{"id":1644,"date":"2026-03-29T19:15:54","date_gmt":"2026-03-29T11:15:54","guid":{"rendered":"https:\/\/iweb20wp-b205b.url.tku.edu.tw\/jase\/?post_type=tkuisotope&p=1644"},"modified":"2026-05-23T19:18:10","modified_gmt":"2026-05-23T11:18:10","slug":"knowledge-graph-representation-learning-model-based-on-capsule-network-and-information-fusion","status":"publish","type":"tkuisotope","link":"\/jase\/?tkuisotope=knowledge-graph-representation-learning-model-based-on-capsule-network-and-information-fusion","title":{"rendered":"Knowledge Graph Representation Learning Model Based on Capsule Network and Information Fusion"},"content":{"rendered":"\n
\n
\n

<\/i> 2026<\/a><\/p>\n<\/div>\n\n\n\n

\n

<\/i> Volume 29, Issue 1<\/a><\/p>\n<\/div>\n\n\n\n

\n
\n
\n
\n

Chu Zhao1,3<\/sup>, Gilja So2<\/sup><\/i><\/a>, and Rui Chen3<\/sup><\/p>\n\n\n\n

1<\/sup>Department of Computer and Information Engineering, Graduate School Youngsan University, South Korea<\/p>\n\n\n\n

2<\/sup>Department of Cyber Security Youngsan University, South Korea<\/p>\n\n\n\n

3<\/sup>Software College, Shenyang Normal University, Shenyang, 110034, China<\/p>\n<\/div>\n\n\n\n

\n

Received:\u00a0August 30, 2024
Accepted:\u00a0March 31, 2025
Publication Date:\u00a0March 29, 2026<\/p>\n<\/div>\n<\/div>\n\n\n\n

\"\u4e0a\u50b3\u5716\u7247\"\n\n\n

Subgraph sampling<\/p>\n<\/div>\n<\/div>\n\n\n\n

<\/i> Copyright <\/strong>The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0)<\/a>, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.<\/p>\n\n\n\n

Download Citation:\u00a0 BibTeX <\/a>| https:\/\/doi.org\/10.6180\/jase.202601_29(1).0009<\/a>\u00a0\u00a0<\/p>\n\n\n\n

Download PDF<\/a><\/p>\n\n\n\n

<\/div>\n\n\n\n

In recent years, knowledge representation learning has played a key role in intelligent recommendation, intelligent question-answering, and intelligent retrieval, and has been widely concerned. Knowledge representation learning aims to vectorize semantic information and deduce knowledge through mathematical formulas with the help of low dimensional embedding of entity and relation. Although knowledge representation learning based on knowledge graph can obtain entity structure and relational embedding, it lacks semantic information utilization of entity description text. In addition, with the increase of the scale of the knowledge graph, the categories and quantities of entities and relationships, as well as the content and sources of entity descriptions, the correspondence between the textual descriptions of entities and the triplet structure information becomes more difficult to obtain. Therefore, we propose a novel knowledge graph representation learning model based on capsule network and information fusion in this paper. Based on anchor node and neighbor node and the relational sampling strategy, each node on the knowledge graph is represented by the predicted operator graph. The capsule network is used to gather the image features for each node to obtain the node representation vector, which is finally input to the decoder to calculate the score. In particular, we construct a loss function for the multi-layer attention mechanism of entity structure and semantic fusion. Experimental results show that the proposed method can effectively deduce the hidden link relationship between entities containing complex entity descriptions, and has more accurate classification accuracy than other methods in triplet classification tasks.<\/p>\n\n\n\n

Keywords:\u00a0Knowledge representation learning; Capsule network; Information fusion; Multi-layer attention mechanism<\/em><\/p>\n\n\n\n

<\/div>\n\n\n\n
\n
    \n
  1. [1] Z. Chen, Y. Wang, B. Zhao, J. Cheng, X. Zhao, and Z. Duan, (2020) \u201cKnowledge graph completion: A review\u201d Ieee Access 8: 192435\u2013192456. DOI: 10.1109\/ACCESS.2020.3030076.<\/li>\n
  2. [2] S. Auer, C. Bizer, G. Kobilarov, J. Lehmann, R. Cyganiak, and Z. Ives. \u201cDbpedia: A nucleus for a web of open data\u201d. In: international semantic web conference. Springer. 2007, 722\u2013735. DOI: 10.1007\/978-3-540-76298-0_52.<\/li>\n
  3. [3] A. Madkour, W. G. Aref, and S. Basalamah. \u201cKnowledge cubes\u2014A proposal for scalable and semantically-guided management of Big Data\u201d. In: 2013 IEEE International Conference on Big Data. IEEE. 2013, 1\u20137. DOI: 10.1109\/BigData.2013.6691800.<\/li>\n
  4. [4] F. M. Suchanek, G. Kasneci, and G. Weikum, (2008) \u201cYago: A large ontology from wikipedia and wordnet\u201d Journal of Web Semantics 6(3): 203\u2013217. DOI: 10.1016\/j.websem.2008.06.001.<\/li>\n
  5. [5] R. Xie, Z. Liu, J. Jia, H. Luan, and M. Sun. \u201cRepresentation learning of knowledge graphs with entity descriptions\u201d. In: Proceedings of the AAAI conference on artificial intelligence. 30. 1. 2016. DOI: 10.1609\/aaai.v30i1.10329.<\/li>\n
  6. [6] H. Zhu, D. Xu, Y. Huang, Z. Jin, W. Ding, J. Tong, and G. Chong, (2024) \u201cGraph structure enhanced pre-training language model for knowledge graph completion\u201d IEEE Transactions on Emerging Topics in Computational Intelligence: DOI: 10.1109\/TETCI.2024.3372442.<\/li>\n
  7. [7] S. Feng, C. Zhou, Q. Liu, X. Ji, and M. Huang, (2024) \u201cTemporal Knowledge Graph Reasoning Based on Entity Relationship Similarity Perception\u201d Electronics 13(12): 2417. DOI: 10.3390\/electronics13122417.<\/li>\n
  8. [8] H. Yang and J. Liu. \u201cKnowledge graph representation learning as groupoid: unifying TransE, RotateE, QuatE, ComplEx\u201d. In: Proceedings of the 30th ACM international conference on information & knowledge management. 2021, 2311\u20132320. DOI: 10.1145\/3459637.3482442.<\/li>\n
  9. [9] C. Jin, R. Cui, and Y. Zhao. \u201cResearch on Chinese-Korean Entity Alignment Method Combining TransH and GAT\u201d. In: China Conference on Knowledge Graph and Semantic Computing. Springer. 2021, 134\u2013144. DOI: 10.1007\/978-981-16-6471-7_10.<\/li>\n
  10. [10] F. Liu, Y. Shen, T. Zhang, and H. Gao, (2020) \u201cEntity-related paths modeling for knowledge base completion\u201d Frontiers of Computer Science 14: 1\u201310. DOI: 10.1007\/s11704-019-8264-4.<\/li>\n
  11. [11] M. Zhang and Y. Chen, (2018) \u201cLink prediction based on graph neural networks\u201d Advances in neural information processing systems 31: DOI: 10.1007\/978-981-16-6054-2_10.<\/li>\n
  12. [12] H. Xiao, M. Huang, Y. Hao, and X. Zhu, (2015) \u201cTransG: A generative mixture model for knowledge graph embedding\u201d arXiv preprint arXiv:1509.05488: DOI: 10.48550\/arXiv.1509.05488.<\/li>\n
  13. [13] X. Tang, L. Chen, J. Cui, and B. Wei, (2019) \u201cKnowledge representation learning with entity descriptions, hierarchical types, and textual relations\u201d Information Processing & Management 56(3): 809\u2013822. DOI: 10.1016\/j.ipm.2019.01.005.<\/li>\n
  14. [14] B. An, B. Chen, X. Han, and L. Sun. \u201cAccurate text-enhanced knowledge graph representation learning\u201d. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). 2018, 745\u2013755. DOI: 10.18653\/v1\/N18-1068.<\/li>\n
  15. [15] Y. Zhao, H. Feng, H. Zhou, Y. Yang, X. Chen, R. Xie, F. Zhuang, and Q. Li, (2022) \u201cEIGAT: Incorporating global information in local attention for knowledge representation learning\u201d Knowledge-Based Systems 237: 107909. DOI: 10.1016\/j.knosys.2021.107909.<\/li>\n
  16. [16] Z. Li, X. Liu, X. Wang, P. Liu, and Y. Shen, (2023) \u201cTranso: a knowledge-driven representation learning method with ontology information constraints\u201d World Wide Web 26(1): 297\u2013319. DOI: 10.1007\/s11280-022-01016-3.<\/li>\n
  17. [17] Z. Li, X. Jin, W. Li, S. Guan, J. Guo, H. Shen, Y. Wang, and X. Cheng. \u201cTemporal knowledge graph reasoning based on evolutional representation learning\u201d. In: Proceedings of the 44th international ACM SIGIR conference on research and development in information retrieval. 2021, 408\u2013417. DOI: 10.1145\/3404835.3462963.<\/li>\n
  18. [18] J. Hao, M. Chen, W. Yu, Y. Sun, and W. Wang. \u201cUniversal representation learning of knowledge bases by jointly embedding instances and ontological concepts\u201d. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2019, 1709\u20131719. DOI: 10.1145\/3292500.3330838.<\/li>\n
  19. [19] H. Mousselly-Sergieh, T. Botschen, I. Gurevych, and S. Roth. \u201cA multimodal translation-based approach for knowledge graph representation learning\u201d. In: Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics. 2018, 225\u2013234. DOI: 10.18653\/v1\/S18-2027.<\/li>\n
  20. [20] N. Passalis, M. Tzelepi, and A. Tefas, (2020) \u201cProbabilistic knowledge transfer for lightweight deep representation learning\u201d IEEE Transactions on Neural Networks and Learning Systems 32(5): 2030\u20132039. DOI: 10.1109\/TNNLS.2020.2995884.<\/li>\n
  21. [21] T. Chen, L. Lin, R. Chen, Y. Wu, and X. Luo, (2018) \u201cKnowledge-embedded representation learning for fine-grained image recognition\u201d arXiv preprint arXiv:1807.00505: DOI: 10.48550\/arXiv.1807.00505.<\/li>\n
  22. [22] W. Gan, Y. Sun, and Y. Sun, (2022) \u201cKnowledge structure enhanced graph representation learning model for attentive knowledge tracing\u201d International Journal of Intelligent Systems 37(3): 2012\u20132045. DOI: 10.1002\/int.22763.<\/li>\n
  23. [23] B. Wang, T. Shen, G. Long, T. Zhou, Y. Wang, and Y. Chang. \u201cStructure-augmented text representation learning for efficient knowledge graph completion\u201d. In: Proceedings of the Web Conference 2021. 2021, 1737\u20131748. DOI: 10.1145\/3442381.3450043.<\/li>\n
  24. [24] C. Zhao, J. Jiang, Y. Guan, X. Guo, and B. He, (2018) \u201cEMR-based medical knowledge representation and inference via Markov random fields and distributed representation learning\u201d Artificial intelligence in medicine 87: 49\u201359. DOI: 10.1016\/j.artmed.2018.03.005.<\/li>\n
  25. [25] J. Zhang, S. Liang, Y. Sheng, and J. Shao, (2022) \u201cTemporal knowledge graph representation learning with local and global evolutions\u201d Knowledge-Based Systems 251: 109234. DOI: 10.1016\/j.knosys.2022.109234.<\/li>\n
  26. [26] G. Niu, Y. Zhang, B. Li, P. Cui, S. Liu, J. Li, and X. Zhang. \u201cRule-guided compositional representation learning on knowledge graphs\u201d. In: Proceedings of the AAAI conference on artificial intelligence. 34. 03. 2020, 2950\u20132958. DOI: 10.1609\/aaai.v34i03.5687.<\/li>\n
  27. [27] H. Liu, C. Li, Y. Li, and Y. J. Lee. \u201cImproved baselines with visual instruction tuning\u201d. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2024, 26296\u201326306. DOI: 10.1109\/CVPR52733.2024.02484.<\/li>\n
  28. [28] T. Shen, Y. Mao, P. He, G. Long, A. Trischler, and W. Chen, (2020) \u201cExploiting structured knowledge in text via graph-guided representation learning\u201d arXiv preprint arXiv:2004.14224: DOI: 10.48550\/arXiv.2004.14224.<\/li>\n
  29. [29] S. Seo, B. Oh, and K.-H. Lee, (2020) \u201cReliable knowledge graph path representation learning\u201d IEEE Access 8: 32816\u201332825. DOI: 10.1109\/ACCESS.2020.2973923.<\/li>\n
  30. [30] M. Fan, Q. Zhou, T. F. Zheng, and R. Grishman, (2017) \u201cDistributed representation learning for knowledge graphs with entity descriptions\u201d Pattern Recognition Letters 93: 31\u201337. DOI: 10.1016\/j.patrec.2016.09.005.<\/li>\n
  31. [31] P. Wang, S. Li, and R. Pan. \u201cIncorporating gan for negative sampling in knowledge representation learning\u201d. In: Proceedings of the AAAI conference on artificial intelligence. 32. 1. 2018. DOI: 10.1609\/aaai.v32i1.11536.<\/li>\n
  32. [32] Z. Feng, D. Tang, X. Feng, C. Zhou, J. Liao, S. Wu, B. Qin, Y. Cao, and S. Shi, (2024) \u201cPretraining without wordpieces: learning over a vocabulary of millions of words\u201d International Journal of Machine Learning and Cybernetics 15(9): 3989\u20133998. DOI: 10.1007\/s13042-024-02132-4.<\/li>\n
  33. [33] Y. Jiang and S. Yin, (2023) \u201cHeterogenous-view occluded expression data recognition based on cycle-consistent adversarial network and K-SVD dictionary learning under intelligent cooperative robot environment\u201d Computer Science and Information Systems 20(4): 1869\u20131883. DOI: 10.2298\/CSIS22122803<\/span>4J.<\/li>\n
  34. [34] Z. Zhang, L. Cao, X. Chen, W. Tang, Z. Xu, and Y. Meng, (2020) \u201cRepresentation learning of knowledge graphs with entity attributes\u201d IEEE Access 8: 7435\u20137441. DOI: 10.1109\/ACCESS.2020.2963990.<\/li>\n
  35. [35] S. Yin, H. Li, A. A. Laghari, T. R. Gadekallu, G. A. Sampedro, and A. Almadhor, (2024) \u201cAn Anomaly Detection Model Based on Deep Auto-Encoder and Capsule Graph Convolution via Sparrow Search Algorithm in 6G Internet of Everything\u201d IEEE Internet of Things Journal 11(18): 29402\u201329411. DOI: 10.1109\/JIOT.2024.3353337.<\/li>\n
  36. [36] Z. Li, Q. Zhang, F. Zhu, D. Li, C. Zheng, and Y. Zhang, (2023) \u201cKnowledge graph representation learning with simplifying hierarchical feature propagation\u201d Information Processing & Management 60(4): 103348. DOI: 10.1016\/j.ipm.2023.103348.\n
    \u00a0<\/div>\n<\/li>\n<\/ol>\n<\/div>\n\n\n\n

    <\/p>\n","protected":false},"author":3,"template":"wp-custom-template-detail-4-aricles","meta":{"_uag_custom_page_level_css":""},"categories":[12,15,6,116],"tags":[130],"acf":[],"uagb_featured_image_src":[],"uagb_author_info":{"display_name":"\u6797\u923a\u6db5","author_link":"\/jase\/?author=3"},"uagb_comment_info":0,"uagb_excerpt":" Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited. Download Citation:\u00a0 BibTeX | https:\/\/doi.org\/10.6180\/jase.202601_29(1).0009\u00a0\u00a0 Download PDF In recent years, knowledge representation learning has played a key role…","_links":{"self":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/tkuisotope\/1644"}],"collection":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/tkuisotope"}],"about":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/types\/tkuisotope"}],"author":[{"embeddable":true,"href":"\/jase\/index.php?rest_route=\/wp\/v2\/users\/3"}],"wp:attachment":[{"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1644"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1644"},{"taxonomy":"post_tag","embeddable":true,"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1644"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}