{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T14:46:55Z","timestamp":1785336415474,"version":"3.55.0"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"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. on Mobile Comput."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tmc.2025.3567535","type":"journal-article","created":{"date-parts":[[2025,5,6]],"date-time":"2025-05-06T13:06:23Z","timestamp":1746536783000},"page":"10009-10023","source":"Crossref","is-referenced-by-count":12,"title":["Unimodal Training-Multimodal Prediction: Cross-Modal Federated Learning With Hierarchical Aggregation"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9174-1765","authenticated-orcid":false,"given":"Rongyu","family":"Zhang","sequence":"first","affiliation":[{"name":"Nanjing University and The Hong Kong Polytechnic University, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6559-4378","authenticated-orcid":false,"given":"Xiaowei","family":"Chi","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1135-0706","authenticated-orcid":false,"given":"Wenyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, University of California, Irvine, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7464-523X","authenticated-orcid":false,"given":"Guiliang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Data Science (SDS), The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0921-2726","authenticated-orcid":false,"given":"Dan","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2559-045X","authenticated-orcid":false,"given":"Fangxin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Science and Engineering (SSE), the Shenzhen Future Network of Intelligence Institute (FNii-Shenzhen), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20213"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3235935"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3303350"},{"key":"ref4","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Artif. Intell. Statist.","author":"McMahan","year":"2017"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3136853"},{"key":"ref6","article-title":"Think locally, act globally: Federated learning with local and global representations","author":"Liang","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796724"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3367412"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539384"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3570361.3592517"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045502"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29622"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1561\/9781680837896"},{"key":"ref16","first-page":"5132","article-title":"SCAFFOLD: Stochastic controlled averaging for federated learning","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Karimireddy","year":"2020"},{"key":"ref17","first-page":"10334","article-title":"Is local SGD better than minibatch SGD?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Woodworth","year":"2020"},{"key":"ref18","first-page":"6281","article-title":"Minibatch vs local SGD for heterogeneous distributed learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Woodworth","year":"2020"},{"key":"ref19","article-title":"On the convergence of fedavg on non-IID data","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Li","year":"2010"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00077"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.008.2200654"},{"key":"ref22","article-title":"Adaptive federated optimization","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Reddi","year":"2021"},{"key":"ref23","article-title":"Adaptive gradient-based meta-learning methods","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Khodak","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155494"},{"key":"ref25","article-title":"Federated uncertainty-aware learning for distributed hospital EHR data","author":"Boughorbel","year":"2019"},{"key":"ref26","first-page":"150","article-title":"Multimodal language analysis with recurrent multistage fusion","volume-title":"Proc. 2018 Conf. Emp. Methods Natural Lang. Process.","author":"Liang","year":"2018"},{"key":"ref27","article-title":"Learning factorized multimodal representations","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Tsai","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6431"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017216"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016892"},{"key":"ref32","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani","year":"2017"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00148"},{"key":"ref34","first-page":"2592","article-title":"UNIMO: Towards unified-modal understanding and generation via cross-modal contrastive learning","volume-title":"Proc. 59th Annu. Meeting Assoc. Comput. Linguistics 11th Int. Joint Conf. Natural Lang. Process.","author":"Li","year":"2021"},{"key":"ref35","first-page":"14200","article-title":"Attention bottlenecks for multimodal fusion","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Nagrani","year":"2021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3390\/s23156986"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1398-0"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599825"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101890"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IoTDI54339.2022.00011"},{"key":"ref41","article-title":"Multimodal federated learning via contrastive representation ensemble","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Yu","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613837"},{"key":"ref43","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume-title":"Proc. Mach. Learn. Syst.","volume":"2","author":"Li","year":"2020"},{"key":"ref44","article-title":"Federated learning via posterior averaging: A new perspective and practical algorithms","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Al-Shedivat","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852464"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/S0047-259X(03)00096-4"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref49","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18653\/v1\/2020.challengehml-1.1","article-title":"A transformer-based joint-encoding for emotion recognition and sentiment analysis","volume-title":"Proc. 2nd Grand-Challenge Workshop Multimodal Lang.","author":"Delbrouck","year":"2020"},{"key":"ref50","first-page":"1","article-title":"Modulated fusion using transformer for linguistic-acoustic emotion recognition","volume-title":"Proc. 1st Int. Workshop Natural Lang. Process. Beyond Text","author":"Delbrouck","year":"2020"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3581791.3596844"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4380-9_16"},{"key":"ref53","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lakshminarayanan","year":"2017"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2004.03.020"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7755\/11154819\/10989558.pdf?arnumber=10989558","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T19:53:07Z","timestamp":1757533987000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10989558\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":55,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2025.3567535","relation":{},"ISSN":["1536-1233","1558-0660","2161-9875"],"issn-type":[{"value":"1536-1233","type":"print"},{"value":"1558-0660","type":"electronic"},{"value":"2161-9875","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}