The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks
Abstract
Large knowledge graphs often grow to store temporal facts that model the dynamic relations or interactions of entities along the timeline. Since such temporal knowledge graphs often suffer from incompleteness, it is important to develop time-aware representation learning models that help to infer the missing temporal facts. While the temporal facts are typically evolving, it is observed that many facts often show a repeated pattern along the timeline, such as economic crises and diplomatic activities. This observation indicates that a model could potentially learn much from the known facts appeared in history. To this end, we propose a new representation learning model for temporal knowledge graphs, namely CyGNet, based on a novel time-aware copy-generation mechanism. CyGNet is not only able to predict future facts from the whole entity vocabulary, but also capable of identifying facts with repetition and accordingly predicting such future facts with reference to the known facts in the past. We evaluate the proposed method on the knowledge graph completion task using five benchmark datasets. Extensive experiments demonstrate the effectiveness of CyGNet for predicting future facts with repetition as well as de novo fact prediction.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“For convenience, many TKGC methods split time intervals into discrete time points [Zhu et al., 2021].”
From Temporal Knowledge Graph Completion: A Survey (2023) · cites this paper as Zhu et al., 2021
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“The outputs of the two modes are aggregated for the final prediction.”
From Temporal Knowledge Graph Completion: A Survey (2023) · cites this paper as Zhu et al., 2021
The cited source says what the claim attributes to it.
In the citing paper
“[Zhu et al., 2021] observes that history often repeats itself in the knowledge graph datasets; for example, they report that more than 80% of events recorded from 1995 to 2019 in ICEWS repository have occurred previously.”
From Temporal Knowledge Graph Completion: A Survey (2023) · cites this paper as Zhu et al., 2021
The cited source says what the claim attributes to it.
In the citing paper
“Based on this, the model consists of two modes (Copy and Generation) for inference.”
From Temporal Knowledge Graph Completion: A Survey (2023) · cites this paper as Zhu et al., 2021
The cited source says what the claim attributes to it.
In the citing paper
“The Copy mode learns the probability that the query is a repeat of related historical facts.”
From Temporal Knowledge Graph Completion: A Survey (2023) · cites this paper as Zhu et al., 2021
The cited source says what the claim attributes to it.
In the citing paper
“The Generation mode learns the probability of all possible candidates to be the prediction, with a linear classifier.”
From Temporal Knowledge Graph Completion: A Survey (2023) · cites this paper as Zhu et al., 2021
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Knowledge Graph Embedding by Translating on Hyperplanes
Wang, Z., Zhang, J., Feng, J., & Chen, Z. (2014) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v28i1.8870 · Cited by 3,915
A Survey on Knowledge Graphs: Representation, Acquisition, and Applications
Ji, S., Pan, S., Cambria, E., Marttinen, P., & Yu, P. S. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3070843 · Cited by 2,947
Complex Embeddings for Simple Link Prediction
Trouillon, T., Welbl, J., Riedel, S., Gaussier, É., & Bouchard, G. (2016) · arXiv · doi:10.48550/arxiv.1606.06357 · Cited by 2,100
RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
Sun, Z., Deng, Z.-H., Nie, J.-Y., & Tang, J. (2019) · arXiv · doi:10.48550/arxiv.1902.10197 · Cited by 1,414
SimplE Embedding for Link Prediction in Knowledge Graphs
Kazemi, S. M., & Poole, D. (2018) · arXiv · doi:10.48550/arxiv.1802.04868 · Cited by 476 · cited 1×
“2020) leverages diachronic embeddings to represent entities at different timestamps and employs the same score function as SimplE (Kazemi and Poole 2018) to score the plausibility of a quadruple.”
BackgroundSimulating the East African wildebeest migration patterns using GIS and remote sensing
Musiega, D. E., & Kazadi, S. (2004) · African Journal of Ecology · doi:10.1111/j.1365-2028.2004.00538.x · Cited by 46
Chen, T., Wang, Z., Li, L., Li, D., Li, Z., Chang, X., Bian, P., Liang, G., Wang, Q., & Xie, T. (2025) · Schloss Dagstuhl – Leibniz-Zentrum für Informatik · doi:10.4230/lipics.ecoop.2025.6
Research works printed but not linked: 36
- Balazevic, I.; Allen, C.; and Hospedales, T. 2019. TuckER: Tensor Factorization for Knowledge Graph Completion. In Proceedings of the 2019 Conference on Empirical Meth- ods in Natural Language Processing and the 9th Interna- tional Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 5188-5197.
- Bordes, A.; Usunier, N.; Garcia-Duran, A.; Weston, J.; and Yakhnenko, O. 2013. Translating embeddings for model- ing multi-relational data. In Advances in neural information processing systems, 2787-2795.
- Chen, J.; Chen, J.; and Yu, Z. 2019. Incorporating struc- tured commonsense knowledge in story completion. In Pro- ceedings of the AAAI Conference on Artificial Intelligence, volume 33, 6244-6251.
- Chen, M.; Zhang, H.; Wang, H.; and Roth, D. 2020. "What Are You Trying To Do?" Semantic Typing of Event Pro- cesses. In Proceedings of the 24th Conference on Computa- tional Natural Language Learning (CoNLL 2020).
- ACL.
- Dai, Y.; Wang, S.; Xiong, N. N.; and Guo, W. 2020. A Sur- vey on Knowledge Graph Embedding: Approaches, Appli- cations and Benchmarks. Electronics 9(5): 750.
- Dasgupta, S. S.; Ray, S. N.; and Talukdar, P. 2018. Hyte: Hyperplane-based temporally aware knowledge graph em- bedding. In Proceedings of the 2018 conference on empiri- cal methods in natural language processing, 2001-2011.
- Dettmers, T.; Minervini, P.; Stenetorp, P.; and Riedel, S. 2018. Convolutional 2D knowledge graph embeddings. In 32nd AAAI Conference on Artificial Intelligence, AAAI 2018, volume 32, 1811-1818. AAI Publications.
- Du, N.; Dai, H.; Trivedi, R.; Upadhyay, U.; Gomez- Rodriguez, M.; and Song, L. 2016. Recurrent marked tem- poral point processes: Embedding event history to vector. In KDD, 1555-1564.
- Fan, C.; Zeng, L.; Ding, Y.; Chen, M.; Sun, Y.; and Liu, Z. 2019. Learning to identify high betweenness centrality nodes from scratch: A novel graph neural network approach. In CIKM, 559-568.
- García-Durán, A.; Dumancic, S.; and Niepert, M. 2018. Learning Sequence Encoders for Temporal Knowledge Graph Completion. In EMNLP.
- Glorot, X.; and Bengio, Y. 2010. Understanding the diffi- culty of training deep feedforward neural networks. In Pro- ceedings of the thirteenth international conference on artifi- cial intelligence and statistics, 249-256.
- Goel, R.; Kazemi, S. M.; Brubaker, M.; and Poupart, P. 2020. Diachronic embedding for temporal knowledge graph completion. In AAAI.
- Gu, J.; Lu, Z.; Li, H.; and Li, V. O. 2016. Incorporating Copying Mechanism in Sequence-to-Sequence Learning. In Proceedings of the 54th Annual Meeting of the Associa- tion for Computational Linguistics (Volume 1: Long Papers), 1631-1640.
- Hao, J.; Ju, C. J.-T.; Chen, M.; Sun, Y.; Zaniolo, C.; and Wang, W. 2020. Bio-joie: Joint representation learning of biological knowledge bases. In ACM BCB, 1-10.
- He, H.; Balakrishnan, A.; Eric, M.; and Liang, P. 2017. Learning symmetric collaborative dialogue agents with dy- namic knowledge graph embeddings. In 55th Annual Meet- ing of the Association for Computational Linguistics, ACL 2017, 1766-1776. Association for Computational Linguis- tics (ACL).
- Ji, G.; He, S.; Xu, L.; Liu, K.; and Zhao, J. 2015. Knowl- edge graph embedding via dynamic mapping matrix. In 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), 687-696.
- Jiang, T.; Liu, T.; Ge, T.; Sha, L.; Chang, B.; Li, S.; and Sui, Z. 2016. Towards time-aware knowledge graph com- pletion. In Proceedings of COLING 2016, the 26th Interna- tional Conference on Computational Linguistics: Technical Papers, 1715-1724.
- Jin, W.; Jiang, H.; Qu, M.; Chen, T.; Zhang, C.; Szekely, P.; and Ren, X. 2019. Recurrent Event Network: Global Structure Inference over Temporal Knowledge Graph. arXiv preprint arxiv:1904.05530v3 . · arXiv
- Kipf, T. N.; and Welling, M. 2017. Semi-Supervised Clas- sification with Graph Convolutional Networks. In Interna- tional Conference on Learning Representations (ICLR).
- Koren, Y.; Bell, R.; and Volinsky, C. 2009. Matrix factoriza- tion techniques for recommender systems. Computer 42(8): 30-37.
- Lacroix, T.; Obozinski, G.; and Usunier, N. 2019. Tensor Decompositions for Temporal Knowledge Base Completion. In International Conference on Learning Representations.
- Liu, Z.; Xiong, C.; Sun, M.; and Liu, Z. 2018. Entity- Duet Neural Ranking: Understanding the Role of Knowl- edge Graph Semantics in Neural Information Retrieval. In Proceedings of the 56th Annual Meeting of the Associa- tion for Computational Linguistics (Volume 1: Long Papers), 2395-2405.
- Ma, Y.; Tresp, V.; and Daxberger, E. A. 2019. Embedding models for episodic knowledge graphs. Journal of Web Se- mantics 59: 100490.
- Schlichtkrull, M.; Kipf, T. N.; Bloem, P.; Van Den Berg, R.; Titov, I.; and Welling, M. 2018. Modeling relational data with graph convolutional networks. In European Semantic Web Conference, 593-607.
- Seo, Y.; Defferrard, M.; Vandergheynst, P.; and Bresson, X. 2018. Structured sequence modeling with graph convolu- tional recurrent networks. In International Conference on Neural Information Processing, 362-373. Springer.
- Trivedi, R.; Dai, H.; Wang, Y.; and Song, L. 2017. Know- evolve: deep temporal reasoning for dynamic knowledge graphs. In Proceedings of the 34th International Conference on Machine Learning-Volume 70, 3462-3471.
- Trivedi, R.; Farajtabar, M.; Biswal, P.; and Zha, H. 2018. Dyrep: Learning representations over dynamic graphs. In International Conference on Learning Representations.
- Vinyals, O.; Fortunato, M.; and Jaitly, N. 2015. Pointer net- works. In Advances in neural information processing sys- tems, 2692-2700.
- Wang, Q.; Mao, Z.; Wang, B.; and Guo, L. 2017. Knowl- edge graph embedding: A survey of approaches and appli- cations. IEEE Transactions on Knowledge and Data Engi- neering 29(12): 2724-2743.
- Wang, Z.; and Li, X. 2019. Hybrid-TE: Hybrid Translation- Based Temporal Knowledge Graph Embedding. In 2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI), 1446-1451. IEEE.
- Yang, B.; Yih, W.-t.; He, X.; Gao, J.; and Deng, L. 2015. Embedding entities and relations for learning and inference in knowledge bases. In ICLR.
- Zhang, H.; Chen, M.; Wang, H.; Song, Y.; and Roth, D. 2020. Analogous Process Structure Induction for Sub-event Sequence Prediction. In Proceedings of the 2020 Confer- ence on Empirical Methods in Natural Language Process- ing. ACL.
- Zhou, L.-k.; Yang, Y.; Ren, X.; Wu, F.; and Zhuang, Y. 2018a. Dynamic Network Embedding by Modeling Triadic Closure Process. In AAAI, 571-578.
- Zhou, Q.; Yang, N.; Wei, F.; and Zhou, M. 2018b. Sequential copying networks. In Thirty-Second AAAI Conference on Artificial Intelligence.
- Zhu, C.; Chen, M.; Fan, C.; Cheng, G.; and Zhang, Y. 2021. Learning from History: Modeling Temporal Knowl- edge Graphs with Sequential Copy-Generation Networks. arXiv preprint .
Cited by
Sorted by citations
Temporal Knowledge Graph Completion: A Survey
Cai, B., Xiang, Y., Gao, L., Zhang, H., Li, Y., & Li, J. (2023) · Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2023/734 · Cited by 133
A Survey on Temporal Knowledge Graph: Representation Learning and Applications
Cai, L., Mao, X., Zhou, Y., Long, Z., Wu, C., & Lan, M. (2024) · arXiv · doi:10.48550/arxiv.2403.04782 · Cited by 68
Metadata
- Authors
- Zhu, C., Chen, M., Fan, C., Cheng, G., & Zhang, Y.
- Venue
- Proceedings of the AAAI Conference on Artificial Intelligence
- Published
- 2021-05-18
- Volume
- 35
- Issue
- 5
- Pages
- 4732-4740
- ISSN
- 2374-3468
- 2159-5399
- Cited by
- 267
- References
- 7
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
