{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:35:06Z","timestamp":1777613706127,"version":"3.51.4"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF","award":["IIS1955532"],"award-info":[{"award-number":["IIS1955532"]}]},{"name":"NSF","award":["HM04762010002"],"award-info":[{"award-number":["HM04762010002"]}]},{"name":"NIH","award":["R01GM140467"],"award-info":[{"award-number":["R01GM140467"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1109\/tkde.2023.3303885","type":"journal-article","created":{"date-parts":[[2023,8,14]],"date-time":"2023-08-14T18:00:02Z","timestamp":1692036002000},"page":"1161-1169","source":"Crossref","is-referenced-by-count":6,"title":["Iterative Graph Self-Distillation"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9292-1645","authenticated-orcid":false,"given":"Hanlin","family":"Zhang","sequence":"first","affiliation":[{"name":"Machine Learning Department, Carnegie Mellong University, Pittsburgh, PA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7078-8257","authenticated-orcid":false,"given":"Shuai","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Intelligent Systems Engineering, Sun Yat-Sen University, Guangzhou, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8234-3263","authenticated-orcid":false,"given":"Weiyang","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Cambridge, Cambridge, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3400-8943","authenticated-orcid":false,"given":"Pan","family":"Zhou","sequence":"additional","affiliation":[{"name":"SEA AI Lab, SEA Group Ltd., Singapore"}]},{"given":"Jian","family":"Tang","sequence":"additional","affiliation":[{"name":"HEC Montreal, Montréal, QC, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3213-3062","authenticated-orcid":false,"given":"Xiaodan","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Intelligent Systems Engineering, Sun Yat-Sen University, Guangzhou, Guangdong, China"}]},{"given":"Eric P.","family":"Xing","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.69.026113"},{"key":"ref2","first-page":"2224","article-title":"Convolutional networks on graphs for learning molecular fingerprints","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Duvenaud"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(20)30192-8"},{"key":"ref4","first-page":"1263","article-title":"Neural message passing for quantum chemistry","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gilmer"},{"key":"ref5","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kipf"},{"key":"ref6","article-title":"How powerful are graph neural networks?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xu"},{"issue":"9","key":"ref7","first-page":"2539","article-title":"Weisfeiler-Lehman graph kernels","volume":"12","author":"Shervashidze","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1120.003.0080"},{"key":"ref9","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00975"},{"key":"ref11","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref12","article-title":"Learning deep representations by mutual information estimation and maximization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hjelm"},{"key":"ref13","article-title":"Strategies for pre-training graph neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu"},{"key":"ref14","first-page":"10 871","article-title":"When does self-supervision help graph convolutional networks?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"You"},{"key":"ref15","article-title":"Deep graph infomax","author":"Veli\u010dkovi\u0107","year":"2018"},{"key":"ref16","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":"ref17","first-page":"3451","article-title":"Contrastive multi-view representation learning on graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hassani"},{"key":"ref18","article-title":"On mutual information maximization for representation learning","author":"Tschannen","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2005.132"},{"key":"ref21","first-page":"2990","article-title":"The multiscale Laplacian graph kernel","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kondor"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2014.22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3090866"},{"key":"ref24","first-page":"4116","article-title":"Contrastive multi-view representation learning on graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hassani"},{"key":"ref25","first-page":"8765","article-title":"Debiased contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Chuang"},{"key":"ref26","first-page":"21 271","article-title":"Bootstrap your own latent - a new approach to self-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Grill"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109631"},{"key":"ref28","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Khosla"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403168"},{"key":"ref30","first-page":"5812","article-title":"Graph contrastive learning with augmentations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"You"},{"key":"ref31","article-title":"Large-scale representation learning on graphs via bootstrapping","author":"Thakoor","year":"2021"},{"key":"ref32","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref33","first-page":"1607","article-title":"Born again neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Furlanello"},{"key":"ref34","article-title":"Self-distillation amplifies regularization in Hilbert space","author":"Mobahi","year":"2020"},{"key":"ref35","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tarvainen"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2018.2858821"},{"issue":"2","key":"ref37","first-page":"896","article-title":"Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks","volume-title":"Proc. Workshop Challenges Representation Learn.","volume":"3","author":"Lee"},{"key":"ref38","article-title":"There are many consistent explanations of unlabeled data: Why you should average","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Athiwaratkun"},{"key":"ref39","first-page":"22 243","article-title":"Big self-supervised models are strong semi-supervised learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17315"},{"key":"ref41","first-page":"13 354","article-title":"Diffusion improves graph learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Klicpera"},{"key":"ref42","first-page":"1024","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hamilton"},{"key":"ref43","article-title":"Order matters: Sequence to sequence for sets","author":"Vinyals","year":"2015"},{"key":"ref44","first-page":"10 268","article-title":"Understanding self-supervised learning dynamics without contrastive pairs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tian"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref46","first-page":"24 794","article-title":"The mechanism of prediction head in non-contrastive self-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wen"},{"key":"ref47","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref48","article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref49","first-page":"6438","article-title":"Manifold mixup: Better representations by interpolating hidden states","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Verma"},{"key":"ref50","first-page":"5049","article-title":"MixMatch: A holistic approach to semi-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Berthelot"},{"key":"ref51","first-page":"3235","article-title":"Realistic evaluation of deep semi-supervised learning algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Oliver"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ACVMOT.2005.107"},{"key":"ref53","article-title":"Benchmark data sets for graph kernels","author":"Kersting","year":"2016"},{"key":"ref54","article-title":"graph2vec: Learning distributed representations of graphs","author":"Narayanan","year":"2017"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-45167-9_11"},{"key":"ref56","first-page":"321","article-title":"Marginalized kernels between labeled graphs","volume-title":"Proc. 20th Int. Conf. Mach. Learn.","author":"Kashima"},{"key":"ref57","first-page":"488","article-title":"Efficient graphlet kernels for large graph comparison","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Shervashidze"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783417"},{"key":"ref59","first-page":"1576","article-title":"Convolutional kernel networks for graph-structured data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/69\/10422839\/10216383-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/69\/10422839\/10216383.pdf?arnumber=10216383","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,12]],"date-time":"2024-02-12T19:52:03Z","timestamp":1707767523000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10216383\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3]]},"references-count":60,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2023.3303885","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":[[2024,3]]}}}