{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T17:30:55Z","timestamp":1745861455492,"version":"3.37.3"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1109\/tkde.2022.3207049","type":"journal-article","created":{"date-parts":[[2022,9,15]],"date-time":"2022-09-15T19:36:47Z","timestamp":1663270607000},"page":"1-14","source":"Crossref","is-referenced-by-count":0,"title":["Task Variance Regularized Multi-Task Learning"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0550-3072","authenticated-orcid":false,"given":"Yuren","family":"Mao","sequence":"first","affiliation":[{"name":"School of Software Technology, Zhejiang University, China"}]},{"given":"Zekai","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2450-3369","authenticated-orcid":false,"given":"Weiwei","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, China"}]},{"given":"Xuemin","family":"Lin","sequence":"additional","affiliation":[{"name":"Antai College of Economics and Management, Shanghai Jiao Tong University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8383-2483","authenticated-orcid":false,"given":"Wenbin","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00197"},{"key":"ref57","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00332"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref15","first-page":"793","article-title":"GradNorm: Gradient normalization for adaptive loss balancing in deep multitask networks","author":"chen","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_31"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.433"},{"key":"ref55","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":"ref10","first-page":"3854","article-title":"Learning to branch for multi-task learning","author":"guo","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref54","first-page":"440","article-title":"Biographies, bollywood, boom-boxes and blenders: Domain adaptation for sentiment classification","author":"blitzer","year":"2007","journal-title":"Proc Conf Assoc Comput Linguistics"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_17"},{"key":"ref16","first-page":"525","article-title":"Multi-task learning as multi-objective optimization","author":"sener","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref19","first-page":"12060","article-title":"Pareto multi-task learning","author":"lin","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00197"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref46","first-page":"2645","article-title":"On the universality of online mirror descent","author":"srebro","year":"2011","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1561\/2200000024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-017-1174-z"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.1120.1641"},{"key":"ref42","volume":"12","author":"miettinen","year":"2012","journal-title":"Nonlinear Multiobjective Optimization"},{"key":"ref41","first-page":"6597","article-title":"Multi-task learning with user preferences: Gradient descent with controlled ascent in pareto optimization","author":"debabrata mahapatra","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2044"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2114"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref8","article-title":"Branched multi-task networks: Deciding what layers to share","author":"vandenhende","year":"2020","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.579"},{"key":"ref9","article-title":"Automated search for resource-efficient branched multi-task networks","author":"bruggemann","year":"2020","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref4","first-page":"7482","article-title":"Multi-task learning using uncertainty to weigh losses for scene geometry and semantics","author":"kendall","year":"2018","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref3","first-page":"38:1","article-title":"Local rademacher complexity-based learning guarantees for multi-task learning","volume":"19","author":"yousefi","year":"2018","journal-title":"J Mach Learn Res"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-12683-3_34"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1001"},{"journal-title":"Convex optimization","year":"2014","author":"boyd","key":"ref40"},{"key":"ref35","first-page":"5595","article-title":"Bias-robust Bayesian optimization via dueling bandit","author":"kirschner","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref34","first-page":"5393","article-title":"Adam with bandit sampling for deep learning","author":"liu","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref37","first-page":"3520","article-title":"AutoSeM: Automatic task selection and mixing in multi-task learning","author":"guo","year":"2019","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref36","first-page":"4851","article-title":"Multi-task learning for contextual bandits","author":"deshmukh","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref31","first-page":"2216","article-title":"Stochastic gradient methods for distributionally robust optimization with f-divergences","author":"namkoong","year":"2016","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref30","first-page":"2975","article-title":"Variance-based regularization with convex objectives","author":"namkoong","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref33","first-page":"6878","article-title":"Bandit samplers for training graph neural networks","author":"liu","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref32","first-page":"68:1","article-title":"Variance-based regularization with convex objectives","volume":"20","author":"duchi","year":"2019","journal-title":"J Mach Learn Res"},{"key":"ref2","first-page":"1817","article-title":"A framework for learning predictive structures from multiple tasks and unlabeled data","volume":"6","author":"ando","year":"2005","journal-title":"J Mach Learn Res"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50012-5"},{"key":"ref39","first-page":"4349","article-title":"Near-optimal representation learning for linear bandits and linear RL","author":"hu","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref38","article-title":"Impact of representation learning in linear bandits","author":"yang","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref24","article-title":"Learning the pareto front with hypernetworks","author":"navon","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.388"},{"key":"ref26","article-title":"Towards impartial multi-task learning","author":"liu","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref25","first-page":"5824","article-title":"Gradient surgery for multi-task learning","author":"yu","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref20","first-page":"6597","article-title":"Multi-task learning with user preferences: Gradient descent with controlled ascent in pareto optimization","author":"mahapatra","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref22","first-page":"6522","article-title":"Efficient continuous pareto exploration in multi-task learning","author":"ma","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"article-title":"Controllable pareto multi-task learning","year":"2020","author":"lin","key":"ref21"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1198\/016214505000000907"},{"key":"ref27","first-page":"3614","article-title":"Multi-task learning for dense prediction tasks: A survey","volume":"44","author":"vandenhende","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1214\/009053606000001019"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/69\/4358933\/09893398.pdf?arnumber=9893398","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,7]],"date-time":"2023-07-07T21:48:24Z","timestamp":1688766504000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9893398\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/tkde.2022.3207049","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"type":"print","value":"1041-4347"},{"type":"electronic","value":"1558-2191"},{"type":"electronic","value":"2326-3865"}],"subject":[],"published":{"date-parts":[[2022]]}}}