{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T17:09:39Z","timestamp":1776100179089,"version":"3.50.1"},"reference-count":128,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-2006861"],"award-info":[{"award-number":["IIS-2006861"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DBI-2028361"],"award-info":[{"award-number":["DBI-2028361"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["1R21NS102828"],"award-info":[{"award-number":["1R21NS102828"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,2,1]]},"DOI":"10.1109\/tpami.2022.3170559","type":"journal-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:49:11Z","timestamp":1651088951000},"page":"2412-2429","source":"Crossref","is-referenced-by-count":266,"title":["Self-Supervised Learning of Graph Neural Networks: A Unified Review"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0320-6728","authenticated-orcid":false,"given":"Yaochen","family":"Xie","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Texas A&M University, College Station, TX, USA"}]},{"given":"Zhao","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Texas A&M University, College Station, TX, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0436-8972","authenticated-orcid":false,"given":"Jingtun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Texas A&M University, College Station, TX, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5146-2884","authenticated-orcid":false,"given":"Zhengyang","family":"Wang","sequence":"additional","affiliation":[{"name":"Amazon.com Services LLC, Seattle, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4205-4563","authenticated-orcid":false,"given":"Shuiwang","family":"Ji","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Texas A&M University, College Station, TX, USA"}]}],"member":"263","reference":[{"key":"ref1","first-page":"19290","article-title":"Rethinking the value of labels for improving class-imbalanced learning","volume-title":"Proc. 34th Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00984"},{"key":"ref3","first-page":"20320","article-title":"Noise2Same: Optimizing a self-supervised bound for image denoising","volume-title":"Proc. 34th Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Xie","year":"2020"},{"key":"ref4","first-page":"6970","article-title":"High-quality self-supervised deep image denoising","volume":"32","author":"Laine","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00223"},{"key":"ref6","first-page":"524","article-title":"Noise2Self: Blind denoising by self-supervision","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Batson"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1375"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1214"},{"key":"ref10","first-page":"4116","article-title":"Contrastive multi-view representation learning on graphs","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Hassani"},{"key":"ref11","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref12","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623732"},{"key":"ref15","article-title":"graph2vec: Learning distributed representations of graphs","author":"Narayanan","year":"2017"},{"key":"ref16","article-title":"SGR: Self-supervised spectral graph representation learning","author":"Tsitsulin","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref20","first-page":"21271","article-title":"Bootstrap your own latent - a new approach to self-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Grill"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1039\/C7SC02664A"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btac112"},{"key":"ref23","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kipf"},{"key":"ref24","article-title":"How powerful are graph neural networks?","author":"Xu","year":"2019","journal-title":"Int. Conf. Learn. Representations"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3081010"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3134200"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3080635"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403076"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5731"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219947"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313395"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3062794"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2999032"},{"key":"ref34","article-title":"StructPool: Structured graph pooling via conditional random fields","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Yuan"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330897"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403085"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403110"},{"key":"ref38","article-title":"Deep graph infomax","author":"Veli\u010dkovi\u0107","year":"2019","journal-title":"Int. Conf. Learn. Representations"},{"key":"ref39","article-title":"Variational graph auto-encoders","author":"Kipf","year":"2016"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1017\/9781108924184"},{"key":"ref41","article-title":"Infograph: Unsupervised and semi-supervised graph-level representation learning via mutual information maximization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sun"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380112"},{"key":"ref43","article-title":"Strategies for pre-training graph neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM50108.2020.00031"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449802"},{"key":"ref46","article-title":"Deep graph contrastive representation learning","volume-title":"Proc. ICML Workshop Graph Representation Learn. Beyond","author":"Zhu"},{"key":"ref47","article-title":"Large-scale representation learning on graphs via bootstrapping","author":"Thakoor","year":"2021"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403168"},{"key":"ref49","first-page":"5812","article-title":"Graph contrastive learning with augmentations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"You"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132967"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00662"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/362"},{"key":"ref53","first-page":"10 712","article-title":"Semi-implicit graph variational auto-encoders","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hasanzadeh"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403237"},{"key":"ref55","article-title":"Self-supervised graph representation learning via global context prediction","author":"Peng","year":"2020"},{"key":"ref56","first-page":"12559","article-title":"Self-supervised graph transformer on large-scale molecular data","volume-title":"Proc. 34th Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Rong"},{"key":"ref57","article-title":"Self-supervised auxiliary learning with meta-paths for heterogeneous graphs","author":"Hwang","year":"2020"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6048"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482469"},{"key":"ref60","first-page":"76","article-title":"From canonical correlation analysis to self-supervised graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref61","article-title":"Self-supervised representation learning via latent graph prediction","author":"Xie","year":"2022"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3090866"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3172903"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462944"},{"key":"ref65","article-title":"Self-supervised learning on graphs: Deep insights and new direction","author":"Jin","year":"2020"},{"key":"ref66","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ganin"},{"key":"ref67","article-title":"Unsupervised domain adaptation through self-supervision","author":"Sun","year":"2019"},{"key":"ref68","article-title":"Learning deep representations by mutual information estimation and maximization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hjelm"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.3160360204"},{"key":"ref70","first-page":"531","article-title":"Mutual information neural estimation","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Belghazi"},{"key":"ref71","first-page":"271","article-title":"f-GAN: Training generative neural samplers using variational divergence minimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Nowozin"},{"key":"ref72","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist.","author":"Gutmann"},{"key":"ref73","first-page":"1857","article-title":"Improved deep metric learning with multi-class n-pair loss objective","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sohn","year":"2016"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24261-3_7"},{"key":"ref76","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Khosla"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1205.2618"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467396"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467415"},{"key":"ref80","article-title":"What makes for good views for contrastive learning?","author":"Tian","year":"2020"},{"key":"ref81","first-page":"15920","article-title":"Adversarial graph augmentation to improve graph contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Suresh"},{"key":"ref82","first-page":"30414","article-title":"InfoGCL: Information-aware graph contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref83","article-title":"Theoretical analysis of self-training with deep networks on unlabeled data","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wei"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1002\/aic.690370209"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.2200\/s01045ed1v01y202009aim046"},{"key":"ref86","first-page":"1024","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hamilton"},{"key":"ref87","article-title":"How to find your friendly neighborhood: Graph attention design with self-supervision","author":"Kim","year":"2021","journal-title":"Int. Conf. Learn. Representations"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441735"},{"issue":"12","key":"ref89","first-page":"3371","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion.","volume":"11","author":"Vincent","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/218380.218473"},{"key":"ref91","first-page":"10871","article-title":"When does self-supervision help graph convolutional networks?","author":"You","year":"2020","journal-title":"Proc. Int. Conf. Mach. Learn."},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.3156\/jsoft.29.5_177_2"},{"key":"ref93","first-page":"2323","article-title":"Junction tree variational autoencoder for molecular graph generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jin"},{"key":"ref94","first-page":"5274","article-title":"Dirichlet graph variational autoencoder","volume-title":"Proc. 34th Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Li"},{"issue":"8","key":"ref95","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4380-9_14"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1162\/0899766042321814"},{"key":"ref98","first-page":"12310","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zbontar"},{"key":"ref99","first-page":"368","article-title":"The information bottleneck method","volume-title":"Proc. 37th Annu. Allerton Conf. Commun.","author":"Tishby"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11604"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref102","article-title":"Tudataset: A collection of benchmark datasets for learning with graphs","volume-title":"Proc. ICML Workshop Graph Representation Learn. Beyond","author":"Morris"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2006.39"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1021\/jm00106a046"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.5b00559"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bti1007"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1016\/S0022-2836(03)00628-4"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783417"},{"key":"ref109","first-page":"40","article-title":"Revisiting semi-supervised learning with graph embeddings","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang"},{"issue":"2","key":"ref110","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1023\/A:1009953814988","article-title":"Automating the construction of internet portals with machine learning","volume":"3","author":"McCallum","year":"2000","journal-title":"Inf. Retrieval"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1145\/276675.276685"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v29i3.2157"},{"key":"ref113","article-title":"Pitfalls of graph neural network evaluation","author":"Shchur","year":"2018"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1145\/2740908.2742839"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767755"},{"key":"ref116","article-title":"GraphSAINT: Graph sampling based inductive learning method","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zeng"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btx252"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1818013116"},{"issue":"240","key":"ref119","first-page":"1","article-title":"DIG: A turnkey library for diving into graph deep learning research","volume":"22","author":"Liu","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref121","article-title":"Fast graph representation learning with PyTorch geometric","volume-title":"Proc. ICLR Workshop Representation Learn. Graphs Manifolds","author":"Fey"},{"key":"ref122","first-page":"5708","article-title":"GraphRNN: Generating realistic graphs with deep auto-regressive models","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"You"},{"key":"ref123","article-title":"Graphaf: A flow-based autoregressive model for molecular graph generation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shi"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403104"},{"key":"ref125","first-page":"7192","article-title":"Graphdf: A discrete flow model for molecular graph generation","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Luo"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/371"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3204236"},{"key":"ref128","article-title":"Task-agnostic graph explanations","author":"Xie","year":"2022"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/34\/10008914\/9764632-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10008914\/09764632.pdf?arnumber=9764632","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T22:42:07Z","timestamp":1705963327000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9764632\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,1]]},"references-count":128,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3170559","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,1]]}}}