{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T09:06:36Z","timestamp":1769504796068,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","funder":[{"name":"China University Research Innovation Fund","award":["2024HY021"],"award-info":[{"award-number":["2024HY021"]}]},{"DOI":"10.13039\/501100004775","name":"Natural Science Foundation of Gansu Province","doi-asserted-by":"publisher","award":["24JRRA137"],"award-info":[{"award-number":["24JRRA137"]}],"id":[{"id":"10.13039\/501100004775","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,13]]},"DOI":"10.1145\/3716553.3750805","type":"proceedings-article","created":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T13:13:16Z","timestamp":1760188396000},"page":"579-587","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Block-Level Fine-Graining Framework for Multimodal Fusion in Federated Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2947-2050","authenticated-orcid":false,"given":"Guozhi","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Northwest Normal University, Lanzhou, Gansu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2282-3712","authenticated-orcid":false,"given":"Mengying","family":"Jia","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Northwest Normal University, Lanzhou, Gansu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1031-1907","authenticated-orcid":false,"given":"Shuyan","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Northwest Normal University, Lanzhou, Gansu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6357-5987","authenticated-orcid":false,"given":"Zixuan","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Northwest Normal University, Lanzhou, Gansu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,12]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","unstructured":"Liwei Che Jiaqi Wang Yao Zhou and Fenglong Ma. 2023. Multimodal Federated Learning: A Survey. Sensors 23 15 (2023) 6986. 10.3390\/s23156986","DOI":"10.3390\/s23156986"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2015.7350781"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539384"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","unstructured":"Grazia Cicirelli Roberto Marani Laura Romeo Manuel\u00a0Garc\u00eda Dom\u00ednguez J\u00f3nathan Heras Anna\u00a0G. Perri and Tiziana D\u2019Orazio. 2022. The HA4M dataset: Multi-Modal Monitoring of an assembly task for Human Action recognition in Manufacturing. Scientific Data 9 1 (2022) 745. 10.1038\/s41597-022-01843-z","DOI":"10.1038\/s41597-022-01843-z"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599825"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","unstructured":"Min Gao Haifeng Zheng Mengxuan Du and Xinxin Feng. 2024. Multimodal Fusion With Block Term Decomposition for Asynchronous Federated Learning. IEEE Transactions on Industrial Informatics 20 12 (2024) 14083\u201314093. 10.1109\/TII.2024.3441634","DOI":"10.1109\/TII.2024.3441634"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","unstructured":"Wei Huang Dexian Wang Xiaocao Ouyang Jihong Wan Jia Liu and Tianrui Li. 2024. Multimodal federated learning: Concept methods applications and future directions. Information Fusion 112 (2024) 102576. 10.1016\/j.inffus.2024.102576","DOI":"10.1016\/j.inffus.2024.102576"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","unstructured":"Xiangen Jia Min Jiang Yihong Dong Feng Zhu Haocai Lin Yu Xin and Huahui Chen. 2023. Multimodal heterogeneous graph attention network. Neural Computing and Applications 35 4 (2023) 3357\u20133372. 10.1007\/s00521-022-07862-6","DOI":"10.1007\/s00521-022-07862-6"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683546"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3483278"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","unstructured":"Jiang Li Xiaoping Wang Guoqing Lv and Zhigang Zeng. 2023. GraphMFT: A graph network based multimodal fusion technique for emotion recognition in conversation. Neurocomputing 550 (2023) 126427. 10.1016\/j.neucom.2023.126427","DOI":"10.1016\/j.neucom.2023.126427"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6824"},{"key":"e_1_3_3_1_14_2","series-title":"Proceedings of Machine Learning Research","first-page":"1273","volume-title":"Proceedings of the 20th International Conference on Artificial Intelligence and Statistics","volume":"54","author":"McMahan Brendan","year":"2017","unstructured":"Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise\u00a0Aguera y Arcas. 2017. Communication-Efficient Learning of Deep Networks from Decentralized Data. In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics(Proceedings of Machine Learning Research, Vol.\u00a054). PMLR, Fort Lauderdale, FL, USA, 1273\u20131282. https:\/\/proceedings.mlr.press\/v54\/mcmahan17a.html"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","unstructured":"Huiling Mou Haifeng Zheng Min Gao and Xinxin Feng. 2022. Multi-Source Heterogeneous Data Fusion Based on Federated Learning. Journal of Computer Research and Development 59 2 (2022) 478\u2013487. 10.7544\/issn1000-1239.20200668","DOI":"10.7544\/issn1000-1239.20200668"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid57682.2023.00032"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3545008.3545085"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581791.3596844"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458864.3467681"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","unstructured":"Brendan Avent Aur\u00e9lien Bellet Mehdi Bennis Arjun Nitin Bhagoji Kallista Bonawitz Zachary Charles Graham Cormode Rachel Cummings Rafael G. L. D\u2019Oliveira Hubert Eichner Salim El Rouayheb David Evans Josh Gardner Zachary Garrett Adri\u00e0 Gasc\u00f3n Badih Ghazi Phillip B. Gibbons Marco Gruteser Zaid Harchaoui Chaoyang He Lie He Zhouyuan Huo Ben Hutchinson Justin Hsu Martin Jaggi Tara Javidi Gauri Joshi Mikhail Khodak Jakub Konecn\u00fd Aleksandra Korolova Farinaz Koushanfar Sanmi Koyejo Tancr\u00e8de Lepoint Yang Liu Prateek Mittal Mehryar Mohri Richard Nock Ayfer \u00d6zg\u00fcr Rasmus Pagh Hang Qi Daniel Ramage Ramesh Raskar Mariana Raykova Dawn Song Weikang Song Sebastian U. Stich Ziteng Sun Ananda Theertha Suresh Florian Tram\u00e8r Praneeth Vepakomma Jianyu Wang Li Xiong Zheng Xu Qiang Yang Felix X. Yu Han\u00a0Yu Peter\u00a0Kairouz H. Brendan\u00a0McMahan and Sen Zhao. 2021. Advances and Open Problems in Federated Learning. Foundations and Trends in Machine Learning 14 1\u20132 (2021) 1\u2013210. 10.1561\/2200000083","DOI":"10.1561\/2200000083"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","unstructured":"Pian Qi Diletta Chiaro and Francesco Piccialli. 2023. FL-FD: Federated learning-based fall detection with multimodal data fusion. Information Fusion 99 (2023) 101890. 10.1016\/j.inffus.2023.101890","DOI":"10.1016\/j.inffus.2023.101890"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","unstructured":"Yuzhi Song Hailiang Ye Ming Li and Feilong Cao. 2022. Deep Multi-Graph Neural Networks with Attention Fusion for Recommendation. Expert Systems with Applications 191 (2022) 116240. 10.1016\/j.eswa.2021.116240","DOI":"10.1016\/j.eswa.2021.116240"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-5495-3_17"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3485946"},{"key":"e_1_3_3_1_25_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Veli\u010dkovi\u0107 Petar","year":"2018","unstructured":"Petar Veli\u010dkovi\u0107, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Li\u00f2, and Yoshua Bengio. 2018. Graph Attention Networks. In Proceedings of the International Conference on Learning Representations (ICLR). https:\/\/openreview.net\/forum?id=rJXMpikCZ"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","unstructured":"Wenhao Wu Shudong Wang Yuanyuan Zhang Wenjing Yin Yawu Zhao and Shanchen Pang. 2024. MOSGAT: Uniting Specificity-Aware GATs and Cross Modal-Attention to Integrate Multi-Omics Data for Disease Diagnosis. IEEE Journal of Biomedical and Health Informatics 28 9 (2024) 5624\u20135637. 10.1109\/JBHI.2024.3415641","DOI":"10.1109\/JBHI.2024.3415641"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/SMC54092.2024.10831861"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","unstructured":"Baochen Xiong Xiaoshan Yang Fan Qi and Changsheng Xu. 2022. A unified framework for multi-modal federated learning. Neurocomputing 480 (2022) 110\u2013118. 10.1016\/j.neucom.2022.01.063","DOI":"10.1016\/j.neucom.2022.01.063"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","unstructured":"Liangqi Yuan Ziran Wang Lichao Sun Philip\u00a0S. Yu and Christopher\u00a0G. Brinton. 2024. Decentralized Federated Learning: A Survey and Perspective. IEEE Internet of Things Journal 11 21 (2024) 34617\u201334638. 10.1109\/JIOT.2024.3407584","DOI":"10.1109\/JIOT.2024.3407584"}],"event":{"name":"ICMI '25: International Conference on Multimodal Interaction","location":"Canberra Australia","acronym":"ICMI '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 27th International Conference on Multimodal Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3716553.3750805","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T22:28:28Z","timestamp":1769466508000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3716553.3750805"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"references-count":28,"alternative-id":["10.1145\/3716553.3750805","10.1145\/3716553"],"URL":"https:\/\/doi.org\/10.1145\/3716553.3750805","relation":{},"subject":[],"published":{"date-parts":[[2025,10,12]]},"assertion":[{"value":"2025-10-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}