{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T08:18:21Z","timestamp":1769847501439,"version":"3.49.0"},"reference-count":77,"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":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Discovery Grants program"},{"name":"Canada Institute for Advanced Research"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2023,10,1]]},"DOI":"10.1109\/tkde.2023.3266785","type":"journal-article","created":{"date-parts":[[2023,4,13]],"date-time":"2023-04-13T17:51:39Z","timestamp":1681408299000},"page":"10140-10150","source":"Crossref","is-referenced-by-count":7,"title":["Towards More General Loss and Setting in Unsupervised Domain Adaptation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6447-6559","authenticated-orcid":false,"given":"Changjian","family":"Shui","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering and Computer Engineering, Universit\u00e9 Laval, Mila Québec, QC, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2507-1190","authenticated-orcid":false,"given":"Ruizhi","family":"Pu","sequence":"additional","affiliation":[{"name":"Department of University of Computer Science, Western University, London, ON, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5983-5756","authenticated-orcid":false,"given":"Gezheng","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of University of Computer Science, Western University, London, ON, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5067-2647","authenticated-orcid":false,"given":"Jun","family":"Wen","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1736-2641","authenticated-orcid":false,"given":"Fan","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Transportation Science and Engineering, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3697-4184","authenticated-orcid":false,"given":"Christian","family":"Gagn\u00e9","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Engineering, Universit\u00e9 Laval, Mila Québec, QC, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3797-1348","authenticated-orcid":false,"given":"Charles X.","family":"Ling","sequence":"additional","affiliation":[{"name":"Department of University of Computer Science, Western University, London, ON, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6108-3589","authenticated-orcid":false,"given":"Boyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of University of Computer Science, Western University, London, ON, Canada"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"issue":"1","key":"ref2","first-page":"2096","article-title":"Domain-adversarial training of neural\n                        networks","volume":"17","author":"Ganin","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.316"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-009-5152-4"},{"key":"ref5","volume-title":"Foundations of Machine Learning","author":"Mohri","year":"2018"},{"key":"ref6","first-page":"7523","article-title":"On learning invariant representations for domain\n                        adaptation","volume-title":"Proc. Int. Conf. Mach.\n                        Learn.","author":"Zhao"},{"key":"ref7","first-page":"527","article-title":"Support and invertibility in domain-invariant\n                        representations","volume-title":"Proc. 22nd Int. Conf.\n                        Artif. Intell. Statist.","author":"Johansson"},{"key":"ref8","first-page":"4013","article-title":"Transferable adversarial training: A general approach\n                        to adapting deep classifiers","volume-title":"Proc. Int.\n                        Conf. Mach. Learn.","author":"Liu"},{"key":"ref9","first-page":"3730","article-title":"Joint distribution optimal transportation for domain\n                        adaptation","volume-title":"Proc. Adv. Neural Inf.\n                        Process. Syst.","author":"Courty"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11784"},{"key":"ref11","first-page":"7404","article-title":"Bridging theory and algorithm for domain\n                        adaptation","volume-title":"Proc. Int. Conf. Mach.\n                        Learn.","author":"Zhang"},{"key":"ref12","first-page":"547","article-title":"On measures of entropy and\n                        information","volume-title":"Proc. 4th Berkeley Symp.\n                        Math. Statist. Probability","author":"R\u00e9nyi"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2014.2320500"},{"key":"ref14","volume-title":"Dataset Shift in Machine Learning","author":"Quionero-Candela","year":"2009"},{"key":"ref15","first-page":"129","article-title":"Impossibility theorems for domain\n                        adaptation","volume-title":"Proc. Int. Conf. Artif.\n                        Intell. Statist.","author":"Ben-David"},{"issue":"3","key":"ref16","first-page":"185","volume-title":"Ann.\n                        Math. Artif. Intell.","volume":"70","author":"Ben-David","year":"2014"},{"key":"ref17","article-title":"Understanding deep learning requires rethinking\n                        generalization","author":"Zhang","year":"2016"},{"key":"ref18","first-page":"57","article-title":"Semi-supervised classification by low density\n                        separation","volume-title":"Proc. Int. Conf. Artif.\n                        Intell. Statist.","author":"Chapelle"},{"key":"ref19","first-page":"1","article-title":"Probabilistic lipschitzness a niceness assumption for\n                        deterministic labels","volume-title":"Proc. Int. Conf.\n                        Neural Inf. Process. Syst. Workshop","author":"Urner"},{"key":"ref20","first-page":"641","article-title":"Access to unlabeled data can speed up prediction\n                        time","volume-title":"Proc. 28th Int. Conf. Int. Conf.\n                        Mach. Learn.","author":"Urner"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-34106-9_14"},{"key":"ref22","first-page":"1","article-title":"A dirt-t approach to unsupervised domain\n                        adaptation","volume-title":"Proc. 6th Int. Conf. Learn.\n                        Representations","author":"Shu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00835"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015401"},{"key":"ref25","first-page":"367","article-title":"Multiple source adaptation and the R\u00e9nyi\n                        divergence","volume-title":"Proc. 25th Conf. Uncertainty\n                        Artif. Intell.","author":"Mansour"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ITWF.2015.7360766"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2017.8006529"},{"key":"ref28","first-page":"435","article-title":"PAC-Bayesian bounds based on the r\u00e9nyi\n                        divergence","volume-title":"Proc. Artif. Intell.\n                        Statist.","author":"B\u00e9gin"},{"key":"ref29","first-page":"1433","article-title":"Direct importance estimation with model selection and\n                        its application to covariate shift adaptation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sugiyama"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139035613"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90020-8"},{"key":"ref32","article-title":"Approximating continuous functions by relu nets of\n                        minimal width","author":"Hanin","year":"2017"},{"key":"ref33","first-page":"297","article-title":"Size-independent sample complexity of neural\n                        networks","volume-title":"Proc. Conf. Learn.\n                        Theory","author":"Golowich"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107298019"},{"key":"ref35","first-page":"6872","article-title":"Domain adaptation with asymmetrically-relaxed\n                        distribution alignment","volume-title":"Proc. Int. Conf.\n                        Mach. Learn.","author":"Wu"},{"key":"ref36","first-page":"530","article-title":"Mutual information neural\n                        estimation","author":"Belghazi","year":"2018","journal-title":"Proc. Int. Conf. Mach.\n                        Learn."},{"key":"ref37","article-title":"Wasserstein GAN","author":"Arjovsky","year":"2017"},{"key":"ref38","first-page":"5767","article-title":"Improved training of wasserstein\n                    GANs","volume-title":"Proc. Adv. neural Inf. Process.\n                        Syst.","author":"Gulrajani"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"issue":"85","key":"ref40","first-page":"2825","article-title":"Scikit-learn: Machine learning in\n                        python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_16"},{"key":"ref42","article-title":"Learning transferable features with deep adaptation\n                        networks","author":"Long","year":"2015"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.05.083"},{"key":"ref44","article-title":"A survey of unsupervised deep domain\n                        adaptation","author":"Wilson","year":"2019"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2945942"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3114536"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3144423"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3112815"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3060037"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2843342"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1017\/9781108552332.007"},{"key":"ref52","first-page":"7397","article-title":"Revisiting (epsilon,gamma,tau)-similarity learning\n                        for domain adaptation","volume-title":"Proc. Adv. Neural\n                        Inf. Process. Syst.","author":"Dhouib"},{"issue":"1","key":"ref53","first-page":"1","article-title":"Adaptation based on generalized\n                        discrepancy","volume":"20","author":"Cortes","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014122"},{"key":"ref55","first-page":"8246","article-title":"Algorithms and theory for multiple-source\n                        adaptation","volume-title":"Proc. Adv. Neural Inf.\n                        Process. Syst.","author":"Hoffman"},{"key":"ref56","first-page":"859","article-title":"A new PAC-Bayesian perspective on domain\n                        adaptation","volume-title":"Proc. Int. Conf. Mach.\n                        Learn.","author":"Germain"},{"key":"ref57","first-page":"1","article-title":"Pseudo-labeling curriculum for unsupervised domain\n                        adaptation","volume-title":"Proc. Brit. Mach. Vis.\n                        Conf.","author":"Choi"},{"key":"ref58","first-page":"9345","article-title":"Co-regularized alignment for unsupervised domain\n                        adaptation","volume-title":"Proc. Adv. Neural Inf.\n                        Process. Syst.","author":"Kumar"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00092"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01004"},{"key":"ref61","first-page":"1951","article-title":"Transferable normalization: Towards improving\n                        transferability of deep neural networks","author":"Wang","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00150"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6123"},{"key":"ref64","first-page":"2266","article-title":"Formal guarantees on the robustness of a classifier\n                        against adversarial manipulation","volume-title":"Proc.\n                        Adv. Neural Inf. Process. Syst.","author":"Hein"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451152"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2984212"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451245"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2905157"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2647904"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927224"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.572"},{"key":"ref72","article-title":"VisDA: The visual domain adaptation\n                        challenge","author":"Peng","year":"2017"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3184848"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.106996"},{"key":"ref75","article-title":"Domain adaptation with randomized multilinear\n                        adversarial networks","author":"Long","year":"2017"},{"key":"ref76","first-page":"770","article-title":"Deep residual learning for image\n                        recognition","volume-title":"Proc. IEEE\n                        Conf. Comput. Vis. Pattern Recognit.","author":"He"},{"key":"ref77","first-page":"2208","article-title":"Deep transfer learning with joint adaptation\n                        networks","volume-title":"Proc. Int. Conf. Mach.\n                        Learn.","author":"Long"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/69\/10251471\/10102307.pdf?arnumber=10102307","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T09:41:13Z","timestamp":1725961273000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10102307\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":77,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2023.3266785","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":[[2023,10,1]]}}}