Sequence Encoder-based Spatiotemporal Knowledge Graph Completion

Authors

  • Wei Jia 1)State Key Laboratory of Air Traffic Management System and Technology, China 2)Nanjing University of Aeronautics and Astronautics, China
  • Xuan Wang State Key Laboratory of Air Traffic Management System and Technology, China
  • Jing Shan Nanjing University of Aeronautics and Astronautics, China
  • Li Yan Nanjing University of Aeronautics and Astronautics, China
  • Weinan Niu Nanjing University of Aeronautics and Astronautics, China
  • Zongmin Ma Nanjing University of Aeronautics and Astronautics, China

DOI:

https://doi.org/10.13052/jwe1540-9589.2166

Keywords:

Knowledge graph completion, recursive neural network, spatiotemporal information

Abstract

Knowledge graph (KG) completion aims to infer new facts from incomplete knowledge graphs. Most existing solutions focus on learning from time-aware fact triples and ignore the spatial information. In reality, knowledge graphs can evolve with time as well as the changing locations, such as the flight domain. Therefore, integrating spatiotemporal information into knowledge graph representation is important for the knowledge graph completion. To address this problem, this paper proposes two Spatio Temporal-aware knowledge graph completion models based on the Sequence Encoder, namely STSE and S-TSE, which incorporate the spatial and temporal information into relations. Specifically, the model consists of two steps: spatiotemporal-aware relation encoding and final scoring function evaluation. The first stage composes the spatiotemporal information into different tokens. Then two methods are proposed to obtain the embedding of spatiotemporal-aware relation by utilizing the Recursive Neural Network. The second stage proposes different scoring functions for two models. Empirically evaluation of the proposed models is conducted on spatiotemporal-aware KG completion task on two public datasets. Experimental results demonstrate the effectiveness of the proposal for spatiotemporal knowledge graph completion.

Downloads

Download data is not yet available.

Author Biographies

Wei Jia, 1)State Key Laboratory of Air Traffic Management System and Technology, China 2)Nanjing University of Aeronautics and Astronautics, China

Wei Jia received the M.S. degree in computer science from Shandong University of Science and Technology, China in 2020. She is currently working toward the Ph.D. degree in the School of Computer Science and Technology at Nanjing University of Aeronautics and Astronautics, China. Her fields of research are social network, knowledge graph, service computing and intelligent information systems.

Xuan Wang, State Key Laboratory of Air Traffic Management System and Technology, China

Xuan Wang received the B.E. degree from University of Hertfordshire, Hartfield, UK in 2011. Later on, he received his M.S. degree from Southampton University, Southampton, UK in 2012. He received his PhD degree in Electronics and Electrical Engineering from Southampton University in 2017. He is currently a senior engineer of State Key Laboratory of Air Traffic Management System and Technology, Nanjing, China. His research interests include information extraction and natural language understanding.

Jing Shan, Nanjing University of Aeronautics and Astronautics, China

Jing Shan received the bachelor degree in information security in 2010 and the master degree in computer science in 2013 from Nanjing University of Aeronautics and Astronautics, China. She is a research associate at Nanjing University of Aeronautics and Astronautics, China, engaging in intelligent system for task allocation, optimization algorithm and application of intelligent transportation system.

Li Yan, Nanjing University of Aeronautics and Astronautics, China

Li Yan received her PhD degree from Northeastern University, China. She is currently a full professor at Nanjing University of Aeronautics and Astronautics, China. Her research interests mainly include big data processing, knowledge graph, spatiotemporal data management, and fuzzy data modeling. She has published more than fifty papers on these topics. She is the author of three monographs published by Springer.

Weinan Niu, Nanjing University of Aeronautics and Astronautics, China

Weinan Niu received the M.S. degree in computer science from Shandong University of Science and Technology, China in 2020. He is currently working toward the Ph.D. degree in the School of Computer Science and Technology at Nanjing University of Aeronautics and Astronautics, China. His fields of research are social network, influence maximization, service computing and intelligent information systems.

Zongmin Ma, Nanjing University of Aeronautics and Astronautics, China

Zongmin Ma received his PhD degree from City University of Hong Kong, China. He is currently a full professor at Nanjing University of Aeronautics and Astronautics, China. His research interests include big data and knowledge engineering, the Semantic Web, temporal/spatial information modeling and processing, deep learning, and knowledge representation and reasoning with a special focus on information uncertainty. He has published more than two hundred papers in international journals and conferences on these topics. In addition, he (co-)authors six monographs with Springer. He is a Fellow of the IFSA and a senior member of the IEEE.

References

Auer S., Bizer C., Kobilarov G., Lehmann J., Cyganiak R., and Ives Z., ‘Dbpedia: a nucleus for a web of open data’, Proc. In the 6th International Semantic Web Conference, pp. 722–735, 2007.

Mahdisoltani F., Biega J., and Suchanek F., ‘Yago3: A knowledge base from multilingual wikipedias’, Proc. In the Seventh Biennial Conference on Innovative Data Systems Research, 2015.

Bollacker K., Evans C., Paritosh P., Sturge T., and Taylor J., ‘Freebase: a collaboratively created graph database for structuring human knowledge’, Proc. In the ACM SIGMOD International Conference on Management of Data, pp. 1247–1250, 2008.

Liu Z., Xiong C., Sun M., and Liu Z., ‘EntityDuet Neural Ranking: Understanding the Role of Knowledge Graph Semantics in Neural Information Retrieval’, Proc. In the 56th Annual Meeting of the Association for Computational Linguistics, pp. 2395-2405, 2018.

Li D. Y., Sheng J., Liu Y. X., et al., ‘Military weapon QA system based on knowledge graph’, Command Information System and Technology, 11(5): 58–65, 2020.

Fan H., Zhong Y., Zeng G., et al., ‘Improving recommender system via knowledge graph based exploring user preference’, Applied Intelligence, https://doi.org/10.1007/s10489-021-02872-8, 2022.

Zhu L., N Li, Bai L., et al., ‘stRDFS: Spatiotemporal Knowledge Graph Modeling’, IEEE Access, 8: 129043-129057, 2020.

Bai L., J Wang, Di X. et al., ‘Fixing the Inconsistencies in Fuzzy Spatiotemporal RDF Graph’, Information Sciences, 578: 166–180, 2021.

Antoine Bordes, Nicolas Usunier, Alberto GarciaDuran, Jason Weston, and Oksana Yakhnenko, ‘Translating Embeddings for Modeling Multi-relational Data’, Proc. In the 27th Annual Conference on Neural Information Processing Systems, pp. 2787–2795, 2013.

Sun Z., Deng Z. H., Nie J. Y. et al., ‘RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space’, Proc. In the 7th International Conference on Learning Representations, 2019.

S. Yang, J. Tian, H. Zhang, J. Yan, H. He, and Y. Jin, ‘TransMS: Knowledge graph embedding for complex relations by multidirectional semantics’, Proc. In the 28th International Joint Conference on Artificial Intelligence, pp. 1935–1942, 2019.

He S., K. Liu, G. Ji, and J. Zhao, ‘Learning to represent knowledge graphs with Gaussian embedding’, Proc. In the 24th ACM Int. Conference Information and Knowledge Management, pp. 623–632, 2015.

Y. Lin, Z. Liu, M. Sun, Y. Liu, and X. Zhu, ‘Learning entity and relation embeddings for knowledge graph completion’, Proc. In the 29th AAAI Conference on Artificial Intelligence, pp. 2181–2187, 2015.

Z. Wang, J. Zhang, J. Feng, and Z. Chen, ‘Knowledge graph embedding by translating on hyperplanes’, Proc. In the 28th AAAI Conference on Artificial Intelligence, pp. 1112–1119, 2014.

M. Nickel, L. Rosasco, and T. Poggio, ‘Holographic embeddings of knowledge graphs’, Proc. In the 30th AAAI Conference on Artificial Intelligence, pp. 1955–1961, 2016.

B. Yang, W.-T. Yih, X. He, J. Gao, and L. Deng, ‘Embedding entities and relations for learning and inference in knowledge bases’, Proc. In the 3rd International Conference on Learning Representations, pp. 1–13, 2015.

K. Hayashi and M. Shimbo, ‘On the equivalence of holographic and complex embeddings for link prediction’, Proc. In the 55th Annual Meeting of the Association for Computational Linguistics, pp. 554–559, 2017.

M. Schlichtkrull, T. N. Kipf, P. Bloem, R. Van Den Berg, I. Titov, and M. Welling, ‘Modeling relational data with graph convolutional networks’, Proc. In the 15th International Conference on Extended Semantic Web, pp. 593–607, 2018.

Chengjin Xu, Mojtaba Nayyeri, Fouad Alkhoury, Jens Lehmann, and Hamed Shariat Yazdi, ‘Temporal knowledge graph embedding model based on additive time series decomposition’, Proc. In the International Semantic Web Conference, 2020.

Sadeghian A., Armandpour M., Colas A. et al., ‘ChronoR: Rotation Based Temporal Knowledge Graph Embedding’, Proc. In the 35th AAAI Conference on Artificial Intelligence, pp. 6471–6479, 2021.

Xu C., Nayyeri M., Alkhoury F., et al., ‘TeRo: A Time-aware Knowledge Graph Embedding via Temporal Rotation’, Proc. In the 28th International Conference on Computational Linguistics, pp. 1583–1593, 2020.

Xu Y., Haihong E., Song M., ‘RTFE: A Recursive Temporal Fact Embedding Framework for Temporal Knowledge Graph Completion’, Proc. In the 2021 Conference of the North American Chapter of the Association for Computational Linguistics, pp. 5671–5681, 2021.

García-Durán, A., Dumani S., Niepert M., ‘Learning Sequence Encoders for Temporal Knowledge Graph Completion’, Proc. In the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 4816–4821, 2018.

Liu Y., Hua W., Xin K., et al., ‘Context-Aware Temporal Knowledge Graph Embedding’, Proc. In the 20th International Conference on Web Information Systems Engineering, pp. 583–598, 2019.

Dasgupta S. S., Ray S. N., Talukdar P., ‘HyTE: Hyperplane-based Temporally aware Knowledge Graph Embedding’, Proc. In the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 2001–2011, 2018.

Xu Y., Sun S., Miao Y., et al., ‘Time-aware Graph Embedding: A temporal smoothness and task-oriented approach’, ACM Transactions on Knowledge Discovery from Data, 16(3): 1–23, 2022.

Zhu C., Chen M., Fan C., et al., ‘Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks’, Proc. In the Thirty-Fifth AAAI Conference on Artificial Intelligence, pp. 4732–4740, 2021.

Lu X. J., Hu T. T., Yin F., ‘A Novel Spatiotemporal Fuzzy Method for Modeling of Complex Distributed Parameter Processes’, IEEE Transactions on Industrial Electronics, 66(10): 7882–7892, 2019.

Han Z., Chen P., Ma Y. P., Tresp V., ‘Explainable subgraph reasoning for forecasting on temporal knowledge graphs’, Proc. In the International Conference on Learning Representations, 2020.

Jung J. H., Jung J. H., Kang U., ‘T-GAP: Learning to walk across time for interpretable temporal knowledge graph completion’, Proc. In the ACM SIGKDD conference on Knowledge Discovery and Data Mining, pp. 786–795, 2021.

Li Z., Jin X., Guan S., et al., ‘Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphs’, Proc. In the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, 2021.

Zhang J., Sheng Y., Wang Z., Shao J., ‘TKGFrame: A Two-Phase Framework for Temporal-Aware Knowledge Graph Completion’, Proc. In the 4th Asia Pacific Web and Web-Age Information Management Joint Conference on Web and Big Data, 2020.

Lv X., Lin Y. K., Cao Y. X., et al. ‘Do Pre-trained Models Benefit Knowledge Graph Completion? A Reliable Evaluation and a Reasonable Approach’, Proc. In the Association for Computational Linguistics, pp. 3570–3581, 2022.

Jin W., Zhang C. L, Szekely P., Ren X., ‘Recurrent Event Network for Reasoning over Temporal Knowledge Graphs’, Proc. In the International Conference on Learning Representations, 2019.

Liu H., Chen C. R., Xu Q. C., et al., ‘Question and answer robot’s technology for air traffic control’, Command Information System and Technology, 12(5): 32–37, 2021.

Published

2022-11-09

Issue

Section

Articles