{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:13:34Z","timestamp":1780636414553,"version":"3.54.1"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key RD Program of China","award":["2022YFF0712100"],"award-info":[{"award-number":["2022YFF0712100"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276131"],"award-info":[{"award-number":["62276131"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["08120002"],"award-info":[{"award-number":["08120002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20240081"],"award-info":[{"award-number":["BK20240081"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["30922010317"],"award-info":[{"award-number":["30922010317"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["82232031"],"award-info":[{"award-number":["82232031"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major Science and Technology Projects in Jiangsu Province","award":["BG2024042"],"award-info":[{"award-number":["BG2024042"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tpami.2025.3547417","type":"journal-article","created":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T18:38:49Z","timestamp":1741286329000},"page":"4553-4566","source":"Crossref","is-referenced-by-count":8,"title":["Learning to Rebalance Multi-Modal Optimization by Adaptively Masking Subnetworks"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5245-3584","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0358-6596","authenticated-orcid":false,"given":"Hongpeng","family":"Pan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9214-7960","authenticated-orcid":false,"given":"Qing-Yuan","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9900-6143","authenticated-orcid":false,"given":"Yi","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9008-222X","authenticated-orcid":false,"given":"Jinhui","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3183112"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2014.03.003"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475692"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102203"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261659"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2852750"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3050918"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/568"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3080293"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3125995"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3160060"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01330"},{"key":"ref15","first-page":"6881","article-title":"Trustworthy multimodal regression with mixture of normal-inverse gamma distributions","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ma"},{"key":"ref16","first-page":"14 200","article-title":"Attention bottlenecks for multimodal fusion","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Nagrani"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00806"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01918"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"ref20","first-page":"9226","article-title":"Modality competition: What makes joint training of multi-modal network fail in deep learning? (Provably)","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang"},{"key":"ref21","first-page":"24 043","article-title":"Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11024-6_44"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.challengehml-1.1"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.143"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02030"},{"key":"ref26","first-page":"1058","article-title":"Regularization of neural networks using dropconnect","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wan"},{"key":"ref27","article-title":"Mixout: Effective regularization to finetune large-scale pretrained language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref29","first-page":"1","article-title":"Stochastic optimization with importance sampling for regularized loss minimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhao"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2738401"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2987728"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-010-0182-0"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-08796-8"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102031"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2879108"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.07.010"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.119491"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102071"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26346"},{"key":"ref41","article-title":"Improving multi-modal learning with uni-modal teachers","author":"Du","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3101421"},{"key":"ref43","first-page":"2575","article-title":"Variational dropout and the local reparameterization trick","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kingma"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298664"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.749"},{"key":"ref46","first-page":"21 442","article-title":"Fine-tuning pre-trained language models effectively by optimizing subnetworks adaptively","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3171983"},{"key":"ref48","first-page":"403","article-title":"An information theoretic framework for multi-view learning","volume-title":"Proc. Annu. Conf. Learn. Theory","author":"Sridharan"},{"key":"ref49","first-page":"530","article-title":"Mutual information neural estimation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Belghazi"},{"key":"ref50","first-page":"1779","article-title":"CLUB: A contrastive log-ratio upper bound of mutual information","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cheng"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2743707"},{"key":"ref52","first-page":"18098","article-title":"WoodFisher: Efficient second-order approximation for neural network compression","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Singh"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.1922.0009"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ISVLSI.2016.117"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref56","first-page":"364","article-title":"Adaptive sampling for SGD by exploiting side information","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gopal"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1239"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/751"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.456"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11962"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-41299-9_32"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548203"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"issue":"7","key":"ref68","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"Duchi","year":"2011","journal-title":"J Mach. Learn. Res."},{"key":"ref69","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10990047\/10915567.pdf?arnumber=10915567","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T17:38:25Z","timestamp":1746725905000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10915567\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":69,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3547417","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":[[2025,6]]}}}