{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T11:27:17Z","timestamp":1776338837676,"version":"3.51.2"},"reference-count":154,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tkde.2021.3090866","type":"journal-article","created":{"date-parts":[[2021,6,22]],"date-time":"2021-06-22T20:09:51Z","timestamp":1624392591000},"page":"1-1","source":"Crossref","is-referenced-by-count":974,"title":["Self-supervised Learning: Generative or Contrastive"],"prefix":"10.1109","author":[{"given":"Xiao","family":"Liu","sequence":"first","affiliation":[]},{"given":"Fanjin","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Zhenyu","family":"Hou","sequence":"additional","affiliation":[]},{"given":"Li","family":"Mian","sequence":"additional","affiliation":[]},{"given":"Zhaoyu","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Tang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref38","article-title":"Unsupervised representation learning by predicting image rotations","author":"gidaris","year":"2018"},{"key":"ref33","article-title":"Adversarial feature learning","author":"donahue","year":"2016"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref31","article-title":"Density estimation using real NVP","author":"dinh","year":"2016"},{"key":"ref30","article-title":"Nice: Non-linear independent components estimation","author":"dinh","year":"2014"},{"key":"ref37","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"ganin","year":"2016","journal-title":"Journal of Machine Learning Research"},{"key":"ref36","article-title":"Adversarially learned inference","author":"dumoulin","year":"2016"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220025"},{"key":"ref34","first-page":"10541","article-title":"Large scale adversarial representation learning","author":"donahue","year":"2019","journal-title":"Proc 33rd Int Conf Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271768"},{"key":"ref27","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1259"},{"key":"ref20","first-page":"4088","article-title":"Triple generative adversarial nets","author":"chongxuan","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref22","article-title":"Word translation without parallel data","author":"conneau","year":"2017"},{"key":"ref21","article-title":"ELECTRA: Pre-training text encoders as discriminators rather than generators","author":"clark","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11865"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref101","first-page":"14837","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","author":"razavi","year":"2019","journal-title":"Proc 33rd Int Conf Neural Inf Process Syst"},{"key":"ref25","first-page":"112","article-title":"Learning classification with unlabeled data","author":"de sa","year":"1994","journal-title":"Proc 6th Int Conf Neural Inf Process"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref50","first-page":"2722","article-title":"Flow++: Improving flow-based generative models with variational dequantization and architecture design","author":"ho","year":"2019","journal-title":"Proc 36th Int Conf Mach Learn"},{"key":"ref51","article-title":"Strategies for pre-training graph neural networks","author":"hu","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref154","article-title":"Neural architecture search with reinforcement learning","author":"zoph","year":"2016"},{"key":"ref153","article-title":"Rethinking pre-training and self-training","author":"zoph","year":"2020"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220052"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00610"},{"key":"ref151","first-page":"465","article-title":"Toward multimodal image-to-image translation","author":"zhu","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11782"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.76"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1139"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00300"},{"key":"ref57","article-title":"Self-supervised visual feature learning with deep neural networks: A survey","author":"jing","year":"2019"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref55","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3072959.3073659","article-title":"Globally and locally consistent image completion","volume":"36","author":"iizuka","year":"2017","journal-title":"ACM Trans Graph"},{"key":"ref54","first-page":"2261","article-title":"Densely connected convolutional networks","author":"huang","year":"2017","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380027"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403237"},{"key":"ref40","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref4","article-title":"A theoretical analysis of contrastive unsupervised representation learning","author":"arora","year":"2019"},{"key":"ref3","first-page":"214","article-title":"Wasserstein generative adversarial networks","author":"arjovsky","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref6","first-page":"15509","article-title":"Learning representations by maximizing mutual information across views","author":"bachman","year":"2019","journal-title":"Proc 33rd Int Conf Neural Inf Process Syst"},{"key":"ref5","article-title":"Learning to retrieve reasoning paths over wikipedia graph for question answering","author":"asai","year":"2019"},{"key":"ref8","first-page":"279","article-title":"Modular learning in neural networks","author":"ballard","year":"1987","journal-title":"Proc 6th Nat Conf Artif Intell"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290967"},{"key":"ref49","article-title":"Learning deep representations by mutual information estimation and maximization","author":"hjelm","year":"2018"},{"key":"ref9","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"bengio","year":"2013"},{"key":"ref46","article-title":"Contrastive multi-view representation learning on graphs","author":"hassani","year":"2020"},{"key":"ref45","article-title":"REALM: Retrieval-augmented language model pre-training","author":"guu","year":"2020"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref47","article-title":"Momentum contrast for unsupervised visual representation learning","author":"he","year":"2019"},{"key":"ref42","article-title":"Bootstrap your own latent: A new approach to self-supervised learning","author":"grill","year":"2020"},{"key":"ref41","article-title":"Self-supervised pretraining of visual features in the wild","author":"goyal","year":"2021"},{"key":"ref44","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","author":"gutmann","year":"2010","journal-title":"Proc 13th Int Conf Artif Intell Statist"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939754"},{"key":"ref127","article-title":"Deep graph infomax","author":"veli?kovi?","year":"2018"},{"key":"ref126","article-title":"Graph attention networks","author":"veli?kovi?","year":"2017"},{"key":"ref125","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref124","first-page":"1747","article-title":"Pixel recurrent neural networks","author":"van oord","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_41"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11536"},{"key":"ref71","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nat"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11872"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.96"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref130","article-title":"Generative adversarial networks: A survey and taxonomy","author":"wang","year":"2019"},{"key":"ref77","article-title":"Adversarial autoencoders","author":"makhzani","year":"2015"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-02145-9"},{"key":"ref75","article-title":"RoBERTa: A robustly optimized bert pretraining approach","author":"liu","year":"2019"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"ref134","article-title":"Pretrained encyclopedia: Weakly supervised knowledge-pretrained language model","author":"xiong","year":"2019"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00201"},{"key":"ref78","article-title":"Masked autoencoder for distribution estimation","author":"mathieu","year":"2015"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref79","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013","journal-title":"CoRR"},{"key":"ref136","article-title":"ClusterFit: Improving generalization of visual representations","author":"yan","year":"2019"},{"key":"ref135","article-title":"How neural networks extrapolate: From feedforward to graph neural networks","author":"xu","year":"2020"},{"key":"ref138","first-page":"5754","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","author":"yang","year":"2019","journal-title":"Proc 33rd Int Conf Neural Inf Process Syst"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.556"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1259"},{"key":"ref62","first-page":"10215","article-title":"Glow: Generative flow with invertible 1x1 convolutions","author":"kingma","year":"2018","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00092"},{"key":"ref63","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2013"},{"key":"ref64","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2016"},{"key":"ref140","first-page":"6410","article-title":"Graph convolutional policy network for goal-directed molecular graph generation","author":"you","year":"2018","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref65","article-title":"Variational graph auto-encoders","author":"kipf","year":"2016"},{"key":"ref141","first-page":"5708","article-title":"GraphRNN: Generating realistic graphs with deep auto-regressive models","author":"you","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref66","article-title":"A mutual information maximization perspective of language representation learning","author":"kong","year":"2019"},{"key":"ref142","article-title":"Graph contrastive learning with augmentations","author":"you","year":"2020"},{"key":"ref67","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc 25th Int Conf Neural Inf Process Syst"},{"key":"ref143","article-title":"When does self-supervision help graph convolutional networks?","author":"you","year":"2020"},{"key":"ref68","article-title":"ALBERT: A lite bert for self-supervised learning of language representations","author":"lan","year":"2019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1099"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330785"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_35"},{"key":"ref1","article-title":"Domain-adversarial neural networks","author":"ajakan","year":"2014"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/594"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220077"},{"key":"ref109","article-title":"Information processing in dynamical systems: Foundations of harmony theory","author":"smolensky","year":"1986"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403168"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1145\/2740908.2742839"},{"key":"ref93","article-title":"MolecularRNN: Generating realistic molecular graphs with optimized properties","author":"popova","year":"2019"},{"key":"ref107","article-title":"GraphAF: A flow-based autoregressive model for molecular graph generation","author":"shi","year":"2020"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623732"},{"key":"ref106","first-page":"6830","article-title":"Style transfer from non-parallel text by cross-alignment","author":"shen","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref91","article-title":"Self-supervised graph representation learning via global context prediction","author":"peng","year":"2020"},{"key":"ref105","article-title":"Adversarial representation learning for domain adaptation","volume":"1050","author":"shen","year":"2017","journal-title":"Stat"},{"key":"ref90","article-title":"Self-supervised graph representation learning via global context prediction","author":"peng","year":"2020"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00591"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098061"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref111","first-page":"512","article-title":"vGraph: A generative model for joint community detection and node representation learning","author":"sun","year":"2019","journal-title":"Proc 33rd Int Conf Neural Inf Process Syst"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6048"},{"key":"ref110","article-title":"InfoGraph: Unsupervised and semi-supervised graph-level representation learning via mutual information maximization","author":"sun","year":"2019"},{"key":"ref98","article-title":"Improving language understanding by generative pre-training","author":"radford","year":"0"},{"key":"ref99","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/s11431-020-1647-3"},{"key":"ref97","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"radford","year":"2015"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"ref11","article-title":"Large scale GAN training for high fidelity natural image synthesis","author":"brock","year":"2018"},{"key":"ref12","article-title":"KBGAN: Adversarial learning for knowledge graph embeddings","author":"cai","year":"2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref14","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","author":"caron","year":"2020"},{"key":"ref15","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020"},{"key":"ref118","article-title":"Contrastive multiview coding","author":"tian","year":"2019"},{"key":"ref16","article-title":"Big self-supervised models are strong semi-supervised learners","author":"chen","year":"2020"},{"key":"ref82","article-title":"Representation learning via invariant causal mechanisms","author":"mitrovic","year":"2020"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1177\/107769905303000401"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098202"},{"key":"ref81","article-title":"Self-supervised learning of pretext-invariant representations","author":"misra","year":"2019"},{"key":"ref18","article-title":"Improved baselines with momentum contrastive learning","author":"chen","year":"2020"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00737"},{"key":"ref119","article-title":"What makes for good views for contrastive learning","author":"tian","year":"2020"},{"key":"ref19","article-title":"Exploring simple siamese representation learning","author":"chen","year":"2020"},{"key":"ref83","article-title":"Spectral normalization for generative adversarial networks","author":"miyato","year":"2018"},{"key":"ref114","article-title":"ERNIE: Enhanced representation through knowledge integration","author":"sun","year":"2019"},{"key":"ref113","article-title":"Multi-stage self-supervised learning for graph convolutional networks","author":"sun","year":"2019"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1145\/1401890.1402008"},{"key":"ref80","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Proc 26th Int Conf Neural Inf Process Syst"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1145\/2736277.2741093"},{"key":"ref120","article-title":"On mutual information maximization for representation learning","author":"tschannen","year":"2019"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref121","first-page":"125","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"Proc 9th ISCA Speech Synth Workshop"},{"key":"ref122","first-page":"4790","article-title":"Conditional image generation with pixelcnn decoders","author":"van den oord","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref123","first-page":"6306","article-title":"Neural discrete representation learning","author":"van den oord","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref85","first-page":"1","article-title":"Sparse autoencoder","volume":"72","author":"ng","year":"2011","journal-title":"Cs294a lecture notes"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00975"},{"key":"ref88","article-title":"Representation learning with contrastive predictive coding","author":"oord","year":"2018"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/69\/4358933\/09462394.pdf?arnumber=9462394","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,8]],"date-time":"2022-12-08T15:19:21Z","timestamp":1670512761000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9462394\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":154,"URL":"https:\/\/doi.org\/10.1109\/tkde.2021.3090866","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":[[2021]]}}}