More Web Proxy on the site http://driver.im/

research-article

Tensor decompositions for temporal knowledge graph completion with time perspective▪

Authors:

Bowei XingAuthors Info & Claims

Volume 237, Issue PA

https://doi.org/10.1016/j.eswa.2023.121267

Published: 27 February 2024 Publication History

Abstract

Facts in the real world are often tied to time, such as the spread of diseases, and the state of military affairs. Therefore, knowledge graphs combined with temporal factors have gained growing attention. In the temporal knowledge graph, most researchers focus on the original facts and pay attention to their changes over time. The temporal factors are only used as auxiliary information for representation learning. In this paper, we try to observe from the perspective of time and find some interesting properties of temporal knowledge graph: (1) Simultaneousness. Various facts occur at the same time; (2) Aggregation. The facts may aggregately occur for a certain individual, organization, or location; (3) Associativity. Some specific relations tend to occur at specific times, such as celebrations at festivals. Based on the above three properties, we add a simple time-aware module to the existing tensor decomposition-based temporal knowledge graph model TComplEx (Lacroix et al., 2020), which obtains impressive improvements and achieves state-of-the-art results on four standard temporal knowledge graph completion benchmarks. Specifically, in terms of mean reciprocal rank (MRR), we advance the state-of-the-art by ＋24.0% on ICEWS14, ＋13.2% on ICEWS05-15, ＋31.9% on YAGO15k, and 4.7% on GDELT.

Highlights

•

Observe the temporal knowledge graph from time perspective.

•

Three properties of time perspective: simultaneousness, aggregation, associativity.

•

Independent temporal embedding for TComplEx for simultaneousness.

•

Combinations of head or tail entities with relations and timestamps for aggregation.

•

Combinations of relations and timestamps for associativity.

References

[1]

Bordes, A., Usunier, N., Garcia-Duran, A., Weston, J., & Yakhnenko, O. (2013). Translating embeddings for modeling multi-relational data. In Proc. of annual conference on neural information processing systems.

[2]

Chen, K., Wang, Y., Li, Y., & Li, A. (2022). RotateQVS: Representing Temporal Information as Rotations in Quaternion Vector Space for Temporal Knowledge Graph Completion. In Proc. of annual meeting of the association for computational linguistics (pp. 5843–5857). https://doi.org/10.18653/v1/2022.acl-long.402.

[3]

Dasgupta, S. S., Ray, S. N., & Talukdar, P. (2018). Hyte: Hyperplane-based temporally aware knowledge graph embedding. In Proc. of conference on empirical methods in natural language processing (pp. 2001–2011). https://doi.org/10.18653/v1/D18-1225.

[4]

Dettmers, T., Minervini, P., Stenetorp, P., & Riedel, S. (2018). Convolutional 2d knowledge graph embeddings. 32, In Proc. of AAAI conference on artificial intelligence (pp. 1811–1818). https://doi.org/10.1609/aaai.v32i1.11573.

[5]

Duchi J., Hazan E., Singer Y., Adaptive subgradient methods for online learning and stochastic optimization., Journal of Machine Learning Research 12 (7) (2011) 2121–2159.

[6]

Garcia-Duran, A., Dumančić, S., & Niepert, M. (2018). Learning Sequence Encoders for Temporal Knowledge Graph Completion. In Proc. of conference on empirical methods in natural language processing (pp. 4816–4821). https://doi.org/10.18653/v1/D18-1516.

[7]

Goel, R., Kazemi, S. M., Brubaker, M., & Poupart, P. (2020). Diachronic embedding for temporal knowledge graph completion. vol. 34, In Proc. of AAAI conference on artificial intelligence (pp. 3988–3995). https://doi.org/10.1609/aaai.v34i04.5815.

[8]

He Z., Hui B., Zhang S., Xiao C., Zhong T., Zhou F., Exploring indirect entity relations for knowledge graph enhanced recommender system, Expert Systems with Applications (2022),.

Digital Library

[9]

Hoffart J., Suchanek F.M., Berberich K., Weikum G., YAGO2: A spatially and temporally enhanced knowledge base from wikipedia, Artificial Intelligence 194 (2013) 28–61,.

Digital Library

[10]

Jain, P., Rathi, S., Chakrabarti, S., et al. (2020). Temporal Knowledge Base Completion: New Algorithms and Evaluation Protocols. In Proc. of conference on empirical methods in natural language processing (pp. 3733–3747). https://doi.org/10.18653/v1/2020.emnlp-main.305.

[11]

Kazemi S.M., Poole D., Simple embedding for link prediction in knowledge graphs, Proceedings of Annual Conference on Neural Information Processing Systems 31 (2018).

[12]

Lacroix, T., Obozinski, G., & Usunier, N. (2020). Tensor Decompositions for Temporal Knowledge Base Completion. In Proc. of international conference on learning representations.

[13]

Lacroix, T., Usunier, N., & Obozinski, G. (2018). Canonical tensor decomposition for knowledge base completion. In Proc. of international conference on machine learning (pp. 2863–2872).

[14]

Lai Y., Chen C., Zheng Z., Zhang Y., Block term decomposition with distinct time granularities for temporal knowledge graph completion, Expert Systems with Applications 201 (2022),.

Digital Library

[15]

Lautenschlager J., Shellman S., Ward M., Icews event aggregations, Harvard Dataverse 3 (595) (2015) 28.

[16]

Le T., Le N., Le B., Knowledge graph embedding by relational rotation and complex convolution for link prediction, Expert Systems with Applications (2022),.

Digital Library

[17]

Leblay, J., & Chekol, M. W. (2018). Deriving validity time in knowledge graph. In Companion Proc. of the the web conference (pp. 1771–1776). https://doi.org/10.1145/3184558.3191639.

[18]

Leetaru, K., & Schrodt, P. A. (2013). Gdelt: Global data on events, location, and tone, 1979–2012. vol. 2, In ISA annual convention (pp. 1–49).

[19]

Liu, K., Zhao, F., Xu, G., Wang, X., & Jin, H. (2023). RETIA: relation-entity twin-interact aggregation for temporal knowledge graph extrapolation. In Proc. of IEEE international conference on data engineering.

[20]

Nickel, M., Tresp, V., & Kriegel, H.-P. (2011). A three-way model for collective learning on multi-relational data. vol. 11, In Proc. of international conference on machine learning (pp. 809–816).

[21]

Paszke A., Gross S., Massa F., Lerer A., Bradbury J., Chanan G., et al., Pytorch: An imperative style, high-performance deep learning library, Proc. of Annual Conference on Neural Information Processing Systems 32 (2019).

[22]

Sadeghian, A., Armandpour, M., Colas, A., & Wang, D. Z. (2021). ChronoR: rotation based temporal knowledge graph embedding. vol. 35, In Proc. of AAAI conference on artificial intelligence (pp. 6471–6479). https://doi.org/10.1609/aaai.v35i7.16802.

[23]

Saxena, A., Tripathi, A., & Talukdar, P. (2020). Improving multi-hop question answering over knowledge graphs using knowledge base embeddings. In Proc. of annual meeting of the association for computational linguistics (pp. 4498–4507). https://doi.org/10.18653/v1/2020.acl-main.412.

[24]

Sun, Z., Deng, Z.-H., Nie, J.-Y., & Tang, J. (2019). RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space. In Proc. of international conference on learning representations.

[25]

Trivedi, R., Dai, H., Wang, Y., & Song, L. (2017). Know-evolve: Deep temporal reasoning for dynamic knowledge graphs. In Proc. of international conference on machine learning (pp. 3462–3471).

[26]

Trouillon, T., Welbl, J., Riedel, S., Gaussier, É., & Bouchard, G. (2016). Complex embeddings for simple link prediction. vol. 48, In Proc. of international conference on machine learning (pp. 2071–2080).

[27]

Wang, Z., Du, H., Yao, Q., & Li, X. (2022). Search to Pass Messages for Temporal Knowledge Graph Completion. In Findings of empirical methods in natural language processing (pp. 6160–6172).

[28]

Wang, Z., Zhang, J., Feng, J., & Chen, Z. (2014). Knowledge graph embedding by translating on hyperplanes. vol. 28, In Proc. of AAAI conference on artificial intelligence (pp. 1112–1119). https://doi.org/10.1609/aaai.v28i1.8870.

[29]

Wu, J., Cao, M., Cheung, J. C. K., & Hamilton, W. L. (2020). TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion. In Proc. of conference on empirical methods in natural language processing (pp. 5730–5746). https://doi.org/10.18653/v1/2020.emnlp-main.462.

[30]

Xu, C., Chen, Y.-Y., Nayyeri, M., & Lehmann, J. (2021). Temporal knowledge graph completion using a linear temporal regularizer and multivector embeddings. In Proc. of North American chapter of the association for computational linguistics (pp. 2569–2578). https://doi.org/10.18653/v1/2021.naacl-main.202.

[31]

Xu C., Nayyeri M., Alkhoury F., Yazdi H.S., Lehmann J., Temporal knowledge graph embedding model based on additive time series decomposition, 2019, arXiv preprint arXiv:1911.07893.

[32]

Xu, C., Nayyeri, M., Alkhoury, F., Yazdi, H. S., & Lehmann, J. (2020). TeRo: A Time-aware Knowledge Graph Embedding via Temporal Rotation. In Proc. of international conference on computational linguistics (pp. 1583–1593). https://doi.org/10.18653/v1/2020.coling-main.139.

[33]

Xu C., Nayyeri M., Chen Y.-Y., Lehmann J., Geometric algebra based embeddings for static and temporal knowledge graph completion, IEEE Transactions on Knowledge and Data Engineering 35 (5) (2023) 4838–4851,.

Digital Library

[34]

Xu, Y., Ou, J., Xu, H., & Fu, L. (2023b). Temporal knowledge graph reasoning with historical contrastive learning. vol. 37, In Proc. of AAAI conference on artificial intelligence (pp. 4765–4773). https://doi.org/10.1609/aaai.v37i4.25601, (4).

[35]

Yang, J., Shi, Y., Tong, X., Wang, R., Chen, T., & Ying, X. (2021). Improving Knowledge Graph Embedding Using Affine Transformations of Entities Corresponding to Each Relation. In Findings of the association for computational linguistics: EMNLP 2021 (pp. 508–517). https://doi.org/10.18653/v1/2021.findings-emnlp.46.

[36]

Yang, B., Yih, W.-t., He, X., Gao, J., & Deng, L. (2015). Embedding entities and relations for learning and inference in knowledge bases. In Proc. of international conference on learning representations.

[37]

Yang, J., Ying, X., Shi, Y., Tong, X., Wang, R., Chen, T., et al. (2022). Learning Hierarchy-Aware Quaternion Knowledge Graph Embeddings with Representing Relations as 3D Rotations. In Proc. of international conference on computational linguistics (pp. 2011–2023).

[38]

Yao S., Pi D., Chen J., Xu Y., GCKG: Novel gated convolutional embedding model for knowledge graphs, Expert Systems with Applications 208 (2022),.

Digital Library

[39]

Yu M., Guo J., Yu J., Xu T., Zhao M., Liu H., et al., TBDRI: block decomposition based on relational interaction for temporal knowledge graph completion, Applied Intelligence 53 (5) (2023) 5072–5084,.

Digital Library

[40]

Zhang, J., Liang, S., Deng, Z., & Shao, J. (2021). Spatial-temporal attention network for temporal knowledge graph completion. In Proc. of international conference of database systems for advanced applications (pp. 207–223). https://doi.org/10.1007/978-3-030-73194-6_15.

[41]

Zhang, S., Tay, Y., Yao, L., & Liu, Q. (2019). Quaternion Knowledge Graph Embeddings. In H. Wallach, H. Larochelle, A. Beygelzimer, F. d’ Alché-Buc, E. Fox, & R. Garnett (Eds.), 32, Proc. of annual conference on neural information processing systems (pp. 2735–2745).

[42]

Zhang, M., Xia, Y., Liu, Q., Wu, S., & Wang, L. (2023). Learning Long- and Short-term Representations for Temporal Knowledge Graph Reasoning. In Proc. of international conference on world wide web (pp. 2412–2422). https://doi.org/10.1145/3543507.3583242.

[43]

Zhang, F., Zhang, Z., Ao, X., Zhuang, F., Xu, Y., & He, Q. (2022). Along the Time: Timeline-traced Embedding for Temporal Knowledge Graph Completion. In Proc. of ACM international conference on information and knowledge management (pp. 2529–2538). https://doi.org/10.1145/3511808.3557233.

[44]

Zitnik M., Agrawal M., Leskovec J., Modeling polypharmacy side effects with graph convolutional networks, Bioinformatics 34 (2018) i457–i466,.

Cited By

Zhang JYing RShao J(2024)Online Detection of Anomalies in Temporal Knowledge Graphs with InterpretabilityProceedings of the ACM on Management of Data10.1145/36988232:6(1-26)Online publication date: 20-Dec-2024
https://dl.acm.org/doi/10.1145/3698823
Wang WZhang XZhang JCai WZhao HZhang X(2024)MHRE: Multivariate link prediction method for medical hyper-relational factsApplied Intelligence10.1007/s10489-023-05248-254:2(1311-1334)Online publication date: 4-Jan-2024
https://dl.acm.org/doi/10.1007/s10489-023-05248-2

Index Terms

Tensor decompositions for temporal knowledge graph completion with time perspective▪

Index terms have been assigned to the content through auto-classification.

Recommendations

Enhance Temporal Knowledge Graph Completion via Time-Aware Attention Graph Convolutional Network
Machine Learning and Knowledge Discovery in Databases
Abstract
Previous works on knowledge graph representation learning focus on static knowledge graph and get fully developed. However, task on temporal knowledge graph is far from consummation because of its late start. Recent researches have shifted to the ...
A Novel Semantic-Enhanced Time-Aware Model for Temporal Knowledge Graph Completion
Natural Language Processing and Chinese Computing
Abstract
Researchers have investigated various graph embedding methods to complete Knowledge Graphs (KGs), most of which merely focus on Static KGs (SKGs) without emphasizing the time dependence of triple-formed facts. However, in reality, KGs are dynamic ...
Multi-hop temporal knowledge graph reasoning with temporal path rules guidance
Abstract
Temporal Knowledge graph (TKG) is a key component of artificial intelligence. In recent years, many large-scale temporal knowledge graphs have been produced and put into practical applications. At present, researchers have proposed many methods ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Expert Systems with Applications: An International Journal

Expert Systems with Applications: An International Journal Volume 237, Issue PA

Mar 2024

1590 pages

Issue’s Table of Contents

Elsevier Ltd.

Publisher

Pergamon Press, Inc.

United States

Publication History

Published: 27 February 2024

Author Tags

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 19 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Zhang JYing RShao J(2024)Online Detection of Anomalies in Temporal Knowledge Graphs with InterpretabilityProceedings of the ACM on Management of Data10.1145/36988232:6(1-26)Online publication date: 20-Dec-2024
https://dl.acm.org/doi/10.1145/3698823
Wang WZhang XZhang JCai WZhao HZhang X(2024)MHRE: Multivariate link prediction method for medical hyper-relational factsApplied Intelligence10.1007/s10489-023-05248-254:2(1311-1334)Online publication date: 4-Jan-2024
https://dl.acm.org/doi/10.1007/s10489-023-05248-2

View Options

View options

Media

Figures

Other

Tables

View Issue’s Table of Contents