{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T21:39:26Z","timestamp":1757540366755,"version":"3.41.2"},"reference-count":39,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2021,4,19]],"date-time":"2021-04-19T00:00:00Z","timestamp":1618790400000},"content-version":"vor","delay-in-days":108,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100010868","name":"Ministry of Public Security of the People's Republic of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010868","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61771072"],"award-info":[{"award-number":["61771072"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Wireless Communications and Mobile Computing"],"published-print":{"date-parts":[[2021,1]]},"abstract":"<jats:p>The goal of network representation learning is to extract deep\u2010level abstraction from data features that can also be viewed as a process of transforming the high\u2010dimensional data to low\u2010dimensional features. Learning the mapping functions between two vector spaces is an essential problem. In this paper, we propose a new similarity index based on traditional machine learning, which integrates the concepts of common neighbor, local path, and preferential attachment. Furthermore, for applying the link prediction methods to the field of node classification, we have innovatively established an architecture named multitask graph autoencoder. Specifically, in the context of structural deep network embedding, the architecture designs a framework of high\u2010order loss function by calculating the node similarity from multiple angles so that the model can make up for the deficiency of the second\u2010order loss function. Through the parameter fine\u2010tuning, the high\u2010order loss function is introduced into the optimized autoencoder. Proved by the effective experiments, the framework is generally applicable to the majority of classical similarity indexes.<\/jats:p>","DOI":"10.1155\/2021\/5537651","type":"journal-article","created":{"date-parts":[[2021,4,19]],"date-time":"2021-04-19T23:03:24Z","timestamp":1618873404000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Link Prediction and Node Classification Based on Multitask Graph Autoencoder"],"prefix":"10.1155","volume":"2021","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0500-9288","authenticated-orcid":false,"given":"Shicong","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2118-9263","authenticated-orcid":false,"given":"Deyu","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuhua","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2021,4,19]]},"reference":[{"key":"e_1_2_11_1_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2020.101876"},{"key":"e_1_2_11_2_2","doi-asserted-by":"publisher","DOI":"10.1177\/1550147719899374"},{"key":"e_1_2_11_3_2","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/2008\/10\/P10008"},{"key":"e_1_2_11_4_2","unstructured":"TrouillonT. WelblJ. RiedelS. GaussierE. andBouchardG. Complex embeddings for simple link prediction Proceedings of The 33rd International Conference on Machine Learning 2016 New York New York USA 2071\u20132080."},{"key":"e_1_2_11_5_2","first-page":"211","article-title":"Similarity index based on local paths for link prediction of complex network","volume":"80","author":"Lv L. Y.","year":"2009","journal-title":"Physical Review E"},{"key":"e_1_2_11_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3013018"},{"key":"e_1_2_11_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2018.2850013"},{"key":"e_1_2_11_8_2","first-page":"130","article-title":"A new algorithm of DeepWalk based on probability","volume":"1069","author":"Cai L.","year":"2019","journal-title":"Journal of Physics: Conference Series"},{"key":"e_1_2_11_9_2","doi-asserted-by":"publisher","DOI":"10.1080\/0022250X.1971.9989788"},{"key":"e_1_2_11_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-8733(03)00009-1"},{"key":"e_1_2_11_11_2","article-title":"Etude comparative de la distribution florale dans une portion des Alpes et des Jura","volume":"37","author":"Jaccard P.","year":"1901","journal-title":"Bulletin of the Torrey Botanical Club"},{"key":"e_1_2_11_12_2","doi-asserted-by":"publisher","DOI":"10.1140\/epjb\/e2009-00335-8"},{"key":"e_1_2_11_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF02289026"},{"key":"e_1_2_11_14_2","unstructured":"MikolovT. ChenK. CorradoG. andDeanJ. Efficient estimation of word representations in vector space 2013 https:\/\/arxiv.org\/abs\/1301.3781."},{"key":"e_1_2_11_15_2","doi-asserted-by":"crossref","unstructured":"PerozziB. AlrfouR. andSkienaS. Deepwalk: online learning of social representations Proceedings of the 20th ACM SIGKDD international conference on knowledge discovery and data mining 2014 Newyork USA 701\u2013710.","DOI":"10.1145\/2623330.2623732"},{"key":"e_1_2_11_16_2","unstructured":"RibeiroL. F. R. SavereseP. H. P. andFigueiredoD. R. struc2vec: learning node representations from structural identity Proceedings of the 23rd ACM SIGKDD international conference on knowledge discovery and data mining 2017 Halifax NS Canada 385\u2013394."},{"key":"e_1_2_11_17_2","doi-asserted-by":"crossref","unstructured":"TangJ. QuM. WangM. ZhangM. YanJ. andMeiQ. Line: large- scale information network embedding Proceedings of the 24th international conference on world wide web 2015 Florence Italy 1067\u20131077.","DOI":"10.1145\/2736277.2741093"},{"key":"e_1_2_11_18_2","unstructured":"MikolovT. SutskeverI. ChenK. CorradoG. andDeanJ. Distributed representations of words and phrases and their compositionality Advances in neural information processing systems 2013 3111\u20133119."},{"key":"e_1_2_11_19_2","first-page":"2672","article-title":"Generative adversarial networks","volume":"3","author":"Goodfellow I. J.","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_11_20_2","doi-asserted-by":"crossref","unstructured":"BengioY. LamblinP. PopoviciD. andLarochelleH. Greedy layerwise training of deep networks International conference on neural information processing systems 2006 Stony Brook University 153\u2013160.","DOI":"10.7551\/mitpress\/7503.003.0024"},{"key":"e_1_2_11_21_2","first-page":"1185","article-title":"Sparse feature learning for dep belief networks","volume":"20","author":"Ranzato M.","year":"2007","journal-title":"Advances in Neural Information Processing Systems"},{"volume-title":"Variational Graph Auto-Encoders","year":"2016","author":"Tomas N. K.","key":"e_1_2_11_22_2"},{"key":"e_1_2_11_23_2","doi-asserted-by":"crossref","unstructured":"WangD. CuiP. andZhuW. Structural deep network embedding Proceedings of the 22nd international conference on knowledge discovery and data mining 2016 San Francisco CA USA 1225\u20131234.","DOI":"10.1145\/2939672.2939753"},{"key":"e_1_2_11_24_2","doi-asserted-by":"publisher","DOI":"10.1002\/asi.20591"},{"key":"e_1_2_11_25_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.75.021102"},{"key":"e_1_2_11_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-2766-4_7"},{"key":"e_1_2_11_27_2","unstructured":"AbadiM. AgarwalA. BarhamP. BrevdoE. ChenZ. CitroC. CorradoG. S. DavisA. DeanJ. DevinM. andGhemawatS. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems 2015 https:\/\/github.com\/tensorflow\/tensorflow."},{"key":"e_1_2_11_28_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"e_1_2_11_29_2","unstructured":"KingmaD. P.andBaJ. L. Adam: a method for stochastic optimization International Conference on Learning Representations (ICLR) 2015 San Diego USA."},{"key":"e_1_2_11_30_2","unstructured":"NairV.andHintonG. E. Rectified linear units improve restricted Boltzmann machines Proceedings of the 27th International Conference on Machine Learning 2010 Toronto Canada."},{"key":"e_1_2_11_31_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.74.036104"},{"volume-title":"Mapping the US Political Blogosphere: Are Conservative Bloggers More Prominent","year":"2005","author":"Ackland R.","key":"e_1_2_11_32_2"},{"key":"e_1_2_11_33_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature750"},{"key":"e_1_2_11_34_2","unstructured":"BatageliV.andMrvarA. Pajek Datasets http:\/\/vlado.fmf.unilj.si\/pub\/networks\/data\/default.htm."},{"key":"e_1_2_11_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2003.822655"},{"key":"e_1_2_11_36_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.1073374"},{"key":"e_1_2_11_37_2","doi-asserted-by":"crossref","unstructured":"GroverA.andLeskovecJ. node2vec: scalable feature learning for networks Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining 2016 San Francisco CA USA 855\u2013864.","DOI":"10.1145\/2939672.2939754"},{"key":"e_1_2_11_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"e_1_2_11_39_2","doi-asserted-by":"publisher","DOI":"10.1049\/cje.2019.06.007"}],"container-title":["Wireless Communications and Mobile Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/wcmc\/2021\/5537651.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/wcmc\/2021\/5537651.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2021\/5537651","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T13:33:16Z","timestamp":1723037596000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2021\/5537651"}},"subtitle":[],"editor":[{"given":"Lihua","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":39,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["10.1155\/2021\/5537651"],"URL":"https:\/\/doi.org\/10.1155\/2021\/5537651","archive":["Portico"],"relation":{},"ISSN":["1530-8669","1530-8677"],"issn-type":[{"type":"print","value":"1530-8669"},{"type":"electronic","value":"1530-8677"}],"subject":[],"published":{"date-parts":[[2021,1]]},"assertion":[{"value":"2021-02-03","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-04-05","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-04-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"5537651"}}