{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T20:16:36Z","timestamp":1776197796950,"version":"3.50.1"},"reference-count":157,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0100204"],"award-info":[{"award-number":["2018AAA0100204"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002920","name":"Research Grants Council of the Hong Kong Special Administrative Region, China","doi-asserted-by":"publisher","award":["CUHK 2300174"],"award-info":[{"award-number":["CUHK 2300174"]}],"id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Collaborative Research Fund","award":["C5026-18GF"],"award-info":[{"award-number":["C5026-18GF"]}]},{"DOI":"10.13039\/501100017610","name":"Key Program of Fundamental Research from the Shenzhen Science and Technology Innovation Commission","doi-asserted-by":"publisher","award":["JCYJ20200109113403826"],"award-info":[{"award-number":["JCYJ20200109113403826"]}],"id":[{"id":"10.13039\/501100017610","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1109\/tnnls.2022.3155478","type":"journal-article","created":{"date-parts":[[2022,3,19]],"date-time":"2022-03-19T01:37:07Z","timestamp":1647653827000},"page":"8174-8194","source":"Crossref","is-referenced-by-count":230,"title":["Graph-Based Semi-Supervised Learning: A Comprehensive Review"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8871-3990","authenticated-orcid":false,"given":"Zixing","family":"Song","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0546-5440","authenticated-orcid":false,"given":"Xiangli","family":"Yang","sequence":"additional","affiliation":[{"name":"SMILE Laboratory, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5550-6461","authenticated-orcid":false,"given":"Zenglin","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8106-6447","authenticated-orcid":false,"given":"Irwin","family":"King","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China"}]}],"member":"263","reference":[{"key":"ref57","author":"chapelle","year":"2010","journal-title":"Semi-Supervised Learning"},{"key":"ref56","first-page":"679","article-title":"Large graph construction for scalable semi-supervised learning","author":"liu","year":"2010","journal-title":"Proc ICML"},{"key":"ref59","first-page":"561","article-title":"Manifold denoising","author":"hein","year":"2006","journal-title":"Proc NIPS"},{"key":"ref58","article-title":"Topics in graph construction for semi-supervised learning","author":"talukdar","year":"2009"},{"key":"ref53","first-page":"1306","article-title":"Poisson learning: Graph based semi-supervised learning at very low label rates","volume":"119","author":"calder","year":"2020","journal-title":"Proc ICML"},{"key":"ref52","first-page":"1","article-title":"Learning a SAT solver from single-bit supervision","author":"selsam","year":"2019","journal-title":"Proc ICLR"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1126\/science.290.5500.2323"},{"key":"ref54","first-page":"1","article-title":"Infograph: Unsupervised and semi-supervised graph-level representation learning via mutual information maximization","author":"sun","year":"2020","journal-title":"Proc ICLR"},{"key":"ref51","article-title":"Janossy pooling: Learning deep permutation-invariant functions for variable-size inputs","author":"murphy","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref50","first-page":"6861","article-title":"Simplifying graph convolutional networks","volume":"97","author":"wu","year":"2019","journal-title":"Proc 36th Int Conf Mach Learn"},{"key":"ref46","first-page":"1","article-title":"Graph attention networks","author":"velickovic","year":"2018","journal-title":"Proc ICLR"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220068"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1137\/17M115222X"},{"key":"ref47","first-page":"5449","article-title":"Representation learning on graphs with jumping knowledge networks","volume":"80","author":"xu","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10851"},{"key":"ref41","first-page":"1024","article-title":"Inductive representation learning on large graphs","author":"hamilton","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref44","article-title":"Learning graph representations with recurrent neural network autoencoders","author":"taheri","year":"2018","journal-title":"Proc KDD Deep Learn Day"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11849"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2932096"},{"key":"ref8","first-page":"154","article-title":"Using the mutual k-nearest neighbor graphs for semi-supervised classification on natural language data","author":"ozaki","year":"2011","journal-title":"Proc CoNLL"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.12.130"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553432"},{"key":"ref4","article-title":"A survey on semi-supervised learning techniques","author":"prakash","year":"2014","journal-title":"arXiv 1402 4645"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CIS.2008.204"},{"key":"ref6","article-title":"An overview of deep semi-supervised learning","author":"ouali","year":"2020","journal-title":"arXiv 2006 05278"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-019-05855-6"},{"key":"ref100","first-page":"52","article-title":"Representation learning on graphs: Methods and applications","volume":"40","author":"hamilton","year":"2017","journal-title":"IEEE Data Eng Bulletin"},{"key":"ref101","volume":"34","author":"spitzer","year":"2013","journal-title":"Principles of Random Walk"},{"key":"ref40","first-page":"3391","article-title":"Deep sets","author":"zaheer","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10179"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939753"},{"key":"ref37","first-page":"1","article-title":"Gated graph sequence neural networks","author":"li","year":"2016","journal-title":"Proc ICLR"},{"key":"ref36","article-title":"Variational graph auto-encoders","author":"kipf","year":"2016","journal-title":"arXiv 1611 07308"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2736277.2741093"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00521"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2806416.2806512"},{"key":"ref149","first-page":"1","article-title":"Combining label propagation and simple models out-performs graph neural networks","author":"huang","year":"2021","journal-title":"Proc ICLR"},{"key":"ref33","first-page":"40","article-title":"Revisiting semi-supervised learning with graph embeddings","author":"yang","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref146","first-page":"12827","article-title":"Uncertainty aware semi-supervised learning on graph data","author":"zhao","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939751"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00981"},{"key":"ref39","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2017","journal-title":"Proc ICLR"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.11.053"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102726"},{"key":"ref156","first-page":"18648","article-title":"Variational inference for graph convolutional networks in the absence of graph data and adversarial settings","author":"elinas","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2019.03.005"},{"key":"ref154","first-page":"9777","article-title":"A unified framework for data poisoning attack to graph-based semi-supervised learning","author":"liu","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref151","first-page":"8713","article-title":"Graph agreement models for semi-supervised learning","author":"stretcu","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref152","first-page":"7015","article-title":"Graph-based semi-supervised learning with non-ignorable non-response","author":"zhou","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16586"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326716"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.60"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2014.428"},{"key":"ref25","first-page":"1","article-title":"Large graph construction for scalable semi-supervised learning","author":"liu","year":"2010","journal-title":"Proc ICML"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2488388.2488393"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-009-0305-8"},{"key":"ref157","first-page":"9263","article-title":"GNNGuard: Defending graph neural networks against adversarial attacks","author":"zhang","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143968"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623732"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/490\/1\/012022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2376936"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1126\/science.290.5500.2323"},{"key":"ref12","first-page":"1547","article-title":"Manifold-based similarity adaptation for label propagation","author":"karasuyama","year":"2013","journal-title":"Proc NIPS"},{"key":"ref15","first-page":"912","article-title":"Semi-supervised learning using Gaussian fields and harmonic functions","author":"zhu","year":"2003","journal-title":"Proc 20th Int Conf Mach Learn (ICML)"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5318"},{"key":"ref14","first-page":"585","article-title":"Laplacian eigenmaps and spectral techniques for embedding and clustering","author":"belkin","year":"2002","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1488"},{"key":"ref97","first-page":"46:1","article-title":"Distributed semi-supervised learning with kernel ridge regression","volume":"18","author":"chang","year":"2017","journal-title":"J Mach Learn Res"},{"key":"ref126","first-page":"167","article-title":"Efficient graph-based semi-supervised learning of structured tagging models","author":"subramanya","year":"2010","journal-title":"Proc EMNLP"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10218"},{"key":"ref127","first-page":"98","article-title":"Graph-based semi-supervised conditional random fields for spoken language understanding using unaligned data","author":"aliannejadi","year":"2014","journal-title":"Proc Australas Lang Technol Assoc Workshop"},{"key":"ref11","first-page":"2328","article-title":"Non-negative low rank and sparse graph for semi-supervised learning","author":"zhuang","year":"2012","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.116"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2018.08.008"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459267"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/400"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00989"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102482"},{"key":"ref16","first-page":"321","article-title":"Learning with local and global consistency","author":"zhou","year":"2003","journal-title":"Proc NIPS"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","article-title":"The graph neural network model","volume":"20","author":"scarselli","year":"2009","journal-title":"IEEE Trans Neural Netw"},{"key":"ref18","first-page":"2399","article-title":"Manifold regularization: A geometric framework for learning from labeled and unlabeled examples","volume":"7","author":"belkin","year":"2006","journal-title":"J Mach Learn Res"},{"key":"ref93","first-page":"2507","article-title":"When is there a representer theorem? Vector versus matrix regularizers","volume":"10","author":"argyriou","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-019-02948-w"},{"key":"ref92","doi-asserted-by":"crossref","first-page":"1033","DOI":"10.1109\/TNN.2010.2047114","article-title":"Discriminative semi-supervised feature selection via manifold regularization","volume":"21","author":"xu","year":"2010","journal-title":"IEEE Trans Neural Netw"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098094"},{"key":"ref95","first-page":"3129","article-title":"Large-scale SVD and manifold learning","volume":"14","author":"talwalkar","year":"2013","journal-title":"J Mach Learn Res"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v12i1.15047"},{"key":"ref94","first-page":"1229","article-title":"Manifold regularization and semi-supervised learning: Some theoretical analyses","volume":"14","author":"niyogi","year":"2013","journal-title":"J Mach Learn Res"},{"key":"ref132","first-page":"40","article-title":"Revisiting semi-supervised learning with graph embeddings","volume":"48","author":"yang","year":"2016","journal-title":"Proc 33rd Int Conf Int Conf Mach Learn"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1145\/1390334.1390438"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1201\/9780203492024"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2956015"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2727526"},{"key":"ref139","first-page":"784","article-title":"Efficient label propagation","volume":"32","author":"fujiwara","year":"2014","journal-title":"Proc ICML"},{"key":"ref86","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1109\/TSMCB.2010.2085433","article-title":"Semisupervised dimensionality reduction and classification through virtual label regression","volume":"41","author":"nie","year":"2011","journal-title":"IEEE Trans Syst Man Cybern B Cybern"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1016\/j.omtn.2019.04.010"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2013.182"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2009.5202789"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0031"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocx032"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2499311"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.03.003"},{"key":"ref82","article-title":"Learning from labeled and unlabeled data with label propagation","author":"zhu","year":"2002"},{"key":"ref144","first-page":"3281","article-title":"A flexible generative framework for graph-based semi-supervised learning","author":"ma","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref81","first-page":"1","article-title":"Consistency of semi-supervised learning algorithms on graphs: Probit and one-hot methods","volume":"21","author":"hoffmann","year":"2020","journal-title":"J Mach Learn Res"},{"key":"ref145","first-page":"1318","article-title":"Non parametric graph learning for Bayesian graph neural networks","author":"pal","year":"2020","journal-title":"Proc Conf Uncertainty Artif Intell"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2514360"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17206"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.90"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM50108.2020.00015"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/475"},{"key":"ref141","first-page":"2071","article-title":"Lightweight label propagation for large-scale network data","volume":"33","author":"li","year":"2021","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/s00245-019-09637-3"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0009"},{"key":"ref108","article-title":"Rethinking graph regularization for graph neural networks","author":"yang","year":"2020","journal-title":"arXiv 2009 02027"},{"key":"ref78","first-page":"132","article-title":"A regularization framework for learning from graph data","author":"zhou","year":"2004","journal-title":"Proc ICML Workshop Stat Relational Learn Connections Other Fields (SRL)"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.12.038"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159706"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11604"},{"key":"ref75","first-page":"67","article-title":"Combining graph Laplacians for semi-supervised learning","author":"argyriou","year":"2005","journal-title":"Proc NIPS"},{"key":"ref104","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102455"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939754"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2017.2654445"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1016\/j.socnet.2004.11.009"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2016.2535367"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2007.46"},{"key":"ref2","article-title":"Semi-supervised learning literature survey","author":"zhu","year":"1530"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01571-7"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2007.190672"},{"key":"ref111","first-page":"7113","article-title":"Constrained generation of semantically valid graphs via regularizing variational autoencoders","author":"ma","year":"2018","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_30"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326716"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.216"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132967"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2014.08.082"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108026"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2012.6252617"},{"key":"ref117","first-page":"1792","article-title":"Confidence-based graph convolutional networks for semi-supervised learning","volume":"89","author":"vashishth","year":"2019","journal-title":"Proc AISTATS"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.03.002"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401308"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40994-3_11"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01157"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015058"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186116"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2011.119"},{"key":"ref113","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3084694"},{"key":"ref114","first-page":"1263","article-title":"Neural message passing for quantum chemistry","volume":"70","author":"gilmer","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2011.09.001"},{"key":"ref122","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"arXiv 1412 3555"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.03.027"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2703120"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref61","first-page":"4343","article-title":"Graph construction for semi-supervised learning","author":"berton","year":"2015","journal-title":"Proc 24th Int Joint Conf Artif Intell"},{"key":"ref121","first-page":"1","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc ICLR"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10299535\/09737635.pdf?arnumber=9737635","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:26:36Z","timestamp":1699903596000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9737635\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11]]},"references-count":157,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3155478","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11]]}}}