{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T09:40:39Z","timestamp":1759830039867,"version":"build-2065373602"},"reference-count":28,"publisher":"European Alliance for Innovation n.o.","issue":"4","license":[{"start":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T00:00:00Z","timestamp":1759795200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-sa\/4.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["ICST Transactions on Scalable Information Systems"],"abstract":"<jats:p>In this paper, we propose a novel knowledge graph completion framework to leverage a relation-specific attention mechanism integrated with an embedding translation strategy to improve the accuracy and contextual understanding of link prediction tasks. Unlike traditional models that rely on fixed transformation spaces, the proposed method dynamically captures fine-grained relational semantics by combining hierarchical candidate categorization, relation-guided entity projection, and asymmetric score functions. Specifically, the proposed model employs K-means clustering and principal component analysis (PCA) to identify semantically consistent entity sets, and integrates attention-weighted multi-attribute embeddings to construct robust relational representations. A margin-based ranking loss with normalized embedding constraints ensures effective optimization, further supported by Xavier initialization and stochastic gradient descent. Extensive experiments on two benchmark datasets, WN18 and FB15K, demonstrate the superiority of the proposed method. Specifically, on WN18, the proposed method achieves the lowest mean rank (MR) of 144, with competitive results in mean reciprocal rank (MRR) (0.902), Hits@1 (89.0%), Hits@3 (90.4%), and Hits@10 (96.3%), closely rivaling state- of-the-art models like QuatE and ComplEx. On FB15K, the proposed method again delivers the best Mean Rank of 21, along with strong scores in MRR (0.831), Hits@1 (72.2%), Hits@3 (88.4%), and the highest Hits@10 (92.5%) among all compared methods.<\/jats:p>","DOI":"10.4108\/eetsis.9117","type":"journal-article","created":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T09:02:08Z","timestamp":1759827728000},"source":"Crossref","is-referenced-by-count":0,"title":["Leveraging Relation Attention Mechanisms for Enhanced Knowledge Graph Completion with Embedding Translation"],"prefix":"10.4108","volume":"12","author":[{"given":"Jiahao","family":"Shi","sequence":"first","affiliation":[]},{"given":"Zhengping","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Yuzhong","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Yuliang","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Lin","sequence":"additional","affiliation":[]}],"member":"2587","published-online":{"date-parts":[[2025,10,7]]},"reference":[{"key":"177567","unstructured":"[1] S. Kekki, W. Featherstone, Y. Fang, P. Kuure, A. Li, A. Ranjan, D. Purkayastha, F. Jiangping, D. Frydman, G. Verin et al., \u201cMec in 5g networks,\u201d ETSI white paper, vol. 28, no. 28, pp. 1\u201328, 2018."},{"key":"177568","doi-asserted-by":"crossref","unstructured":"[2] S. Guo and X. Zhao, \u201cMulti-agent deep reinforcement learning based transmission latency minimization for delay-sensitive cognitive satellite-UAV networks,\u201d IEEE Trans. Commun., vol. 71, no. 1, pp. 131\u2013144, 2023.","DOI":"10.1109\/TCOMM.2022.3222460"},{"key":"177569","doi-asserted-by":"crossref","unstructured":"[3] H. Hui and W. Chen, \u201cJoint scheduling of proactive pushing and on-demand transmission over shared spectrum for profit maximization,\u201d IEEE Trans. Wirel. Commun., vol. 22, no. 1, pp. 107\u2013121, 2023.","DOI":"10.1109\/TWC.2022.3191361"},{"key":"177570","doi-asserted-by":"crossref","unstructured":"[4] M. Rahim, G. Kaddoum, and T. N. Do, \u201cJoint devices and IRSs association for terahertz communications in industrial IoT networks,\u201d IEEE Trans. Green Commun. Netw., vol. 8, no. 1, pp. 375\u2013390, 2024.","DOI":"10.1109\/TGCN.2023.3332571"},{"key":"177571","doi-asserted-by":"crossref","unstructured":"[5] M. Alawida, \u201cA novel image encryption algorithm based on cyclic chaotic map in industrial IoT environments,\u201d IEEE Trans. Ind. Informatics, vol. 20, no. 8, pp. 10530\u201310541, 2024.","DOI":"10.1109\/TII.2024.3395631"},{"key":"177572","doi-asserted-by":"crossref","unstructured":"[6] Y. Ge, K. Xiong, Q. Wang, Q. Ni, P. Fan, and K. B. Letaief, \u201cAoi-minimal power adjustment in RF-EH-powered industrial IoT networks: A soft actor-critic-based method,\u201d IEEE Trans. Mob. Comput., vol. 23, no. 9, pp. 8729\u20138741, 2024.","DOI":"10.1109\/TMC.2024.3356229"},{"key":"177573","doi-asserted-by":"crossref","unstructured":"[7] C. Hu, J. Liu, H. Xia, S. Deng, and J. Yu, \u201cA lightweight mutual privacy preserving K-means clustering in industrial IoT,\u201d IEEE Trans. Netw. Sci. Eng., vol. 11, no. 2, pp. 2138\u20132152, 2024.","DOI":"10.1109\/TNSE.2023.3337828"},{"key":"177574","doi-asserted-by":"crossref","unstructured":"[8] J. Wang, Y. Hu, Y. Zhu, T. Wang, and A. Schmeink, \u201cReliability-optimal offloading for mobile edge-computing in low-latency industrial IoT networks,\u201d IEEE Trans. Wirel. Commun., vol. 23, no. 10, pp. 12765\u2013 12781, 2024.","DOI":"10.1109\/TWC.2024.3396161"},{"key":"177575","doi-asserted-by":"crossref","unstructured":"[9] Q. Xiong, X. Zhu, Y. Jiang, J. Cao, X. Xiong, and H. Wang,\u201cStatus prediction and data aggregation for AoI-oriented short-packet transmission in industrial IoT,\u201d IEEE Trans. Commun., vol. 71, no. 1, pp. 611\u2013625, 2023.","DOI":"10.1109\/TCOMM.2022.3226188"},{"key":"177576","doi-asserted-by":"crossref","unstructured":"[10] L. Bai, X. Song, and L. Zhu, \u201cJoint multi-feature information entity alignment for cross-lingual temporal knowledge graph with BERT,\u201d IEEE Trans. Big Data, vol. 11, no. 2, pp. 345\u2013358, 2025.","DOI":"10.1109\/TBDATA.2024.3378113"},{"key":"177577","doi-asserted-by":"crossref","unstructured":"[11] F. Yang, W. Chen, H. Lin, S. Wu, X. Li, Z. Li, and Y. Wang, \u201cTask-oriented tool manipulation with robotic dexterous hands: A knowledge graph approach from fingers to functionality,\u201d IEEE Trans. Cybern., vol. 55, no. 1, pp. 395\u2013408, 2025.","DOI":"10.1109\/TCYB.2024.3487845"},{"key":"177578","doi-asserted-by":"crossref","unstructured":"[12] T. Zhang, J. Cheng, L. Miao, H. Chen, Q. Li, Q. He, J. Lyu, and L. Ma, \u201cMulti-hop reasoning with relation based node quality evaluation for sparse medical knowledge graph,\u201d IEEE Trans. Emerg. Top. Comput. Intell., vol. 9, no. 2, pp. 1805\u20131816, 2025.","DOI":"10.1109\/TETCI.2024.3452748"},{"key":"177579","doi-asserted-by":"crossref","unstructured":"[13] Z. Liu, T. Sun, X. Sun, and W. Cui, \u201cEstimating remaining useful life of aircraft engine system via a novel graph tensor fusion network based on knowledge of physical structure and thermodynamics,\u201d IEEE Trans. Instrum. Meas., vol. 74, pp. 1\u201314, 2025.","DOI":"10.1109\/TIM.2025.3550613"},{"key":"177580","doi-asserted-by":"crossref","unstructured":"[14] H. Sun, J. Wang, J. Weng, and W. Tan, \u201cKG-ID: knowledge graph-based intrusion detection on in-vehicle network,\u201d IEEE Trans. Intell. Transp. Syst., vol. 26, no. 4, pp. 4988\u20135000, 2025.","DOI":"10.1109\/TITS.2025.3530155"},{"key":"177581","doi-asserted-by":"crossref","unstructured":"[15] L. Liao, L. Zheng, J. Shang, X. Li, and F. Chen, \u201cATPF: an adaptive temporal perturbation framework for adversarial attacks on temporal knowledge graph,\u201d IEEE Trans. Knowl. Data Eng., vol. 37, no. 3, pp. 1091\u20131104, 2025.","DOI":"10.1109\/TKDE.2024.3510689"},{"key":"177582","doi-asserted-by":"crossref","unstructured":"[16] T. Song, L. Yin, Y. Liu, L. Liao, J. Luo, and Z. Xu, \u201cExpressiveness analysis and enhancing framework for geometric knowledge graph embedding models,\u201d IEEE Trans. Knowl. Data Eng., vol. 37, no. 1, pp. 306\u2013318, 2025.","DOI":"10.1109\/TKDE.2024.3486915"},{"key":"177583","doi-asserted-by":"crossref","unstructured":"[17] S. Bi, Z. Miao, and Q. Min, \u201cLEMON: A knowledge-enhanced, type-constrained, and grammar-guided model for question generation over knowledge graphs,\u201d IEEE Trans. Learn. Technol., vol. 18, pp. 256\u2013272, 2025.","DOI":"10.1109\/TLT.2025.3544454"},{"key":"177584","doi-asserted-by":"crossref","unstructured":"[18] C. Mai, Y. Chang, C. Chen, and Z. Zheng, \u201cEnhanced scalable graph neural network via knowledge distillation,\u201d IEEE Trans. Neural Networks Learn. Syst., vol. 36, no. 1, pp. 1258\u20131271, 2025.","DOI":"10.1109\/TNNLS.2023.3333846"},{"key":"177585","doi-asserted-by":"crossref","unstructured":"[19] X. Sun, B. Zhang, Y. Wang, J. Mai, Y. Wang, J. Tan, and W. Wang, \u201cA multiscale attention mechanism super-resolution confocal microscopy for wafer defect detection,\u201d IEEE Trans Autom. Sci. Eng., vol. 22, pp. 1016\u20131027, 2025.","DOI":"10.1109\/TASE.2024.3358693"},{"key":"177586","doi-asserted-by":"crossref","unstructured":"[20] L. Jin and L. Guo, \u201cFacial expression recognition based on feature representation learning and clustering-based attention mechanism,\u201d IEEE Trans. Biom. Behav. Identity Sci., vol. 7, no. 2, pp. 182\u2013194, 2025.","DOI":"10.1109\/TBIOM.2024.3454975"},{"key":"177587","doi-asserted-by":"crossref","unstructured":"[21] Z. Wang, G. Wang, and G. He, \u201cCOSA plus: Enhanced co-operative systolic arrays for attention mechanism in transformers,\u201d IEEE Trans. Comput. Aided Des. Integr. Circuits Syst., vol. 44, no. 2, pp. 723\u2013736, 2025.","DOI":"10.1109\/TCAD.2024.3434447"},{"key":"177588","doi-asserted-by":"crossref","unstructured":"[22] L. Zhang, J. Wang, Y. Guo, H. Zhang, L. Cheng, and W. Xia, \u201cA self-attention mechanism-based model to detect ipv6 multi-field covert channels,\u201d IEEE Trans. Cogn. Commun. Netw., vol. 11, no. 1, pp. 258\u2013273, 2025.","DOI":"10.1109\/TCCN.2024.3421309"},{"key":"177589","doi-asserted-by":"crossref","unstructured":"[23] S. Li, L. Zhang, H. Guo, J. Li, J. Yu, X. He, Y. Zhao, and X. He, \u201cCSA-FCN: channel- and spatial-gated attention mechanism based fully complex-valued neural network for system matrix calibration in magnetic particle imaging,\u201d IEEE Trans. Computational Imaging, vol. 11, pp. 65\u201376, 2025.","DOI":"10.1109\/TCI.2025.3525948"},{"key":"177590","doi-asserted-by":"crossref","unstructured":"[24] X. Liu, R. Dong, and H. Yang, \u201cDHHG-TAC: fusion of dynamic heterogeneous hypergraphs and transformer attention mechanism for visual question answering tasks,\u201d IEEE Trans. Ind. Informatics, vol. 21, no. 1, pp. 545\u2013553, 2025.","DOI":"10.1109\/TII.2024.3453919"},{"key":"177591","doi-asserted-by":"crossref","unstructured":"[25] M. Li, Z. Wang, K. Li, and X. Liao, \u201cMultiagent-system-based attention mechanism for predicting product popularity: Handling positive-negative diffusion over social networks,\u201d IEEE Trans. Neural Networks Learn. Syst., vol. 36, no. 1, pp. 1925\u20131932, 2025.","DOI":"10.1109\/TNNLS.2023.3330100"},{"key":"177592","doi-asserted-by":"crossref","unstructured":"[26] Z. Fu, K. Jiang, Y. Xu, Y. Wang, T. Wen, H. Gao, Z. Zhong, and D. Yang, \u201cTop-down attention-based mechanisms for interpretable autonomous driving,\u201d IEEE Trans. Intell. Transp. Syst., vol. 26, no. 2, pp. 2212\u20132226, 2025.","DOI":"10.1109\/TITS.2024.3510853"},{"key":"177593","doi-asserted-by":"crossref","unstructured":"[27] X. Li, W. Jiao, Q. Han, and Z. Lu, \u201cDetection of FDIA in power grid based on hypergraph and attention mechanism,\u201d IEEE Trans. Smart Grid, vol. 16, no. 2, pp. 1862\u20131871, 2025.","DOI":"10.1109\/TSG.2024.3524629"},{"key":"177594","doi-asserted-by":"crossref","unstructured":"[28] X. Xu, W. Lv, W. Wang, Y. Zhang, and J. Chen, \u201cEmpowering semantic segmentation with selective frequency enhancement and attention mechanism for tampering detection,\u201d IEEE Trans. Artif. Intell., vol. 5, no. 6, pp. 3270\u20133283, 2024.","DOI":"10.1109\/TAI.2023.3347178"}],"container-title":["ICST Transactions on Scalable Information Systems"],"original-title":[],"link":[{"URL":"https:\/\/publications.eai.eu\/index.php\/sis\/article\/download\/9117\/3724","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/publications.eai.eu\/index.php\/sis\/article\/download\/9117\/3724","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T09:02:29Z","timestamp":1759827749000},"score":1,"resource":{"primary":{"URL":"https:\/\/publications.eai.eu\/index.php\/sis\/article\/view\/9117"}},"subtitle":["Leveraging Relation Attention Mechanisms"],"short-title":[],"issued":{"date-parts":[[2025,10,7]]},"references-count":28,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,7,15]]}},"URL":"https:\/\/doi.org\/10.4108\/eetsis.9117","relation":{},"ISSN":["2032-9407"],"issn-type":[{"value":"2032-9407","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,7]]}}}