{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T20:23:19Z","timestamp":1757622199787,"version":"3.44.0"},"reference-count":84,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62227808"],"award-info":[{"award-number":["62227808"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major Key Project of Peng Cheng Laboratory","award":["PCL2024A05"],"award-info":[{"award-number":["PCL2024A05"]}]},{"DOI":"10.13039\/501100001809","name":"Shenzhen Science and Technology Program","doi-asserted-by":"publisher","award":["ZDSYS20210623091809029"],"award-info":[{"award-number":["ZDSYS20210623091809029"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1109\/tnnls.2025.3555683","type":"journal-article","created":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T13:34:08Z","timestamp":1745847248000},"page":"17322-17335","source":"Crossref","is-referenced-by-count":0,"title":["Multitask Causal Contrastive Learning"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3614-9371","authenticated-orcid":false,"given":"Chaoyang","family":"Li","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4470-9364","authenticated-orcid":false,"given":"Heyan","family":"Chai","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Chinese University of Hong Kong, Hong Kong, China"}]},{"given":"Yan","family":"Jia","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8355-0969","authenticated-orcid":false,"given":"Ning","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1012-5301","authenticated-orcid":false,"given":"Qing","family":"Liao","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"ref2","article-title":"An overview of multi-task learning in deep neural networks","author":"Ruder","year":"2017","journal-title":"arXiv:1706.05098"},{"issue":"1","key":"ref3","first-page":"2853","article-title":"The benefit of multitask representation learning","volume":"17","author":"Maurer","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref4","first-page":"7852","article-title":"On the theory of transfer learning: The importance of task diversity","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Tripuraneni"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512043"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE55515.2023.00314"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00312"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3288537"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3251897"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1441"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00197"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3097498"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2399233"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3234166"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2949929"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3056383"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105284"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2933439"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3028022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2919774"},{"key":"ref21","first-page":"156","article-title":"Actor-mimic: Deep multitask and transfer reinforcement learning","volume-title":"Proc. 4th Int. Conf. Learn. Represent.","author":"Parisotto"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2022.106004"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220007"},{"key":"ref24","first-page":"2039","article-title":"Just pick a sign: Optimizing deep multitask models with gradient sign dropout","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Zhao"},{"key":"ref25","first-page":"8728","article-title":"AdaShare: Learning what to share for efficient deep multi-task learning","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Sun"},{"key":"ref26","first-page":"3854","article-title":"Learning to branch for multi-task learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guo"},{"key":"ref27","first-page":"525","article-title":"Multi-task learning as multi-objective optimization","volume-title":"Proc. NIPS","author":"Sener"},{"key":"ref28","first-page":"793","article-title":"GradNorm: Gradient normalization for adaptive loss balancing in deep multitask networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref29","first-page":"1","article-title":"RotoGrad: Gradient homogenization in multitask learning","volume-title":"Proc. 10th Int. Conf. Learn. Represent.","author":"Javaloy"},{"key":"ref30","first-page":"5824","article-title":"Gradient surgery for multi-task learning","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Yu"},{"key":"ref31","first-page":"18878","article-title":"Conflict-averse gradient descent for multi-task learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Liu"},{"key":"ref32","first-page":"16428","article-title":"Multi-task learning as a bargaining game","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"162","author":"Navon"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26275"},{"article-title":"Multi-digit MNIST for few-shot learning","year":"2019","author":"Sun","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1214\/09-SS057"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1080\/00949655.2018.1505197"},{"key":"ref37","first-page":"1","article-title":"Reasonable effectiveness of random weighting: A litmus test for multi-task learning","volume":"2022","author":"Lin","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref38","first-page":"1","article-title":"Gradient vaccine: Investigating and improving multi-task optimization in massively multilingual models","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_7"},{"key":"ref40","first-page":"34216","article-title":"AutoMTL: A programming framework for automating efficient multi-task learning","volume-title":"Proc. NeurIPS","volume":"35","author":"Zhang"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3442442.3452323"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.433"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557559"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01824"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00781"},{"key":"ref46","first-page":"13597","article-title":"Do current multi-task optimization methods in deep learning even help?","volume-title":"Proc. NeurIPS","volume":"35","author":"Xin"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512021"},{"key":"ref48","first-page":"27503","article-title":"Efficiently identifying task groupings for multi-task learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Fifty"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2991344"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01970"},{"key":"ref51","article-title":"From dependence to causation","author":"Lopez-Paz","year":"2016","journal-title":"arXiv:1607.03300"},{"key":"ref52","first-page":"655","article-title":"Causal intervention for weakly-supervised semantic segmentation","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Zhang"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11248"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21296"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3121705"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611873"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-62077-6_14"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1161"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/659"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014846"},{"key":"ref61","first-page":"10220","article-title":"CXPlain: Causal explanations for model interpretation under uncertainty","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Schwab"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3058954"},{"key":"ref63","first-page":"1","article-title":"A meta-transfer objective for learning to disentangle causal mechanisms","volume-title":"Proc. 8th Int. Conf. Learn. Represent.","author":"Bengio"},{"key":"ref64","first-page":"1","article-title":"Representation learning via invariant causal mechanisms","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Mitrovic"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3284038"},{"key":"ref66","article-title":"Proactive pseudo-intervention: Causally informed contrastive learning for interpretable vision models","author":"Wang","year":"2020","journal-title":"arXiv:2012.03369"},{"key":"ref67","first-page":"18123","article-title":"Counterfactual contrastive learning for weakly-supervised vision-language grounding","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Zhang"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.265"},{"key":"ref69","first-page":"6345","article-title":"Learning contrastive embedding in low-dimensional space","volume-title":"Proc. NeurIPS","volume":"35","author":"Chen"},{"key":"ref70","first-page":"4358","article-title":"Energy-based contrastive learning of visual representations","volume-title":"Proc. NeurIPS","volume":"35","author":"Kim"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-short.59"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.114"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/84"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE55515.2023.00391"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01449"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01428"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599503"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599768"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE55515.2023.00059"},{"key":"ref80","first-page":"882","article-title":"Learning to explain: An information-theoretic perspective on model interpretation","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"80","author":"Chen"},{"key":"ref81","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11151745\/10979291.pdf?arnumber=10979291","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T17:46:53Z","timestamp":1757353613000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10979291\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":84,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3555683","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}