{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T10:41:10Z","timestamp":1784198470360,"version":"3.55.0"},"reference-count":99,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2021,11,17]],"date-time":"2021-11-17T00:00:00Z","timestamp":1637107200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61972290 and 61972173"],"award-info":[{"award-number":["61972290 and 61972173"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["2018YFC1604000"],"award-info":[{"award-number":["2018YFC1604000"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Natural Sciences and Engineering Research Council (NSERC) of Canada"},{"name":"York Research Chairs"},{"DOI":"10.13039\/501100001381","name":"National Research Foundation, Singapore","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Inf. Syst."],"published-print":{"date-parts":[[2022,7,31]]},"abstract":"<jats:p>Cross-lingual entity alignment has attracted considerable attention in recent years. Past studies using conventional approaches to match entities share the common problem of missing important structural information beyond entities in the modeling process. This allows graph neural network models to step in. Most existing graph neural network approaches model individual knowledge graphs (KGs) separately with a small amount of pre-aligned entities served as anchors to connect different KG embedding spaces. However, this characteristic can cause several major problems, including performance restraint due to the insufficiency of available seed alignments and ignorance of pre-aligned links that are useful in contextual information in-between nodes. In this article, we propose DuGa-DIT, a dual gated graph attention network with dynamic iterative training, to address these problems in a unified model. The DuGa-DIT model captures neighborhood and cross-KG alignment features by using intra-KG attention and cross-KG attention layers. With the dynamic iterative process, we can dynamically update the cross-KG attention score matrices, which enables our model to capture more cross-KG information. We conduct extensive experiments on two benchmark datasets and a case study in cross-lingual personalized search. Our experimental results demonstrate that DuGa-DIT outperforms state-of-the-art methods.<\/jats:p>","DOI":"10.1145\/3471165","type":"journal-article","created":{"date-parts":[[2021,11,17]],"date-time":"2021-11-17T21:53:46Z","timestamp":1637186026000},"page":"1-30","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":19,"title":["Dual Gated Graph Attention Networks with Dynamic Iterative Training for Cross-Lingual Entity Alignment"],"prefix":"10.1145","volume":"40","author":[{"given":"Zhiwen","family":"Xie","sequence":"first","affiliation":[{"name":"Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Runjie","family":"Zhu","sequence":"additional","affiliation":[{"name":"York University and AI Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kunsong","family":"Zhao","sequence":"additional","affiliation":[{"name":"Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Liu","sequence":"additional","affiliation":[{"name":"Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangyou","family":"Zhou","sequence":"additional","affiliation":[{"name":"Central China Normal University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jimmy Xiangji","family":"Huang","sequence":"additional","affiliation":[{"name":"York University, Toronto, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,11,17]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.5555\/1785162.1785216"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1431"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376746"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-013-5363-6"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.5555\/2999792.2999923"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1140"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-47426-3_65"},{"key":"e_1_3_2_9_2","unstructured":"Danqi Chen Richard Socher Christopher D. Manning and Andrew Y. Ng. 2013. Learning new facts from knowledge bases with neural tensor networks and semantic word vectors. arXiv:1301.3618."},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.5555\/3304222.3304326"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.5555\/3172077.3172097"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.5555\/3504035.3504256"},{"key":"e_1_3_2_13_2","first-page":"4171","volume-title":"Proceedings of NAACL-HLT","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of NAACL-HLT. 4171\u20134186. DOI: https:\/\/doi.org\/10.18653\/v1\/n19-1423"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413628"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.5555\/3032027.3032102"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1034"},{"key":"e_1_3_2_17_2","unstructured":"Alberto Garc\u0107a-Duran and Mathias Niepert. 2018. KBLRN: End-to-end learning of knowledge base representations with latent relational and numerical features. arXiv:1709.04676."},{"key":"e_1_3_2_18_2","first-page":"315","volume-title":"Proceedings of AISTATS","author":"Glorot Xavier","year":"2011","unstructured":"Xavier Glorot, Antoine Bordes, and Yoshua Bengio. 2011. Deep sparse rectifier neural networks. In Proceedings of AISTATS. 315\u2013323."},{"key":"e_1_3_2_19_2","first-page":"2505","volume-title":"Proceedings of ICML","author":"Guo Lingbing","year":"2019","unstructured":"Lingbing Guo, Zequn Sun, and Wei Hu. 2019. Learning to exploit long-term relational dependencies in knowledge graphs. In Proceedings of ICML. 2505\u20132514."},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-3168-7_1"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/2806416.2806502"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.5555\/2999325.2999488"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1067"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.5555\/3015812.3015959"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1162\/dint_a_00003"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.5555\/3327144.3327341"},{"key":"e_1_3_2_27_2","volume-title":"Proceedings of ICLR","author":"Kingma Diederik P.","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In Proceedings of ICLR."},{"key":"e_1_3_2_28_2","volume-title":"Proceedings of ICLR","author":"Kipf Thomas N.","year":"2017","unstructured":"Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of ICLR."},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2083"},{"key":"e_1_3_2_30_2","doi-asserted-by":"crossref","unstructured":"Agustinus Kristiadi Mohammad Asif Khan Denis Lukovnikov Jens Lehmann and Asja Fischer. 2019. Incorporating literals into knowledge graph embeddings. arXiv:1802.00934.","DOI":"10.1007\/978-3-030-30793-6_20"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-25007-6_37"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.3233\/SW-140134"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1274"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2008.202"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00053"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1082"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.5555\/3060832.3061022"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.5555\/2886521.2886624"},{"key":"e_1_3_2_39_2","unstructured":"Zhiyuan Liu Yixin Cao Liangming Pan Juanzi Li and Tat-Seng Chua. 2020. Exploring and evaluating attributes values and structures for entity alignment. In Proceedings of EMNLP . 6355\u20136364."},{"key":"e_1_3_2_40_2","volume-title":"Proceedings of the ICML Workshop","author":"Hannun Awni Y.","year":"2013","unstructured":"Andrew L. Maas, Awni Y. Hannun, and Andrew Y. Ng. 2013. Rectifier nonlinearities improve neural network acoustic models. In Proceedings of the ICML Workshop."},{"key":"e_1_3_2_41_2","volume-title":"Proceedings of CIDR","author":"Mahdisoltani Farzaneh","year":"2015","unstructured":"Farzaneh Mahdisoltani, Joanna Biega, and Fabian Suchanek. 2015. YAGO3: A knowledge base from multilingual Wikipedias. In Proceedings of CIDR."},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371804"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.5555\/2976040.2976154"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413598"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1466"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.5555\/1858681.1858704"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2053"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K16-1005"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1226"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.5555\/3016100.3016172"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.5555\/3104482.3104584"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.5555\/3491440.3491946"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271769"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313646"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403268"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.5555\/3367471.3367490"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.5555\/3304222.3304366"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93417-4_38"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013060"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.5555\/3298239.3298420"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1075"},{"key":"e_1_3_2_63_2","article-title":"Introducing the knowledge graph: Things, not strings","author":"Singhal Amit","year":"2012","unstructured":"Amit Singhal. 2012. Introducing the knowledge graph: Things, not strings. Google Blog.","journal-title":"Google Blog."},{"key":"e_1_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.websem.2008.06.001"},{"key":"e_1_3_2_65_2","doi-asserted-by":"crossref","unstructured":"Zequn Sun Muhao Chen Wei Hu Chengming Wang Jian Dai and Wei Zhang. 2020. Knowledge association with hyperbolic knowledge graph embeddings. arXiv:2010.02162.","DOI":"10.18653\/v1\/2020.emnlp-main.460"},{"key":"e_1_3_2_66_2","volume-title":"Proceedings of ICLR","author":"Sun Zhiqing","year":"2019","unstructured":"Zhiqing Sun, Zhi-Hong Deng, Jian-Yun Nie, and Jian Tang. 2019. RotatE: Knowledge graph embedding by relational rotation in complex space. In Proceedings of ICLR."},{"key":"e_1_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68288-4_37"},{"key":"e_1_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.5555\/3304222.3304381"},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5354"},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045609"},{"key":"e_1_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i03.5694"},{"key":"e_1_3_2_72_2","unstructured":"Petar Velickovic Guillem Cucurull Arantxa Casanova Adriana Romero Pietro Li\u00f2 and Yoshua Bengio. 2017. Graph attention networks. arXiv:1710.10903."},{"key":"e_1_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1145\/2187980.2188242"},{"key":"e_1_3_2_74_2","unstructured":"Kai Wang Yu Liu Xiujuan Xu and Dan Lin. 2018. Knowledge graph embedding with entity neighbors and deep memory network. arXiv:1808.03752. DOI: https:\/\/doi.org\/CoRR abs\/1808.03752."},{"key":"e_1_3_2_75_2","unstructured":"Quan Wang Pingping Huang Haifeng Wang Songtai Dai Wenbin Jiang Jing Liu Yajuan Lyu Yong Zhu and Hua Wu. 2019. CoKE: Contextualized knowledge graph embedding. arXiv:1911.02168."},{"key":"e_1_3_2_76_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015329"},{"key":"e_1_3_2_77_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1032"},{"key":"e_1_3_2_78_2","doi-asserted-by":"publisher","DOI":"10.5555\/2893873.2894046"},{"key":"e_1_3_2_79_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413556"},{"key":"e_1_3_2_80_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1616"},{"key":"e_1_3_2_81_2","doi-asserted-by":"publisher","DOI":"10.5555\/3367722.3367779"},{"key":"e_1_3_2_82_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1023"},{"key":"e_1_3_2_83_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.578"},{"key":"e_1_3_2_84_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-3017"},{"key":"e_1_3_2_85_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1219"},{"key":"e_1_3_2_86_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.526"},{"key":"e_1_3_2_87_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.520"},{"key":"e_1_3_2_88_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1060"},{"key":"e_1_3_2_89_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6476"},{"key":"e_1_3_2_90_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1304"},{"key":"e_1_3_2_91_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.06.054"},{"key":"e_1_3_2_92_2","volume-title":"Proceedings of ICLR","author":"Yang Bishan","year":"2015","unstructured":"Bishan Yang, Wen-Tau Yih, Xiaodong He, Jianfeng Gao, and Li Deng. 2015. Embedding entities and relations for learning and inference in knowledge bases. In Proceedings of ICLR."},{"key":"e_1_3_2_93_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1451"},{"key":"e_1_3_2_94_2","doi-asserted-by":"publisher","DOI":"10.5555\/3367243.3367307"},{"key":"e_1_3_2_95_2","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3454533"},{"key":"e_1_3_2_96_2","first-page":"1056","article-title":"Entity alignment across knowledge graphs based on representative relations selection","author":"Zhang Youmin","year":"2018","unstructured":"Youmin Zhang, Li Liu, Shun Fu, and Fujin Zhong. 2018. Entity alignment across knowledge graphs based on representative relations selection. Proceedings of ICSAI. 1056\u20131061. DOI: https:\/\/doi.org\/10.1109\/ICSAI.2018.8599288","journal-title":"Proceedings of ICSAI"},{"key":"e_1_3_2_97_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1139"},{"key":"e_1_3_2_98_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2017.11.044"},{"key":"e_1_3_2_99_2","doi-asserted-by":"publisher","DOI":"10.5555\/3171837.3171881"},{"key":"e_1_3_2_100_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/269"}],"container-title":["ACM Transactions on Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3471165","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3471165","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T17:49:30Z","timestamp":1750268970000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3471165"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,17]]},"references-count":99,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,7,31]]}},"alternative-id":["10.1145\/3471165"],"URL":"https:\/\/doi.org\/10.1145\/3471165","relation":{},"ISSN":["1046-8188","1558-2868"],"issn-type":[{"value":"1046-8188","type":"print"},{"value":"1558-2868","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,17]]},"assertion":[{"value":"2020-11-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-06-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-11-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}