{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T12:03:34Z","timestamp":1780401814821,"version":"3.54.1"},"reference-count":46,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T00:00:00Z","timestamp":1780358400000},"content-version":"vor","delay-in-days":152,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Intelligent Systems"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:p>In recent years, entity matching methods based on graph neural networks have significantly improved the ability of entity structure representation through multilayer neighborhood aggregation. However, such methods still suffer from oversmoothing and noise diffusion in local structures, as well as insufficient global topological consistency and limited geometric expression. Existing methods usually rely on local aggregation to obtain structural representations, making it difficult to explicitly model the global topological patterns and hierarchical structures between entities. Especially in heterogeneous or cross\u2010lingual graphs, traditional Euclidean embedding spaces cannot fully represent complex semantic hierarchies and multiscale geometric relationships. To this end, this paper proposes a Triview Dual\u2010space Contrastive Perception Matching (TriDCPM) method, which unifies the modeling of local correlations, global topologies, and cross\u2010graph consistency under a multiview representation and geometric collaborative learning framework. Specifically, TriDCPM constructs a triview framework consisting of local, global, and cross\u2010graph views and simultaneously learns multiscale entity representations in both Euclidean and hyperbolic geometric spaces. A global structure enhancement module based on singular value decomposition (SVD) is adopted to extract key topological patterns, and a gated residual unit (GRU) is introduced to alleviate noise propagation and oversmoothing. In the local encoding stage, multilayer attention aggregation and a degree\u2010aware relation fusion mechanism are employed to further enhance heterogeneous neighborhood and relational semantic features. Finally, a dual\u2010level contrastive consistency learning mechanism is adopted to jointly optimize feature consistency between the local\u2013global levels and the Euclidean\u2013hyperbolic spaces, achieving collaborative perception and discriminative unification of multiview representations. Experimental results on four public benchmark datasets demonstrate that the proposed method significantly outperforms existing structure\u2010driven entity alignment approaches in terms of Hit@1, MRR, and other metrics, with particularly outstanding performance in relation\u2010heterogeneous and cross\u2010lingual scenarios. Further ablation experiments and visualization analysis verify the effectiveness and stability of the proposed method in global structure modeling, noise suppression, and multispace contrastive optimization.<\/jats:p>","DOI":"10.1155\/int\/5865814","type":"journal-article","created":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T11:06:54Z","timestamp":1780398414000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Three\u2010View Dual\u2010Space Contrastive Perception Matching Method for Entity Alignment"],"prefix":"10.1155","volume":"2026","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2072-9955","authenticated-orcid":false,"given":"Qiwen","family":"Tan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0166-1324","authenticated-orcid":false,"given":"Tiezheng","family":"Nie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,6,2]]},"reference":[{"key":"e_1_2_10_1_2","doi-asserted-by":"crossref","unstructured":"AuerS. BizerC. KobilarovG. LehmannJ. CyganiakR. andIvesZ. Dbpedia: A Nucleus for a Web of Open Data International Semantic Web Conference 2007 722\u2013735.","DOI":"10.1007\/978-3-540-76298-0_52"},{"key":"e_1_2_10_2_2","doi-asserted-by":"crossref","unstructured":"SuchanekF. M. KasneciG. andWeikumG. Yago: A Core of Semantic Knowledge Proceedings of the 16th International Conference on World Wide Web 2007 697\u2013706.","DOI":"10.1145\/1242572.1242667"},{"key":"e_1_2_10_3_2","doi-asserted-by":"crossref","unstructured":"BollackerK. EvansC. ParitoshP. SturgeS. andTaylorJ. Freebase: a Collaboratively Created Graph Database for Structuring Human Knowledge Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data 2008 1247\u20131250.","DOI":"10.1145\/1376616.1376746"},{"key":"e_1_2_10_4_2","doi-asserted-by":"crossref","unstructured":"JadonA.andPatilA. A Comprehensive Survey of Evaluation Techniques for Recommendation Systems International Conference on Computation of Artificial Intelligence and Machine Learning 2024 281\u2013304.","DOI":"10.1007\/978-3-031-71484-9_25"},{"key":"e_1_2_10_5_2","doi-asserted-by":"crossref","unstructured":"WangY. LipkaN. RossiR. A. AhmedN. K. ZhangR. andDerrT. Knowledge Graph Prompting for Multi-Document Question Answering 38 Proceedings of the AAAI Conference on Artificial Intelligence 2024 no. 17 19206\u201319214 https:\/\/doi.org\/10.1609\/aaai.v38i17.29889.","DOI":"10.1609\/aaai.v38i17.29889"},{"key":"e_1_2_10_6_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41564-023-01575-9"},{"key":"e_1_2_10_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106143"},{"key":"e_1_2_10_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102581"},{"key":"e_1_2_10_9_2","first-page":"2787","article-title":"Translating Embeddings for Modeling Multi-Relational Data","volume":"26","author":"Bordes A.","year":"2013","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_10_2","unstructured":"WuF. SouzaA. ZhangT. FiftyC. YuT. andWeinbergerK. Q. Simplifying Graph Convolutional Networks International Conference on Machine Learning 2019 6861\u20136871."},{"key":"e_1_2_10_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.108009"},{"key":"e_1_2_10_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3643861"},{"key":"e_1_2_10_13_2","doi-asserted-by":"crossref","unstructured":"WangC. WangW. LiangQ.et al. GSEA: Global Structure-Aware Graph Neural Networks for Entity Alignment CCF International Conference on Natural Language Processing and Chinese Computing 2024 187\u201319.","DOI":"10.1007\/978-981-97-9434-8_15"},{"key":"e_1_2_10_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.129445"},{"key":"e_1_2_10_15_2","unstructured":"WangC. WangW. LiangQ. BaoF. andGaoG. Unifying Dual-Space Embedding for Entity Alignment via Contrastive Learning Proceedings of the 31st International Conference on Computational Linguistics 2025 Abu Dhabi UAE: Association for Computational Linguistics 3110\u20133122."},{"key":"e_1_2_10_16_2","doi-asserted-by":"crossref","unstructured":"ChenM. TianY. YangM.et al. Multilingual Knowledge Graph Embeddings for Cross-Lingual Knowledge Alignment 2016.","DOI":"10.24963\/ijcai.2017\/209"},{"key":"e_1_2_10_17_2","doi-asserted-by":"crossref","unstructured":"ZhuH. XieR. LiuZ.et al. Iterative Entity Alignment via Joint Knowledge Embeddings Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI 2017) 2017 4258\u20134264.","DOI":"10.24963\/ijcai.2017\/595"},{"key":"e_1_2_10_18_2","doi-asserted-by":"crossref","unstructured":"SunZ. HuW. ZhangQ. andQuY. Bootstrapping Entity Alignment With Knowledge Graph Embedding Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI 2018) 2018 4396\u20134402.","DOI":"10.24963\/ijcai.2018\/611"},{"key":"e_1_2_10_19_2","doi-asserted-by":"crossref","unstructured":"WangZ. LvQ. LanX. andZhangY. Cross-Lingual Knowledge Graph Alignment via Graph Convolutional Networks Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP 2018) 2018 349\u2013357.","DOI":"10.18653\/v1\/D18-1032"},{"key":"e_1_2_10_20_2","doi-asserted-by":"crossref","unstructured":"ZhuZ. FanX. ChuX.et al. HGCN: A Heterogeneous Graph Convolutional Network-Based Deep Learning Model Toward Collective Classification Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 2020 1161\u20131171.","DOI":"10.1145\/3394486.3403169"},{"key":"e_1_2_10_21_2","article-title":"Dual-Relational Graph for Entity and Relation Comprehension","volume":"243","author":"Sang J.","year":"2022","journal-title":"Knowledge-Based Systems"},{"key":"e_1_2_10_22_2","doi-asserted-by":"crossref","unstructured":"SunZ. WangC. HuW.et al. Knowledge Graph Alignment Network With Gated Multi-Hop Neighborhood Aggregation 34 Proceedings of the AAAI Conference on Artificial Intelligence 2020 no. 01 222\u2013229 https:\/\/doi.org\/10.1609\/aaai.v34i01.5354.","DOI":"10.1609\/aaai.v34i01.5354"},{"key":"e_1_2_10_23_2","unstructured":"LiW. HuangX. ZhengJ.et al. rLLM: Relational Table Learning With LLMs 2025."},{"key":"e_1_2_10_24_2","doi-asserted-by":"crossref","unstructured":"WangZ. DingH. PanL. LiJ. GongZ. andYuP. S. From Cluster Assumption to Graph Convolution: Graph-Based Semi-Supervised Learning Revisited 2025.","DOI":"10.1109\/TNNLS.2024.3454710"},{"key":"e_1_2_10_25_2","doi-asserted-by":"crossref","unstructured":"ZhangW. ShengY. YinZ.et al. SVD-GCN: A Simplified Graph Convolution Paradigm Proceedings of the 2021 IEEE International Conference on Data Mining (ICDM) 2021 IEEE 797\u2013806.","DOI":"10.1109\/ICDM51629.2021.00091"},{"key":"e_1_2_10_26_2","doi-asserted-by":"publisher","DOI":"10.1137\/s0097539704442684"},{"key":"e_1_2_10_27_2","unstructured":"Veli\u010dkovi\u0107P. CucurullG. CasanovaA. RomeroA. Li\u00f2P. andBengioY. Graph Attention Networks International Conference on Learning Representations 2018."},{"key":"e_1_2_10_28_2","first-page":"5998","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani A.","year":"2017"},{"key":"e_1_2_10_29_2","doi-asserted-by":"crossref","unstructured":"SchlichtkrullM. KipfT. N. BloemP. van den BergR. TitovI. andWellingM. Modeling Relational Data With Graph Convolutional Networks Proceedings of the 15th Extended Semantic Web Conference (ESWC) 2018 593\u2013607.","DOI":"10.1007\/978-3-319-93417-4_38"},{"key":"e_1_2_10_30_2","doi-asserted-by":"crossref","unstructured":"ChoK. van Merri\u00ebnboerB. GulcehreC.et al. Learning Phrase Representations Using RNN Encoder-Decoder for Statistical Machine Translation Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) 2014 1724\u20131734.","DOI":"10.3115\/v1\/D14-1179"},{"key":"e_1_2_10_31_2","doi-asserted-by":"crossref","unstructured":"ChenD. LinY. LiW. LiP. ZhouJ. andSunX. Measuring and Relieving the Over-Smoothing Problem for Graph Neural Networks From the Topological View 34 Proceedings of the AAAI Conference on Artificial Intelligence 2020 no. 04 3438\u20133445 https:\/\/doi.org\/10.1609\/aaai.v34i04.5747.","DOI":"10.1609\/aaai.v34i04.5747"},{"key":"e_1_2_10_32_2","unstructured":"KipfT. N.andWellingM. Semi-Supervised Classification With Graph Convolutional Networks International Conference on Learning Representations (ICLR) 2017."},{"key":"e_1_2_10_33_2","unstructured":"HassaniK.andKhaashmadiA. H. Contrastive Multi-View Representation Learning on Graphs International Conference on Machine Learning (ICML) 2020 4116\u20134126."},{"key":"e_1_2_10_34_2","first-page":"6338","volume-title":"Advances in Neural Information Processing Systems","author":"Nickel M.","year":"2017"},{"key":"e_1_2_10_35_2","doi-asserted-by":"crossref","unstructured":"SchroffF. KalenichenkoD. andPhilbinJ. FaceNet: A Unified Embedding for Face Recognition and Clustering Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2015 815\u2013823.","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_2_10_36_2","unstructured":"ZhaoX. LiuZ. andSunM. Effective and Efficient: Toward Open-World Entity Alignment Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) 2020 7780\u20137789."},{"key":"e_1_2_10_37_2","unstructured":"ConneauA. LampleG. RanzatoM. DenoyerL. andJ\u00e9gouH. Word Translation Without Parallel Data International Conference on Learning Representations (ICLR) 2018."},{"key":"e_1_2_10_38_2","doi-asserted-by":"crossref","unstructured":"PeiS. YuL. andYuG. Improving Cross-Lingual Entity Alignment via Optimal Transport Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI 2019) 2019 3231\u20133237.","DOI":"10.24963\/ijcai.2019\/448"},{"key":"e_1_2_10_39_2","first-page":"1784","article-title":"Improving Knowledge Graph Entity Alignment With Graph Augmentation","volume":"8","author":"Xie F.","year":"2022","journal-title":"IEEE Transactions on Big Data"},{"key":"e_1_2_10_40_2","doi-asserted-by":"crossref","unstructured":"LiuX. ZhangK. LiuY.et al. RHGN: Relation-Gated Heterogeneous Graph Network for Entity Alignment in Knowledge Graphs Findings of the Association for Computational Linguistics: ACL 2023 2023 8683\u20138696.","DOI":"10.18653\/v1\/2023.findings-acl.553"},{"key":"e_1_2_10_41_2","unstructured":"WangY. ZhangZ. WangH. ChenH. andZhangW. Global Structure and Local Context-Aware Contrastive Learning for Entity Alignment Proceedings of the IEEE International Conference on Data Mining (ICDM 2024) 2024 3564\u20133576."},{"key":"e_1_2_10_42_2","unstructured":"WangC. WangW. LiangQ. BaoF. andGaoG. Unifying Dual-Space Embedding for Entity Alignment via Contrastive Learning Proceedings of the 31st International Conference on Computational Linguistics (COLING 2025) 2025 3110\u20133122."},{"key":"e_1_2_10_43_2","doi-asserted-by":"crossref","unstructured":"MaoX. WangW. WuY.et al. Boosting the Speed of Entity Alignment 10 \u00d7: Dual Attention Matching Network With Normalized Hard Sample Mining Proceedings of the Web Conference 2021 (WWW 2021) 2021 821\u2013832.","DOI":"10.1145\/3442381.3449897"},{"key":"e_1_2_10_44_2","unstructured":"QiuJ.andLiJ. SVD-Embedding: A SVD-Based Method for Node Embedding in Graphs Proceedings of the 2018 SIAM International Conference on Data Mining (SDM) 2018 61\u201369."},{"key":"e_1_2_10_45_2","unstructured":"LiY. TarlowD. BrockschmidtM. andZemelR. Gated Graph Sequence Neural Networks International Conference on Learning Representations (ICLR) 2016."},{"key":"e_1_2_10_46_2","unstructured":"LiuQ. NickelM. andKielaD. Self-Supervised Learning on Hyperbolic Space International Conference on Learning Representations (ICLR) 2021."}],"container-title":["International Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/5865814","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1155\/int\/5865814","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/5865814","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T11:07:14Z","timestamp":1780398434000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/int\/5865814"}},"subtitle":[],"editor":[{"given":"Richard","family":"Murray","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":46,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1155\/int\/5865814"],"URL":"https:\/\/doi.org\/10.1155\/int\/5865814","archive":["Portico"],"relation":{},"ISSN":["0884-8173","1098-111X"],"issn-type":[{"value":"0884-8173","type":"print"},{"value":"1098-111X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"2025-08-18","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-10","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-02","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"5865814"}}