{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T09:46:19Z","timestamp":1785577579134,"version":"3.56.0"},"reference-count":90,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2023,4,1]]},"DOI":"10.1109\/tkde.2021.3131584","type":"journal-article","created":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T20:38:07Z","timestamp":1638391087000},"page":"4216-4235","source":"Crossref","is-referenced-by-count":212,"title":["Self-Supervised Learning on Graphs: Contrastive, Generative, or Predictive"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5551-3194","authenticated-orcid":false,"given":"Lirong","family":"Wu","sequence":"first","affiliation":[{"name":"AI Lab, School of Engineering, Westlake University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6379-6590","authenticated-orcid":false,"given":"Haitao","family":"Lin","sequence":"additional","affiliation":[{"name":"AI Lab, School of Engineering, Westlake University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8639-923X","authenticated-orcid":false,"given":"Cheng","family":"Tan","sequence":"additional","affiliation":[{"name":"AI Lab, School of Engineering, Westlake University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhangyang","family":"Gao","sequence":"additional","affiliation":[{"name":"AI Lab, School of Engineering, Westlake University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2961-8096","authenticated-orcid":false,"given":"Stan Z.","family":"Li","sequence":"additional","affiliation":[{"name":"AI Lab, School of Engineering, Westlake University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3090866"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref3","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref4","article-title":"Bootstrap your own latent: A new approach to self-supervised learning","author":"Grill","year":"2020"},{"key":"ref5","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"issue":"8","key":"ref6","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref7","article-title":"Albert: A lite bert for self-supervised learning of language representations","author":"Lan","year":"2019"},{"key":"ref8","article-title":"Inductive representation learning on large graphs","author":"Hamilton","year":"2017"},{"key":"ref9","article-title":"Deep graph infomax","volume-title":"Proc. ICLR","author":"Velickovic"},{"key":"ref10","article-title":"Self-supervised learning on graphs: Deep insights and new direction","author":"Jin","year":"2020"},{"key":"ref11","article-title":"Strategies for pre-training graph neural networks","author":"Hu","year":"2019"},{"key":"ref12","first-page":"10 871","article-title":"When does self-supervision help graph convolutional networks?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"You"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.04.021"},{"key":"ref14","article-title":"Self-supervised training of graph convolutional networks","author":"Zhu","year":"2020"},{"key":"ref15","article-title":"Graph-bert: Only attention is needed for learning graph representations","author":"Zhang","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380112"},{"key":"ref17","article-title":"Pre-training graph neural networks for generic structural feature extraction","author":"Hu","year":"2019"},{"key":"ref18","first-page":"4116","article-title":"Contrastive multi-view representation learning on graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hassani"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM50108.2020.00031"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3170559"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3172903"},{"key":"ref22","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"key":"ref23","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref25","first-page":"12121","article-title":"Graph contrastive learning with augmentations","volume-title":"in Proc. Adv. Neural Inf. Process. Syst.","author":"You"},{"key":"ref26","article-title":"Deep graph contrastive representation learning","author":"Zhu","year":"2020"},{"key":"ref27","article-title":"Bootstrapped representation learning on graphs","author":"Thakoor","year":"2021"},{"key":"ref28","article-title":"Spatio-temporal deep graph infomax","author":"Opolka","year":"2019"},{"key":"ref29","article-title":"Improving graph representation learning by contrastive regularization","author":"Ma","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449971"},{"key":"ref31","article-title":"Heterogeneous deep graph infomax","author":"Ren","year":"2019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403237"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3303885"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17293"},{"key":"ref35","article-title":"Self-supervised graph neural networks without explicit negative sampling","author":"Kefato","year":"2021"},{"key":"ref36","article-title":"Transfer learning of graph neural networks with ego-graph information maximization","author":"Zhu","year":"2020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441783"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403168"},{"key":"ref39","article-title":"Motif-driven contrastive learning of graph representations","author":"Zhang","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449802"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1086\/228631"},{"key":"ref42","first-page":"1999","article-title":"The pagerank citation ranking: Bringing order to the web","volume-title":"Tech. Rep.","author":"Page","year":"1999"},{"key":"ref43","article-title":"Towards robust graph contrastive learning","author":"Jovanovi\u0107","year":"2021"},{"key":"ref44","article-title":"Variational graph auto-encoders","author":"Kipf","year":"2016"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-73194-6_10"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467340"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467415"},{"key":"ref48","article-title":"Graph infoclust: Leveraging cluster-level node information for unsupervised graph representation learning","author":"Mavromatis","year":"2020"},{"key":"ref49","article-title":"Infograph: Unsupervised and semi-supervised graph-level representation learning via mutual information maximization","author":"Sun","year":"2019"},{"key":"ref50","first-page":"531","article-title":"Mutual information neural estimation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Belghazi"},{"key":"ref51","article-title":"f-GAN: Training generative neural samplers using variational divergence minimization","author":"Nowozin","year":"2016"},{"key":"ref52","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","volume-title":"Proc. Int. Conf. Artif. Intell. Stat","author":"Gutmann"},{"key":"ref53","first-page":"1857","article-title":"Improved deep metric learning with multi-class N-pair loss objective","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sohn"},{"key":"ref54","article-title":"On mutual information maximization for representation learning","author":"Tschannen","year":"2019"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.145"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01437"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"ref59","article-title":"Self-supervised graph representation learning via global context prediction","author":"Peng","year":"2020"},{"key":"ref60","first-page":"281","article-title":"Some methods for classification and analysis of multivariate observations","volume-title":"Proc. Berkeley Symp. Math. Stat. Probability","author":"Macqueen"},{"key":"ref61","article-title":"Clustering based on graph of density topology","author":"Gao","year":"2020"},{"key":"ref62","article-title":"Deep clustering and representation learning that preserves geometric structures","author":"Wu","year":"2020"},{"key":"ref63","article-title":"Consistent representation learning for high dimensional data analysis","author":"Li","year":"2020"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00419"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.556"},{"key":"ref66","first-page":"478","article-title":"Unsupervised deep embedding for clustering analysis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xie"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9413131"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref69","article-title":"Self-supervised auxiliary learning with meta-paths for heterogeneous graphs","author":"Hwang","year":"2020"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450060"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11604"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/2008\/10\/P10008"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-41695-z"},{"key":"ref74","article-title":"CAGNN: Cluster-aware graph neural networks for unsupervised graph representation learning","author":"Zhu","year":"2020"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6048"},{"key":"ref76","article-title":"Self-supervised graph transformer on large-scale molecular data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rong"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783417"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1016\/S0022-2836(03)00628-4"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btx252"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5985"},{"key":"ref81","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","author":"Zbontar","year":"2021"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441738"},{"key":"ref83","article-title":"Self-supervised smoothing graph neural networks","author":"Yu","year":"2020"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449822"},{"key":"ref85","article-title":"Debiased contrastive learning","volume-title":"in Proc. Adv. Neural Inf. Process. Syst.","author":"Chuang"},{"key":"ref86","article-title":"Hard negative mixing for contrastive learning","author":"Kalantidis","year":"2020"},{"key":"ref87","article-title":"Contrastive learning with hard negative samples","author":"Robinson","year":"2020"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/825"},{"key":"ref89","article-title":"Pre-training on dynamic graph neural networks","author":"Zhang","year":"2021"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3004555"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/69\/10063074\/09632431.pdf?arnumber=9632431","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T19:53:57Z","timestamp":1709322837000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9632431\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,1]]},"references-count":90,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2021.3131584","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,1]]}}}