{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T16:53:14Z","timestamp":1769273594734,"version":"3.49.0"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Centre for Frontier AI Research"},{"name":"Maritime AI Research Programme of Singapore","award":["SMI-2022-MTP-06"],"award-info":[{"award-number":["SMI-2022-MTP-06"]}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["FT220100391"],"award-info":[{"award-number":["FT220100391"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP210101348"],"award-info":[{"award-number":["DP210101348"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001348","name":"Agency for Science, Technology and Research","doi-asserted-by":"publisher","award":["C222812019"],"award-info":[{"award-number":["C222812019"]}],"id":[{"id":"10.13039\/501100001348","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":[[2023,10]]},"DOI":"10.1109\/tpami.2023.3273249","type":"journal-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:31:35Z","timestamp":1683307895000},"page":"11753-11765","source":"Crossref","is-referenced-by-count":3,"title":["Earning Extra Performance From Restrictive Feedbacks"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7584-1240","authenticated-orcid":false,"given":"Jing","family":"Li","sequence":"first","affiliation":[{"name":"Center for Frontier AI Research, Agency for Science, Technology and Research (A* A*STAR), Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7950-4900","authenticated-orcid":false,"given":"Yuangang","family":"Pan","sequence":"additional","affiliation":[{"name":"Center for Frontier AI Research, Agency for Science, Technology and Research (A* A*STAR), Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8394-2121","authenticated-orcid":false,"given":"Yueming","family":"Lyu","sequence":"additional","affiliation":[{"name":"Center for Frontier AI Research, Agency for Science, Technology and Research (A* A*STAR), Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3204-0739","authenticated-orcid":false,"given":"Yinghua","family":"Yao","sequence":"additional","affiliation":[{"name":"Australian Artificial Intelligence Institute, University of Technology Sydney, Ultimo, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9510-6574","authenticated-orcid":false,"given":"Yulei","family":"Sui","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of New South Wales, Sydney, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2211-8176","authenticated-orcid":false,"given":"Ivor W.","family":"Tsang","sequence":"additional","affiliation":[{"name":"Center for Frontier AI Research, Agency for Science, Technology and Research (A* A*STAR), Singapore"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11257-011-9118-4"},{"key":"ref57","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2987550.2987558"},{"key":"ref56","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"1999","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","first-page":"9229","article-title":"Test-time training with self-supervision for generalization under distribution shifts","author":"sun","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref59","article-title":"Bayesian optimization is superior to random search for machine learning hyperparameter tuning: Analysis of the black-box optimization challenge 2020","author":"turner","year":"2021"},{"key":"ref14","first-page":"949","article-title":"Natural evolution strategies","volume":"15","author":"wierstra","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1111\/itor.12292"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.463"},{"key":"ref52","author":"qui\u00f1onero-candela","year":"2009","journal-title":"Dataset Shift in Machine Learning"},{"key":"ref11","first-page":"1877","article-title":"Language models are few-shot learners","author":"brown","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref55","article-title":"Practical Bayesian optimization of machine learning algorithms","author":"snoek","year":"2012"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2009.2025137"},{"key":"ref54","first-page":"97","article-title":"Learning transferable features with deep adaptation networks","author":"long","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00966"},{"key":"ref16","article-title":"Unsupervised domain adaptation in the absence of source data","author":"sahoo","year":"2020"},{"key":"ref19","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"mcmahan","year":"2017","journal-title":"Proc Artif Intell Statist"},{"key":"ref18","first-page":"6028","article-title":"Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation","author":"liang","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134077"},{"key":"ref50","article-title":"The CMA evolution strategy: A tutorial","author":"hansen","year":"2016"},{"key":"ref46","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00197"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s10287-022-00425-z"},{"key":"ref47","first-page":"3515","article-title":"Equality of opportunity in supervised learning","author":"hardt","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref42","first-page":"11539","article-title":"Improving robustness against common corruptions by covariate shift adaptation","author":"schneider","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref41","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","author":"ganin","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref43","first-page":"5436","article-title":"Being Bayesian, even just a bit, fixes overconfidence in reLU networks","author":"kristiadi","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref49","article-title":"Set-valued classification–overview via a unified framework","author":"chzhen","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2535302"},{"key":"ref7","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc Assoc Comput Linguistics"},{"key":"ref9","first-page":"1929","article-title":"Fairness without demographics in repeated loss minimization","author":"hashimoto","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref4","first-page":"647","article-title":"DeCAF: A deep convolutional activation feature for generic visual recognition","author":"donahue","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33012412"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1031"},{"key":"ref5","article-title":"Big self-supervised models are strong semi-supervised learners","author":"chen","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.244"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2507157.2507163"},{"key":"ref34","first-page":"202","article-title":"Scaling up the accuracy of naive-bayes classifiers: A decision-tree hybrid","author":"kohavi","year":"1996","journal-title":"Proc Int Conf Knowl Disc Data Mining"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S17-2001"},{"key":"ref36","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","author":"hendrycks","year":"2019"},{"key":"ref31","first-page":"583","article-title":"Greedy layerwise learning can scale to imagenet","author":"belilovsky","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","article-title":"Few-shot image generation with elastic weight consolidation","author":"li","year":"2020"},{"key":"ref33","first-page":"103","article-title":"Evaluation and analysis of the performance of the exp3 algorithm in stochastic environments","author":"seldin","year":"2013","journal-title":"Proc of European Workshop on Reinforcement Learning"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref2","article-title":"Fully test-time adaptation by entropy minimization","author":"wang","year":"2020"},{"key":"ref1","first-page":"1","article-title":"Distributed fine-tuning of language models on private data","author":"popov","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref39","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref38","article-title":"A comprehensive analysis of information leakage in deep transfer learning","author":"chen","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2018.06.010"},{"key":"ref23","article-title":"Using sequential statistical tests to improve the performance of random search in hyperparameter tuning","author":"buczak","year":"2021"},{"key":"ref26","first-page":"3866","article-title":"NAttack: Learning the distributions of adversarial examples for an improved black-box attack on deep neural networks","author":"li","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/0304-4076(88)90027-9"},{"key":"ref20","article-title":"Restricted category removal from model representations using limited data","author":"mazumder","year":"2021"},{"key":"ref22","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"bergstra","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3115\/981658.981684"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2015.09.021"},{"key":"ref27","article-title":"Lecture notes on metric embeddings","author":"matou\u0161ek","year":"2013"},{"key":"ref29","article-title":"Revisiting batch normalization for practical domain adaptation","author":"li","year":"2016"},{"key":"ref60","article-title":"Data-efficient graph grammar learning for molecular generation","author":"guo","year":"2022"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10241246\/10119201.pdf?arnumber=10119201","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T17:28:49Z","timestamp":1717781329000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10119201\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":60,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3273249","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":[[2023,10]]}}}