use graph convolutional network (GCN) and translation-based embedding model to fully learn structural information representation and attribute information representation. Based on these two representations, the entity similarity is calculated separately and combined using linear weighting. To improve the accuracy of entity alignment, we also propose a concept of nearest neighbor matching, which matches the most similar entity pair according to distance matrix. Experiments show that our proposed model has a significant improvement compared to previous methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
- Available as PDF
- Read on any device
- Instant download
- Own it forever
- Available as EPUB and PDF
- Compact, lightweight edition
- Dispatched in 3 to 5 business days
- Free shipping worldwide - see info
Tax calculation will be finalised at checkout
Purchases are for personal use only
Institutional subscriptions
Asamoah, C., Tao, L., Gai, K., Jiang, N.: Powering filtration process of cyber security ecosystem using knowledge graph. In: CSCloud, pp. 240–246 (2016)
Google Scholar
Bordes, A., Usunier, N., García-Durán, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: NIPS, pp. 2787–2795 (2013)
Chen, M., Tian, Y., Yang, M., Zaniolo, C.: Multilingual knowledge graph embeddings for cross-lingual knowledge alignment. In: IJCAI, pp. 1511–1517 (2017)
Chen, M., Tian, Y.N., Chang, K., Skiena, S., Zaniolo, C.: Co-training embeddings of knowledge graphs and entity descriptions for cross-lingual entity alignment. In: IJCAI, pp. 3998–4004 (2018)
Cao, Y., Wang, X., He, X., Hu, Z., Chua, T. S.: Unifying knowledge graph learning and recommendation: Towards a better understanding of user preferences. In: WWW, pp. 151–161 (2019)
Cao, Y., Liu, Z., Li, C., Liu, Z., Li, J., Chua, T.S.: Multi-channel graph neural network for entity alignment. In ACL, pp. 1452–1461 (2019)
Dasgupta, S.S., Ray, S.N., Talukdar, P.P.: HyTE: hyperplane-based temporally aware knowledge graph embedding. In: EMNLP, pp. 2001–2011 (2018)
Erxleben, F., Günther, M., Krötzsch, M., Mendez, J., Vrandečić, D.: Introducing wikidata to the linked data web. In: Mika, P., et al. (eds.) ISWC 2014. LNCS, vol. 8796, pp. 50–65. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-11964-9_4
Chapter Google Scholar
Goel, R., Kazemi, S.M., Brubaker, M., Poupart, P.: Diachronic embedding for temporal knowledge graph completion. In: AAAI, pp. 3988–3995 (2020)
García-Durán, A., Dumančić S., Niepert, M.: Learning sequence encoders for temporal knowledge graph completion. In: EMNLP, pp. 4816–4821 (2018)
Jin, W., Qu, M., Jin, X., Ren, X.: Recurrent event network: autoregressive structure inference over temporal knowledge graphs. In: EMNLP (2020)
Leblay, J., Chekol, M.W.: Deriving validity time in knowledge graph. In: Champin, pp. 1771–1776 (2018)
Liao, S., Liang, S., Meng, Z., Zhang, Q.: Learning dynamic embeddings for temporal knowledge graphs. In: WSDM, pp. 535–543 (2021)
Mahdisoltani, F., Biega, J., Suchanek, F.M.: Yago3: A knowledge base from multilingual wikipedias. In: CIDR (2013)
Nickel, M., Tresp, V., Kriegel, H.P.: A three-way model for collective learning on multi-relational data. In: ICML (2011)
Sun, Z., Wang, C., Hu, W., Chen, M., Dai, J., Zhang, W., Qu, Y.: Knowledge graph alignment network with gated multi-hop neighborhood aggregation. In: AAAI, pp. 222–229 (2020)
Sun, Z., Hu, W., Zhang, Q., Qu, Y.: Bootstrapping entity alignment with knowledge graph embedding. In: IJCAI, pp. 4396–4402 (2018)
Sun, Z., Hu, W., Li, C.: Cross-lingual entity alignment via joint attribute-preserving embedding. In: d’Amato, C., et al. (eds.) ISWC 2017. LNCS, vol. 10587, pp. 628–644. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-68288-4_37
Trouillon, T., Welbl, J., Riedel, S., Gaussier, E., Bouchard, G.: Complex embeddings for simple link prediction. In: ICML, pp. 2071–2080 (2016)
Trivedi, R., Dai, H., Wang, Y., Song, L.: Know-evolve: Deep temporal reasoning for dynamic knowledge graphs. In: ICML, pp. 3462–3471 (2017)
Trsedya, B.D., Qi, J., Rui, Z.: Entity alignment between knowledge graphs using attribute embeddings. In: AAAI, pp. 297–304 (2019)
Wang, Z., Lv, Q., Lan, X., Zhang, Y.: Cross-lingual knowledge graph alignment via graph convolutional networks. In: EMNLP, pp. 349–357 (2018)
Wu, Y., Liu, X., Feng, Y., Wang, Z., Zhao, D.: Jointly learning entity and relation representations for entity alignment. In: EMNLP (2019)
Wu, Y., Liu, X., Feng, Y., Wang, Z., Yan, R., Zhao, D.: Relation-aware entity alignment for heterogeneous knowledge graphs. In: IJCAI (2019)
Xu, C., Nayyeri, M., Alkhoury, F., Yazdi, H. S., Lehmann, J.: Temporal knowledge graph embedding model based on additive time series decomposition. arXiv preprint arXiv:1911.07893 (2019)
Yang, B., Yih, W., He, X., Gao, J., Deng, L.: Embedding entities and relations for learning and inference in knowledge bases. In: ICLR (2015)
Yan, Z., Peng, R., Wang, Y., Li, W.: CTEA: Context and topic enhanced entity alignment for knowledge graphs. In: Neurocomputing, pp. 419–431 (2020)
Yih, W.T., Chang, M.W., He, X., Gao J.: Semantic parsing via staged query graph generation: question answering with knowledge base. In: ACL, pp. 1321–1331 (2015)
Zhu, Y., Liu, H., Wu, Z., Du, Y.: Relation-aware neighborhood matching model for entity alignment. In: AAAI, pp. 4749–4756 (2021)
Zhang, S., Tay, Y., Yao, L., Liu, Q.: Quaternion knowledge graph embeddings. In: NIPS, pp. 2731–2741 (2019)
Zhu, H., Xie, R., Liu, Z., Sun, M.: Iterative entity alignment via joint knowledge embeddings. In: IJCAI, pp. 4258–4264 (2017)
Zhang, Q., Sun, Z., Hu, W., Chen, M., Guo, L., Qu, Y.: Multi-view knowledge graph embedding for entity alignment. In: IJCAI, pp. 5429–5435 (2019)
Zhang, Z., Bu, J., Li, Z., Yao, C., Wang, C., Wu, J.: TigeCMN: On exploration of temporal interaction graph embedding via coupled memory neural networks. In: Neural Networks, pp. 13–26 (2021)
Download references
Acknowledgment
The work was supported by the National Natural Science Foundation of China (61402087), the Natural Science Foundation of Hebei Province (F2019501030), the Key Project of Scientific Research Funds in Colleges and Universities of Hebei Education Department (ZD2020402), the Fundamental Research Funds for the Central Universities (N2023019), and in part by the Program for 333 Talents in Hebei Province (A202001066).
Author information
Authors and affiliations.
School of Computer and Communication Engineering, Northeastern University (Qinhuangdao), Qinhuangdao, 066004, China
Xiuting Song, Luyi Bai, Rongke Liu & Han Zhang
You can also search for this author in PubMed Google Scholar
Corresponding author
Correspondence to Luyi Bai .
Editor information
Editors and affiliations.
Dept. of Computer Science&Engr., Indian Institutes of Technology, Kanpur, Uttar Pradesh, India
Arnab Bhattacharya
National University of Singapore, Singapore, Singapore
Janice Lee Mong Li
University of California, Santa Barbara, Santa Barbara, CA, USA
Divyakant Agrawal
IIIT Hyderabad, Hyderabad, India
P. Krishna Reddy
Indraprastha Institute of Information Technology Delhi, New Delhi, India
Mukesh Mohania
Ashoka University, Sonepat, Haryana, India
Anirban Mondal
Indraprastha Institute of Information Te, New Delhi, India
Vikram Goyal
University of Aizu, Aizu, Japan
Rage Uday Kiran
Rights and permissions
Reprints and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper.
Song, X., Bai, L., Liu, R., Zhang, H. (2022). Temporal Knowledge Graph Entity Alignment via Representation Learning. In: Bhattacharya, A., et al. Database Systems for Advanced Applications. DASFAA 2022. Lecture Notes in Computer Science, vol 13246. Springer, Cham. https://doi.org/10.1007/978-3-031-00126-0_30
Download citation
DOI : https://doi.org/10.1007/978-3-031-00126-0_30
Published : 08 April 2022
Publisher Name : Springer, Cham
Print ISBN : 978-3-031-00125-3
Online ISBN : 978-3-031-00126-0
eBook Packages : Computer Science Computer Science (R0)
Share this paper
Anyone you share the following link with will be able to read this content:
Sorry, a shareable link is not currently available for this article.
Provided by the Springer Nature SharedIt content-sharing initiative
- Publish with us
Policies and ethics
- Find a journal
- Track your research
GTRL: An Entity Group-Aware Temporal Knowledge Graph Representation Learning Method
Ieee account.
- Change Username/Password
- Update Address
Purchase Details
- Payment Options
- Order History
- View Purchased Documents
Profile Information
- Communications Preferences
- Profession and Education
- Technical Interests
- US & Canada: +1 800 678 4333
- Worldwide: +1 732 981 0060
- Contact & Support
- About IEEE Xplore
- Accessibility
- Terms of Use
- Nondiscrimination Policy
- Privacy & Opting Out of Cookies
A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity. © Copyright 2024 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.
Refereed Journal and Conference Papers
- Yongpan Sheng , A syntactic-based model for open relation extraction . Computer Science ( Computer Science ). (In Chinese) (To be Submitted)
- Xiaoshi Wang, Yongpan Sheng *, Guangyu Zhang, Zhuping Ding, Lirong He, An Adaptive Clustering Centered-Oriented Projection Method for Hypernym-Hyponym Relation Identification .
- Yongpan Sheng , Chunyan Liu, Lirong He , and Yan Lei *, A Systematical Study on Dynamic Fault Localization for Machine Learning Methods . (To be Submitted)
- Yongpan Sheng *, Lirong He , and Wenjie Li, A Short Survey on Deep Learning-Based Open Relation Extraction: Recent Advances, Resources and Perspective . (Under Review)
- Lirong He , Yongpan Sheng *, Hekai Zhang , Meng Chen , and Jiatian Pi , Semantic-Path Guided Graph Neural Network for Heterogeneous Graph Embedding . Mathmetics ( Mathmetics ). (Minor for Accepted)
- Hao Zhou, Zekai Chen, Yun Liu, Yongpan Sheng , Wenqi Ren, and Hailing Xiong, Physical-priors-guided DehazeFormer . Knowledge-Based Systems ( KBS ). (IF = 8.038, CCF-C, JCR Q1, 中科院 Q1)
- Chunyan Liu, Yan Lei , Yongpan Sheng , Meng Yan , Xiaoguang Mao, and Zhou Xu , Review on Dynamic Fault Localization Methods Based on Machine Learning . (Under Review)
- Yongpan Sheng , Lirong He , Incorporating Contextualized Definition into Term-Pair Representations for Enhanced Hypernym-hyponym Relation Identification . (Under Review)
- Yongpan Sheng , Lirong He , Fuli Huang , and Jie Shao *, An Overview of Embedding Models of Entities and Relationships for Temporal Knowledge Graph Completion . (Under Review)
- Yongpan Sheng , An Extraction and Verification Framework for Harvesting Temporal Knowledge Graph from News Articles . (To be Submitted)
- Peng Zhao, Yongpan Sheng , and Xiaohui Zhan*, An advanced NMF-based approach for single cell data clustering . The 2022 2nd International Conference on Information Communication and Software Engineering ( ICICSE-22 ). Chongqing, China, March 18-20 2022 (EI Indexed)
- Jiasheng Zhang, Shuang Liang, Yongpan Sheng , and Jie Shao *, Temporal knowledge graph representation learning with local and global evolutions . Knowledge-Based Systems ( KBS ). (IF = 8.038, CCF-C, JCR Q1, 中科院 Q1)
- Meng Chen , Jiaxin Hou, Yongpan Sheng , Yingbo Wu *, Sen Wang , Jianyuan Lu, and Qilin Fan , HA-D3QN: Embedding Virtual Private Cloud in Cloud Data Centers with Heuristic Assisted Deep Reinforcement Learning . Future Generation Computer Systems ( FGCS ). (IF = 7.307 in 2022, JCR Q1, 中科院 Q1)
- Yongpan Sheng # , Jiasheng Zhang # , Lirong He , Xiaohong Zhang, and Jie Shao , TKBData: A Large-Scale Temporal Knowledge Base Dataset with Evaluation on State-of-the-Art Tasks . The 28th International Conference on Computational Linguistics ( COLING-20 ). Barcelona, Spain, December 8-11 2019 (CCF: B) (To be Submitted)
- Jiasheng Zhang, Yongpan Sheng *, Zheng Wang, and Jie Shao , TKGFrame: A Two-Phase Framework for Temporal-Aware Knowledge Graph Completion . The 4th Asia Pacific Web and Web-Age Information Management Joint Conference on Web and Big Data ( APWeb-WAIM-20 ). Tianjin, China, August 12-14 2020 (CCF-C)
- Yongpan Sheng # , Lirong He # , and Jie Shao , A Hybrid Neural Network Model for Hypernym-hyponym Relation Identification . Information Sciences ( IS ). (IF = 5.910, CCF-B, JCR Q1, 中科院 Q1) (In Press)
- Guanglin Niu , Bo Li , Yongfei Zhang *, Yongpan Sheng , Chuan Shi , Jingyang Li, and Shiliang Pu, Joint Semantics and Data-Driven Path Representation for Knowledge Graph Inference . Neurocomputing ( Neurocomputing ). (IF = 5.719, CCF-C, JCR Q1, 中科院 Q1)
- Yongpan Sheng , Research and Application of Learning Methods for Knowledge Graphs , Chengdu: University of Electronic Science and Technology of China. (Doctoral Dissertation, In Chinese)
- (SELECTED) Yongpan Sheng , Zenglin Xu , Yafang Wang , and Gerard de Melo *, Multi-document semantic relation extraction for news analytics . World Wide Web: Internet and Web Information Systems ( WWW Journal ). (IF = 1.15, CCF-B)
- Yongpan Sheng , and Haojie Huang, A Framework for Graph-based Multi-Document Relation Exploration: A Case Study on the News Datasets . The Annual Conference of the 8th National Conference on Social Media Processing ( SMP-19 ). Shenzhen, China, August 16-18 2019
- Yongpan Sheng , and Zenglin Xu , Coherence and Salience-Based Multi-Document Relationship Mining . The 3rd Asia Pacific Web and Web-Age Information Management Joint Conference on Web and Big Data ( APWeb-WAIM-19 ). Chengdu, China, August 1-3 2019 (CCF-C)
- Yongpan Sheng , Meng Wang *, Tianxing Wu , and Han Xu, Adaptive Local Learning Regularized Nonnegative Matrix Factorization for Data Clustering . Applied Intelligence ( AI ). (IF = 1.651, JCR Q2, 中科院 Q3)
- Yongpan Sheng , Hekai Zhang , Jibing Gong , Lirong He , and Xuefeng Fu , Hypernym-hyponym relation detection method by incorporating textual knowledge . Journal of Computer Applications ( JCA ). (In Chinese)
- Han Xu*, Xiwei Qiu , Yongpan Sheng , Liang Luo , and Yanping Xiang *, A Qos-driven Approach for Cloud Service Addressing Attribute of Security . IEEE Access ( IEEE Access ). (IF = 3.557, JCR Q1, 中科院 Q2)
- (SELECTED) Yongpan Sheng , Zenglin Xu , Yafang Wang , Xiangyu Zhang, Jia Jia, Zhonghui You , and Gerard de Melo , Visualizing Multi-Document Semantics via Open Domain Information Extraction . The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases ( ECML-PKDD-18 ). Dublin, Ireland, September 10-14, 2018 (CCF-B) (Demonstration Paper)
- Lirong He , Bin Liu , Guangxi Li , Yongpan Sheng , Yafang Wang , and Zenglin Xu , Knowledge Base Completion by Variational Bayesian Neural Tensor Decomposition . Cognitive Computation ( Cognitive Computation ). (IF = 3.479, JCR Q1, 中科院 Q2)
- Yongpan Sheng , Xuefeng Fu *, and Tianxing Wu , Multi-document conceptual graph construction research based on open domain extraction . Application Research of Computers ( ARC ). (In Chinese)
- Yazhou Ren , Peng Zhao, Yongpan Sheng , Dezhong Yao, and Zenglin Xu , A Robust Softmax Regression for Multi-class Classification with Self-Paced Learning . The 26th International Joint Conference on Artificial Intelligence ( IJCAI-17 ). Melbourne, Australia, August 19-25 2017 (CCF-A)
Before 2017
- Yongpan Sheng , Yangyang Wang, Lu Wang, and Gaofeng Zhao, A comparison of learning rules in pulse-based neural networks . The 13th International Computer Conference on Wavelet Active Media Technology and Information Processing ( ICCWAMTIP-16 ). Chengdu, China, December 16-18 2016 (EI Indexed)
- Xiaojia Pan, Lei Wu, Dean Wu, and Yongpan Sheng , Ant colony Optimization of Virtual Machine Placement for Data Latency Minimization in Cloud Systems . The 12nd International Computer Conference on Wavelet Active Media Technology and Information Processing ( ICCWAMTIP-15 ). Chengdu, China, December 18-20 2016 (EI Indexed)
Manuscript/Preprints
- Jinze Sun, Yongpan Sheng , Ling Zhan, and Lirong He , TemT: A New Temporal Knowledge Graph Completion Method with Transformer Hawkes Process and Random Walk Aggregation Strategy .
- Jinze Sun, Yongpan Sheng , Ling Zhan, and Lirong He , TemT: A New Temporal Knowledge Graph Completion Method with Transformer Hawkes Process and Random Walk Aggregation Strategy , 2023.05.28, China (Submitted)
- Zenglin Xu , Lirong He , Bin Liu , Guangxi Li , Yongpan Sheng , Yafang Wang , A Method of Knowledge Base Completion by Variational Bayesian Neural Tensor Decomposition (No. ZL201610578882.9), 2018.09.04, China (Authorized)
- Yongpan Sheng , Yan Zhang, Peng Zhao, Ying Xie, Lu Wang, A Hierarchical Classification Method of Email Contents (No. ZL201610793018.0), 2019.03.15, China (Authorized)
IMAGES
VIDEO
COMMENTS
3.1. Evolution of the temporal knowledge graph. Definition 1 Temporal Knowledge Graph. A temporal knowledge graph (TKG) is defined as a directed graph with timestamps G = (E, R, T), where E and R are the entity set and relation set, respectively. T is the set of valid timestamps. Each knowledge in TKG is represented as a quadruple (s, r, o, τ), in which s ∈ E and o ∈ E are the subject and ...
Temporal knowledge graph (TKG) representation learning aims to project entities and relations in TKGs to a low-dimensional vector space while preserving the evolutionary nature of TKGs. Most ...
2023. TLDR. A novel Knowledge Evolution with Time Duration (KETD) model is proposed for knowledge representation of temporal knowledge graphs with finer-time granularities and is the first attempt to learn embeddings of time durations and combines them into embeddings of entities and relations to predict potential periodic facts. Expand.
2.1. Problem Formulation. A temporal knowledge graph is a directed multi-relational graph containing structured facts. It is usually expressed as G = (E, R, T, F), where E, R, and. T are the sets of entities, relations, and timestamps, respectively, and F ⊂. E × R × E × T is the set of all possible facts.
Knowledge graphs have garnered significant research attention and are widely used to enhance downstream applications. However, most current studies mainly focus on static knowledge graphs, whose facts do not change with time, and disregard their dynamic evolution over time. As a result, temporal knowledge graphs have attracted more attention because a large amount of structured knowledge ...
PDF (PC) 1983. 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 ...
Temporal knowledge graph representation learning with local and global evolutions. Abstract . Temporal knowledge graph (TKG) representation learning aims to project entities and relations in TKGs to a low-dimensional vector space while preserving the evolutionary nature of TKGs. Most existing methods treat knowledge that ...
Knowledge graph completion (KGC) has been widely explored, but the task of temporal knowledge graph completion (TKGC) for predicting future events is far from perfection. Some embedding-based approaches have achieved significant results on the TKGC task by modeling the structural information of each temporal snapshot and the evolution between temporal snapshots. However, due to the uneven ...
As a result, temporal knowledge graphs have attracted more attention because a large amount of structured knowledge exists only within a specific period. Knowledge graph representation learning aims to learn low-dimensional vector embeddings for entities and relations in a knowledge graph. The representation learning of temporal knowledge ...
Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning. Pages 408-417. Previous Chapter ... we propose a novel Recurrent Evolution network based on Graph Convolution Network (GCN), called RE-GCN, which learns the evolutional representations of entities and relations at each timestamp by modeling the KG sequence ...
Temporal knowledge graph (TKG) representation learning aims to project entities and relations in TKG to low-dimensional vector space while preserving the evolutionary nature of TKG. Most existing methods separately treat knowledge that happened at different times, which fails to explore how temporal knowledge graph evolves over time.
Abstract. Temporal knowledge graphs store a large number of tempo-ral facts that simulate the dynamic interactions of entities along the timeline. Since existing temporal knowledge graphs often suffer from incompleteness, it is crucial to build time-aware representation learn-ing models that help to infer the missing temporal facts. However, most
Temporal knowledge graphs (TKGs) have been identified as a promising approach to represent the dynamics of facts along the timeline. The extrapolation of TKG is to predict unknowable facts happening in the future, holding significant practical value across diverse fields. Most extrapolation studies in TKGs focus on modeling global historical fact repeating and cyclic patterns, as well as local ...
In practical applications, the temporal completeness of knowledge graphs is of great importance. However, previous studies have mostly focused on static knowledge graphs, generally neglecting the dynamic evolutionary properties of facts. Moreover, the unpredictable and limited availability of temporal knowledge graphs, together with the complex temporal dependency patterns, make current models ...
contrastive learning to better guide the fusion of global and local historical information, and enhance the robust-ness of LogCL. To the best of our knowledge, LogCL is the first model to leverage local-global history-aware contrastive learning to improve model robustness in TKG reasoning. • We propose entity-aware attention applied to encode ...
Abstract. Temporal knowledge graphs store a large number of temporal facts that simulate the dynamic interactions of entities along the timeline. Since existing temporal knowledge graphs often suffer from incompleteness, it is crucial to build time-aware representation learning models that help to infer the missing temporal facts.
Temporal knowledge graph representation learning with local and global evolutions. Knowl. Based Syst., Vol. 251 (2022), 109234. Google Scholar Digital Library; Ying Zhou, Xuanang Chen, Ben He, Zheng Ye, and Le Sun. 2022. Re-thinking Knowledge Graph Completion Evaluation from an Information Retrieval Perspective. In SIGIR '22: The 45th ...
A Survey on Temporal Knowledge Graph: Representation Learning and Applications, ArXiv, 2024. paper Cai, Li, Xin Mao, ... "Temporal knowledge graph representation learning with local and global evolutions". Knowledge-Based Systems 2022. Github [2] (TuckERT) Pengpeng Shao, Dawei Zhang, Guohua Yang, Jianhua Tao, Feihu Che, Tong Liu. ...
2.1 Temporal Knowledge Graph Embedding. In recent years, the representation learning of static KGs has been extensively studied. Some examples of typical embedding models include TransE [], DistMult [], RESCAL [], ComplEx [] and QuatE [].These methods have been proved to be effective for the completion task of static KGs, but cannot model the temporal evolution of KGs due to their neglect of ...
the temporal reasoning tasks on six benchmark datasets. Especially, it achieves up to 11.46% improvement in MRR for entity predic-tion with up to 82 times speedup comparing to the state-of-the-art baseline. CCS CONCEPTS • Computing methodologies →Temporal reasoning. KEYWORDS Temporal knowledge graph, evolutional representation learning,
Temporal Knowledge Graph (TKG) representation learning embeds entities and event types into a continuous low-dimensional vector space by integrating the temporal information, which is essential for downstream tasks, e.g., event prediction and question answering. Existing methods stack multiple graph convolution layers to model the influence of distant entities, leading to the over-smoothing ...
Jiasheng Zhang, Shuang Liang, Yongpan Sheng, and Jie Shao*, Temporal knowledge graph representation learning with local and global evolutions. Knowledge-Based Systems . (IF = 8.038, CCF-C, JCR Q1, 中科院 Q1) Meng Chen, Jiaxin Hou, Yongpan Sheng, Yingbo Wu*, Sen Wang, Jianyuan Lu, and Qilin Fan, HA-D3QN: Embedding Virtual Private Cloud in ...
A Survey on Temporal Graph Representation Learning and Generative Modeling. Temporal graphs represent the dynamic relationships among entities and occur in many real life application like social networks, e commerce, communication, road networks, biological systems, and many more. They necessitate research beyond the work related to static ...