{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T05:21:32Z","timestamp":1783056092053,"version":"3.54.6"},"reference-count":164,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T00:00:00Z","timestamp":1779840000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T00:00:00Z","timestamp":1779840000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR-20-CE25-0002"],"award-info":[{"award-number":["ANR-20-CE25-0002"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR-20-CE25-0002"],"award-info":[{"award-number":["ANR-20-CE25-0002"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["(ANR- 22-PESN-0013)"],"award-info":[{"award-number":["(ANR- 22-PESN-0013)"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["(ANR- 22-PESN-0013)"],"award-info":[{"award-number":["(ANR- 22-PESN-0013)"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s00521-025-11815-0","type":"journal-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T03:06:49Z","timestamp":1779851209000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A survey on multimodal federated learning"],"prefix":"10.1007","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-7697-1566","authenticated-orcid":false,"given":"Silvia","family":"Grosso","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6382-3839","authenticated-orcid":false,"given":"Nawel","family":"Benarba","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0558-0123","authenticated-orcid":false,"given":"Sara","family":"Bouchenak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5366-292X","authenticated-orcid":false,"given":"Roberto","family":"Esposito","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4890-5020","authenticated-orcid":false,"given":"Mirko","family":"Polato","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,27]]},"reference":[{"key":"11815_CR1","doi-asserted-by":"crossref","unstructured":"Voigt P, Von dem Bussche A (2017) The Eu General Data Protection Regulation (GDPR). A Practical Guide, vol 10, 1st edn. Springer International Publishing, Cham, pp 10\u20135555","DOI":"10.1007\/978-3-319-57959-7"},{"key":"11815_CR2","unstructured":"The European Commission.: The Artificial Intelligence Act. https:\/\/artificialintelligenceact.eu\/"},{"key":"11815_CR3","unstructured":"White House Office of Science and Technology Policy .: Blueprint for an AI Bill of Rights. Available from: https:\/\/www.whitehouse.gov\/wp-content\/uploads\/2022\/10\/Blueprint-for-an-AI-Bill-of-Rights.pdf"},{"key":"11815_CR4","unstructured":"McMahan B, Moore E, Ramage D, Hampson S, y Arcas BA. (2017) Communication-Efficient Learning of Deep Networks from Decentralized Data. Artificial Intelligence and Statistics. Fort Lauderdale, FL, USA, pp 1273\u20131282"},{"key":"11815_CR5","unstructured":"Achiam J, Adler S, Agarwal S, Ahmad L, Akkaya I, Aleman FL, et al Gpt-4 Technical Report"},{"key":"11815_CR6","doi-asserted-by":"crossref","unstructured":"Girdhar R, El-Nouby A, Liu Z, Singh M, Alwala KV, Joulin A et al (2023). Imagebind: One Embedding Space to Bind Them All. Vancouver, BC, Canada, pp 15180\u201315190","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"11815_CR7","unstructured":"Saab K, Tu T, Weng WH, Tanno R, Stutz D, Wulczyn E, et al Capabilities of Gemini Models in Medicine"},{"key":"11815_CR8","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2023.104338","volume":"141","author":"F Cremonesi","year":"2023","unstructured":"Cremonesi F, Planat V, Kalokyri V, Kondylakis H, Sanavia T, Resinas VMM et al (2023) The Need for Multimodal Health Data Modeling: a Practical Approach for a Federated Learning Healthcare Platform. J Biomed Inform 141:104338","journal-title":"J Biomed Inform"},{"key":"11815_CR9","doi-asserted-by":"crossref","unstructured":"Zhang Y, Liu L, Liu L (2023) Cuing Without Sharing: A Federated Cued Speech Recognition Framework Via Mutual Knowledge Distillation. pp 8781\u20138789","DOI":"10.1145\/3581783.3612134"},{"key":"11815_CR10","doi-asserted-by":"crossref","unstructured":"Liang PP, Liu T, Cai A, Muszynski M, Ishii R, Allen N, et al Learning Language and Multimodal Privacy Preserving Markers of Mood From Mobile Data. arXiv preprint arXiv:2106.13213. 2021;","DOI":"10.18653\/v1\/2021.acl-long.322"},{"key":"11815_CR11","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1631\/FITEE.1601650","volume":"18","author":"T Zhang","year":"2017","unstructured":"Zhang T, Li Q, Cs Zhang, Hw Liang, Li P, Tm Wang et al (2017) Current Trends in the Development of Intelligent Unmanned Autonomous Systems. Frontiers of information technology & electronic engineering. 18:68\u201385","journal-title":"Frontiers of information technology & electronic engineering."},{"issue":"4","key":"11815_CR12","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1007\/s11633-022-1398-0","volume":"20","author":"YM Lin","year":"2023","unstructured":"Lin YM, Gao Y, Gong MG, Zhang SJ, Zhang YQ, Li ZY (2023) Federated Learning On Multimodal Data: A Comprehensive Survey. Machine Intelligence Research 20(4):539\u2013553","journal-title":"Machine Intelligence Research"},{"issue":"15","key":"11815_CR13","doi-asserted-by":"crossref","first-page":"6986","DOI":"10.3390\/s23156986","volume":"23","author":"L Che","year":"2023","unstructured":"Che L, Wang J, Zhou Y, Ma F (2023) Multimodal Federated Learning: A Survey. Sensors 23(15):6986","journal-title":"Sensors"},{"key":"11815_CR14","volume":"112","author":"W Huang","year":"2024","unstructured":"Huang W, Wang D, Ouyang X, Wan J, Liu J, Li T (2024) Multimodal federated learning: Concept, methods, applications and future directions. Information Fusion 112:102576","journal-title":"Information Fusion"},{"issue":"4","key":"11815_CR15","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1007\/s00530-024-01422-9","volume":"30","author":"H Pan","year":"2024","unstructured":"Pan H, Zhao X, He L, Shi Y, Lin X (2024) A survey of multimodal federated learning: background, applications, and perspectives. Multimedia Syst 30(4):222","journal-title":"Multimedia Syst"},{"key":"11815_CR16","doi-asserted-by":"crossref","unstructured":"Anagnostopoulos C, Gkillas A, Mavrokefalidis C, Pikoulis EV, Piperigkos N, Lalos AS (2024) Multimodal Federated Learning in AIoT Systems: Existing Solutions, Applications, and Challenges. IEEE Access.;","DOI":"10.1109\/ACCESS.2024.3508030"},{"key":"11815_CR17","doi-asserted-by":"crossref","unstructured":"Adam M, Albaseer A, Baroudi U, Abdallah M (2025) Survey of Multimodal Federated Learning: Exploring Data Integration, Challenges, and Future Directions. IEEE Open Journal of the Communications Society","DOI":"10.1109\/OJCOMS.2025.3554537"},{"key":"11815_CR18","first-page":"56","volume-title":"State-of-the-art and research challenges","author":"M Ye","year":"2023","unstructured":"Ye M, Fang X, Du B, Yuen PC, Tao D (2023) State-of-the-art and research challenges. Heterogeneous federated learning, ACM Computing Surveys, p 56"},{"key":"11815_CR19","unstructured":"Google Support.: Start conversations with Google Assistant using Look and Talk on Nest Hub Max. Available from: https:\/\/support.google.com\/googlenest\/answer\/11410414"},{"key":"11815_CR20","unstructured":"Mark Spates (Google Product Manager).: Nest Mini brings twice the bass and an upgraded Assistant. Google. Available from: https:\/\/blog.google\/products\/google-nest\/nest-mini\/"},{"key":"11815_CR21","unstructured":"Google Blog.: Introducing Google Tensor: Our first custom-built chip. Available from: https:\/\/blog.google\/products\/pixel\/introducing-google-tensor\/"},{"key":"11815_CR22","doi-asserted-by":"crossref","unstructured":"Page MJ, McKenzie JE, Bossuyt PM, Boutron I, Hoffmann TC, Mulrow CD, et al. (2021) The PRISMA 2020 Statement: An Updated Guideline for Reporting Systematic Reviews. bmj. 372","DOI":"10.1136\/bmj.n71"},{"key":"11815_CR23","unstructured":"Liang PP, Zadeh A, Morency LP (2022) Foundations and Recent Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions. arXiv preprint. arxiv:2209.03430"},{"key":"11815_CR24","unstructured":"Waibel A, Stiefelhagen R, Carlson R, Casas JR, Kleindienst J, Lamel L, et al Computers in the Human Interaction Loop"},{"key":"11815_CR25","doi-asserted-by":"crossref","unstructured":"T\u00fcr G, Stolcke A, Voss LL, Dowding J, Favre B, Fern\u00e1ndez R, Meeting TCALO, Recognition S, System U, In, et al (2008) IEEE Spoken Language Technology Workshop. Goa India 2008:69\u201372","DOI":"10.1109\/SLT.2008.4777842"},{"key":"11815_CR26","doi-asserted-by":"crossref","first-page":"72096","DOI":"10.52202\/075280-3155","volume":"36","author":"S Huang","year":"2023","unstructured":"Huang S, Dong L, Wang W, Hao Y, Singhal S, Ma S et al (2023) Language is not all you need: Aligning perception with language models. Adv Neural Inf Process Syst 36:72096\u201372109","journal-title":"Adv Neural Inf Process Syst"},{"key":"11815_CR27","unstructured":"Zhang Z, Zhang A, Li M, Zhao H, Karypis G, Smola A. Multimodal chain-of-thought reasoning in language models. arXiv preprint arXiv:2302.00923. 2023;"},{"key":"11815_CR28","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.102040","volume":"102","author":"T Shaik","year":"2024","unstructured":"Shaik T, Tao X, Li L, Xie H, Vel\u00e1squez JD (2024) A Survey of Multimodal Information Fusion for Smart Healthcare: Mapping the Journey from Data to Wisdom. Inf Fusion 102:102040","journal-title":"Inf Fusion"},{"key":"11815_CR29","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1016\/j.inffus.2021.06.007","volume":"76","author":"G Muhammad","year":"2021","unstructured":"Muhammad G, Alshehri F, Karray F, El-Saddik A, Alsulaiman M, Falk TH (2021) A Comprehensive Survey on Multimodal Medical Signals Fusion for Smart Healthcare Systems. Inf Fusion 76:355\u2013375","journal-title":"Inf Fusion"},{"key":"11815_CR30","doi-asserted-by":"crossref","first-page":"133583","DOI":"10.1109\/ACCESS.2019.2941419","volume":"7","author":"Q Cai","year":"2019","unstructured":"Cai Q, Wang H, Li Z, Liu X (2019) A Survey on Multimodal Data-Driven Smart Healthcare Systems: Approaches and Applications. IEEE Access 7:133583\u2013133599","journal-title":"IEEE Access"},{"key":"11815_CR31","unstructured":"Kirchner EA, Fairclough SH, Kirchner F. Embedded Multimodal Interfaces in Robotics: Applications, Future Trends, and Societal Implications"},{"key":"11815_CR32","doi-asserted-by":"crossref","unstructured":"Lee MA, Zhu Y, Srinivasan K, Shah P, Savarese S, Fei-Fei L, et al. (2019) Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Tasks. In: International Conference on Robotics and Automation, ICRA 2019, May 20-24, 2019. Montreal, QC, Canada. p. 8943\u20138950","DOI":"10.1109\/ICRA.2019.8793485"},{"issue":"3","key":"11815_CR33","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1109\/MMUL.2006.63","volume":"13","author":"MR Naphade","year":"2006","unstructured":"Naphade MR, Smith JR, Tesic J, Chang S, Hsu WH, Kennedy LS et al (2006) Large-Scale Concept Ontology for Multimedia. IEEE Multim 13(3):86\u201391","journal-title":"IEEE Multim"},{"issue":"2","key":"11815_CR34","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","volume":"41","author":"T Baltrusaitis","year":"2019","unstructured":"Baltrusaitis T, Ahuja C, Morency L (2019) Multimodal Machine Learning: A Survey and Taxonomy. IEEE Trans Pattern Anal Mach Intell 41(2):423\u2013443","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11815_CR35","doi-asserted-by":"crossref","unstructured":"Stahlschmidt SR, Ulfenborg B, Synnergren J (2022) Multimodal Deep Learning for Biomedical Data Fusion: A Review. Briefings Bioinform. 23(2)","DOI":"10.1093\/bib\/bbab569"},{"key":"11815_CR36","doi-asserted-by":"crossref","unstructured":"Snoek C, Worring M, Smeulders AWM (2005). Early versus late fusion in semantic video analysis. Singapore, pp 399\u2013402","DOI":"10.1145\/1101149.1101236"},{"key":"11815_CR37","doi-asserted-by":"crossref","unstructured":"Gadzicki K, Khamsehashari R, Zetzsche C (2020) Early vs Late Fusion in Multimodal Convolutional Neural Networks. In: IEEE 23rd International Conference on Information Fusion, FUSION 2020. Rustenburg, South Africa. p. 1\u20136","DOI":"10.23919\/FUSION45008.2020.9190246"},{"key":"11815_CR38","doi-asserted-by":"crossref","unstructured":"Gadzicki K, Khamsehashari R, Zetzsche C (2020) Early vs late fusion in multimodal convolutional neural networks. In: IEEE 23rd international conference on information fusion (FUSION). IEEE 2020:1\u20136","DOI":"10.23919\/FUSION45008.2020.9190246"},{"key":"11815_CR39","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1007\/s00530-010-0182-0","volume":"16","author":"PK Atrey","year":"2010","unstructured":"Atrey PK, Hossain MA, El Saddik A, Kankanhalli MS (2010) Multimodal fusion for multimedia analysis: a survey. Multimedia Syst 16:345\u2013379","journal-title":"Multimedia Syst"},{"issue":"4","key":"11815_CR40","doi-asserted-by":"crossref","first-page":"669","DOI":"10.1007\/s11517-020-02136-6","volume":"58","author":"SP Yadav","year":"2020","unstructured":"Yadav SP, Yadav S (2020) Image fusion using hybrid methods in multimodality medical images. Medical & biological engineering & computing 58(4):669\u2013687","journal-title":"Medical & biological engineering & computing"},{"key":"11815_CR41","unstructured":"Socher R, Ganjoo M, Manning CD (2013) Ng A Zero-shot learning through cross-modal transfer. Advances in neural information processing systems. 26"},{"key":"11815_CR42","doi-asserted-by":"crossref","unstructured":"Tan H, Bansal M (2020) Vokenization: Improving language understanding with contextualized, visual-grounded supervision. arXiv preprint arXiv:2010.06775","DOI":"10.18653\/v1\/2020.emnlp-main.162"},{"key":"11815_CR43","doi-asserted-by":"crossref","unstructured":"Pham H, Liang PP, Manzini T, Morency LP, P\u00f3czos B (2019) Found in translation: Learning robust joint representations by cyclic translations between modalities. pp 6892\u20136899","DOI":"10.1609\/aaai.v33i01.33016892"},{"key":"11815_CR44","doi-asserted-by":"crossref","unstructured":"Liu F, Wu X, Ge S, Fan W, Zou Y (2020) Federated Learning for Vision-and-Language Grounding Problems. In: The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, IAAI 2020, The Tenth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2020. New York, NY, USA. p. 11572\u201311579","DOI":"10.1609\/aaai.v34i07.6824"},{"key":"11815_CR45","doi-asserted-by":"crossref","unstructured":"Le HQ, Nguyen MN, Thwal CM, Qiao Y, Zhang C, Hong CS (2023) FedMEKT: Distillation-based Embedding Knowledge Transfer for Multimodal Federated Learning. arXiv preprint. arxiv:2307.13214","DOI":"10.2139\/ssrn.4641403"},{"key":"11815_CR46","unstructured":"Yu Q, Liu Y, Wang Y, Xu K, Liu J. Multimodal Federated Learning via Contrastive Representation Ensemble. Kigali, Rwanda"},{"key":"11815_CR47","doi-asserted-by":"crossref","unstructured":"Ouyang X, Xie Z, Fu H, Cheng S, Pan L, Ling N, Harmony, et al (2023). Heterogeneous Multi-Modal Federated Learning through Disentangled Model Training. Applications and Services, Helsinki, Finland, pp 530\u2013543","DOI":"10.1145\/3581791.3596844"},{"key":"11815_CR48","doi-asserted-by":"crossref","unstructured":"Feng T, Bose D, Zhang T, Hebbar R, Ramakrishna A, Gupta R, et al (2023) FedMultimodal: A Benchmark For Multimodal Federated Learning. arXiv preprint. arxiv:2306.09486","DOI":"10.1145\/3580305.3599825"},{"key":"11815_CR49","doi-asserted-by":"crossref","first-page":"970","DOI":"10.3390\/s23020970","volume":"23","author":"MU Alam","year":"2023","unstructured":"Alam MU, Rahmani R (2023) FedSepsis: A Federated Multi-Modal Deep Learning-Based Internet of Medical Things Application for Early Detection of Sepsis from Electronic Health Records Using Raspberry Pi and Jetson Nano Devices. Sensors 23:970","journal-title":"Sensors"},{"key":"11815_CR50","doi-asserted-by":"crossref","unstructured":"Liu P, Jiang L, Lin H, Hu J, Garg S, Alrashoud M (2023) Federated Multimodal Learning for Privacy-Preserving Driver Break Recommendations in Consumer Electronics. IEEE Transactions on Consumer Electronics","DOI":"10.1109\/TCE.2023.3339630"},{"key":"11815_CR51","unstructured":"Hinton G, Vinyals O, Dean J (2015) Distilling the Knowledge in a Neural Network. arXiv preprint. arxiv:1503.02531"},{"key":"11815_CR52","doi-asserted-by":"crossref","unstructured":"Feng J, Wang Z, Wei Z, Li Y, Ding B, Xu H (2024) Federated Heterogeneous Contrastive Distillation for Molecular Representation Learning. pp 1038\u20131048","DOI":"10.1145\/3627673.3679725"},{"key":"11815_CR53","doi-asserted-by":"crossref","unstructured":"Chen J, Zhang A (2024) On Disentanglement of Asymmetrical Knowledge Transfer for Modality-Task Agnostic Federated Learning. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a038, p. 11311\u201311319","DOI":"10.1609\/aaai.v38i10.29010"},{"key":"11815_CR54","unstructured":"Chen J, Zhang A (2024) FedMBridge: Bridgeable Multimodal Federated Learning. In: Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27. OpenReview.net; 2024. p. 1\u20136. Available from: https:\/\/openreview.net\/forum?id=jrHUbftLd6"},{"key":"11815_CR55","doi-asserted-by":"crossref","unstructured":"Zhao Y, Barnaghi PM (2022) Haddadi H. Multimodal Federated Learning on IoT Data. In: Seventh IEEE\/ACM International Conference on Internet-of-Things Design and Implementation, IoTDI 2022. Milano, Italy. p. 43\u201354","DOI":"10.1109\/IoTDI54339.2022.00011"},{"key":"11815_CR56","doi-asserted-by":"crossref","unstructured":"Song H, Wang J, Zhou J, Wang L (2024) Tackling Modality-Heterogeneous Client Drift Holistically for Heterogeneous Multimodal Federated Learning. IEEE Transactions on Medical Imaging","DOI":"10.1109\/TMI.2024.3523378"},{"key":"11815_CR57","doi-asserted-by":"crossref","unstructured":"Chen J, Zhang A (2022) FedMSplit: Correlation-Adaptive Federated Multi-Task Learning across Multimodal Split Networks. In: KDD \u201922: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2022. Washington, DC, USA. p. 87\u201396","DOI":"10.1145\/3534678.3539384"},{"key":"11815_CR58","doi-asserted-by":"crossref","unstructured":"Tan Y, Long G, Liu L, Zhou T, Lu Q, Jiang J, et al (2022) Fedproto: Federated prototype learning across heterogeneous clients. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a036, p. 8432\u20138440","DOI":"10.1609\/aaai.v36i8.20819"},{"key":"11815_CR59","doi-asserted-by":"crossref","first-page":"29677","DOI":"10.52202\/068431-2152","volume":"35","author":"S Alam","year":"2022","unstructured":"Alam S, Liu L, Yan M, Zhang M (2022) Fedrolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction. Adv Neural Inf Process Syst 35:29677\u201329690","journal-title":"Adv Neural Inf Process Syst"},{"key":"11815_CR60","first-page":"101890","volume-title":"Piccialli F","author":"P Qi","year":"2023","unstructured":"Qi P, Chiaro D (2023) Piccialli F. Federated Learning-Based Fall Detection with Multimodal Data Fusion. Inf Fusion, FL-FD, p 101890"},{"key":"11815_CR61","doi-asserted-by":"crossref","first-page":"340","DOI":"10.1016\/j.ymeth.2022.03.005","volume":"204","author":"A Nandi","year":"2022","unstructured":"Nandi A, Xhafa F (2022) A Federated Learning Method for Real-Time Emotion State Classification from Multi-Modal Streaming. Methods 204:340\u2013347","journal-title":"Methods"},{"key":"11815_CR62","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2024.106353","volume":"94","author":"N Gahlan","year":"2024","unstructured":"Gahlan N, Sethia D (2024) AFLEMP: Attention-based Federated Learning for Emotion recognition using Multi-modal Physiological data. Biomed Signal Process Control 94:106353","journal-title":"Biomed Signal Process Control"},{"issue":"2","key":"11815_CR63","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","volume":"41","author":"T Baltru\u0161aitis","year":"2018","unstructured":"Baltru\u0161aitis T, Ahuja C, Morency LP (2018) Multimodal machine learning: A survey and taxonomy. IEEE Trans Pattern Anal Mach Intell 41(2):423\u2013443","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11815_CR64","doi-asserted-by":"crossref","unstructured":"Yu S, Wang J, Hussein W, Hung PC (2023) Robust Multimodal Federated Learning for Incomplete Modalities. Computer Communications","DOI":"10.1016\/j.comcom.2023.12.003"},{"key":"11815_CR65","doi-asserted-by":"crossref","unstructured":"Yu S, Yang Q, Wang J, Wu C (2024) FedUSL: A Federated Annotation Method for Driving Fatigue Detection based on Multimodal Sensing Data. ACM Transactions on Sensor Networks","DOI":"10.1145\/3657291"},{"key":"11815_CR66","doi-asserted-by":"crossref","unstructured":"Zhang J, Huang J, Jin S, Lu S (2024) Vision-language models for vision tasks: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"11815_CR67","doi-asserted-by":"crossref","unstructured":"Bano S, Tonellotto N, Cassar\u00e0 P, Gotta A. FedCMD: A Federated Cross-Modal Knowledge Distillation for Drivers Emotion Recognition. ACM Transactions on Intelligent Systems and Technology. 2024","DOI":"10.1145\/3650040"},{"key":"11815_CR68","doi-asserted-by":"crossref","unstructured":"Wang J, Xie G, Huang Y, Zheng Y, Jin Y, FedMed-ATL ZF (2022). Misaligned Unpaired Cross-Modality Neuroimage Synthesis via Affine Transform Loss. Lisboa, Portugal, pp 1522\u20131531","DOI":"10.1145\/3503161.3547762"},{"key":"11815_CR69","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1109\/OJCS.2022.3206407","volume":"3","author":"A Qayyum","year":"2022","unstructured":"Qayyum A, Ahmad K, Ahsan MA, Al-Fuqaha AI, Qadir J (2022) Collaborative Federated Learning for Healthcare: Multi-Modal COVID-19 Diagnosis at the Edge. IEEE Open J Comput Soc 3:172\u2013184","journal-title":"IEEE Open J Comput Soc"},{"key":"11815_CR70","doi-asserted-by":"crossref","unstructured":"Zhou H, Wang S, Jiang C, Zhang X, Guo L, Yuan Y (2023) Waste Not, Want Not: Service Migration-Assisted Federated Intelligence for Multi-Modality Mobile Edge Computing. pp 211\u2013220","DOI":"10.1145\/3565287.3610277"},{"issue":"11","key":"11815_CR71","first-page":"1","volume":"20","author":"CF Hsu","year":"2024","unstructured":"Hsu CF, Li YC, Tsai CC, Wang JK, Hsu CH (2024) Federated Learning Using Multi-Modal Sensors with Heterogeneous Privacy Sensitivity Levels. ACM Trans Multimed Comput Commun Appl 20(11):1\u201327","journal-title":"ACM Trans Multimed Comput Commun Appl"},{"key":"11815_CR72","doi-asserted-by":"crossref","unstructured":"Yang X, Xiong B, Huang Y, Xu C (2022) Cross-Modal Federated Human Activity Recognition via Modality-Agnostic and Modality-Specific Representation Learning. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a036. Virtual Event. p. 3063\u20133071","DOI":"10.1609\/aaai.v36i3.20213"},{"key":"11815_CR73","doi-asserted-by":"crossref","unstructured":"Xiong B, Yang X, Song Y, Wang Y, Xu C (2023). Client-Adaptive Cross-Model Reconstruction Network for Modality-Incomplete Multimodal Federated Learning. Ottawa, ON, Canada, pp 1241\u20131249","DOI":"10.1145\/3581783.3611757"},{"key":"11815_CR74","doi-asserted-by":"crossref","unstructured":"Zheng T, Li A, Chen Z, Wang H, Luo J (2023) AutoFed: Heterogeneity-Aware Federated Multimodal Learning for Robust Autonomous Driving. arXiv preprint. axriv:2302.08646","DOI":"10.1145\/3570361.3592517"},{"key":"11815_CR75","doi-asserted-by":"crossref","first-page":"1030","DOI":"10.1109\/JIOT.2020.3009358","volume":"8","author":"A Saeed","year":"2020","unstructured":"Saeed A, Salim FD, Ozcelebi T, Lukkien J (2020) Federated Self-Supervised Learning of Multisensor Representations for Embedded Intelligence. IEEE Internet Things J 8:1030\u20131040","journal-title":"IEEE Internet Things J"},{"key":"11815_CR76","doi-asserted-by":"crossref","unstructured":"Agbley BLY, Li J, Haq AU, Bankas EK, Ahmad S, Agyemang IO, et al (2021) Multimodal Melanoma Detection with Federated Learning. In: 2021 18th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP). Chengdu, China. p. 238\u2013244","DOI":"10.1109\/ICCWAMTIP53232.2021.9674116"},{"key":"11815_CR77","doi-asserted-by":"crossref","unstructured":"Salehi B, Gu J, Roy D, Chowdhury KRFLASH (2022). Federated Learning for Automated Selection of High-band mmWave Sectors. United Kingdom, London, pp 1719\u20131728","DOI":"10.1109\/INFOCOM48880.2022.9796865"},{"key":"11815_CR78","doi-asserted-by":"crossref","unstructured":"Tan M, Feng Y, Chu L, Shi J, Xiao R, Tang H, et al (2023) FedSea: Federated Learning via Selective Feature Alignment for Non-IID Multimodal Data. IEEE Transactions on Multimedia","DOI":"10.1109\/TMM.2023.3340109"},{"key":"11815_CR79","doi-asserted-by":"crossref","unstructured":"Dai Q, Wei D, Liu H, Sun J, Wang L, Zheng Y (2024) Federated Modality-specific Encoders and Multimodal Anchors for Personalized Brain Tumor Segmentation. arXiv preprint.;arxiv:2403.11803","DOI":"10.1609\/aaai.v38i2.27909"},{"issue":"10","key":"11815_CR80","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1038\/s41591-021-01506-3","volume":"27","author":"I Dayan","year":"2021","unstructured":"Dayan I, Roth HR, Zhong A, Harouni A, Gentili A, Abidin AZ et al (2021) Federated Learning for Predicting Clinical Outcomes in Patients with COVID-19. Nat Med 27(10):1735\u20131743","journal-title":"Nat Med"},{"key":"11815_CR81","unstructured":"Zhang R, Chi X, Liu G, Zhang W, Du Y, Wang F (2023) Unimodal Training-Multimodal Prediction: Cross-modal Federated Learning with Hierarchical Aggregation. arXiv preprint. arxiv:2303.15486"},{"key":"11815_CR82","doi-asserted-by":"crossref","unstructured":"Chen S, Li B (2022). Towards Optimal Multi-Modal Federated Learning on Non-IID Data with Hierarchical Gradient Blending. London, United Kingdom, pp 1469\u20131478","DOI":"10.1109\/INFOCOM48880.2022.9796724"},{"key":"11815_CR83","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1016\/j.neucom.2022.01.063","volume":"480","author":"B Xiong","year":"2022","unstructured":"Xiong B, Yang X, Qi F, Xu C (2022) A Unified Framework for Multi-modal Federated Learning. Neurocomputing 480:110\u2013118","journal-title":"Neurocomputing"},{"issue":"7","key":"11815_CR84","doi-asserted-by":"crossref","first-page":"4788","DOI":"10.1109\/TII.2021.3113708","volume":"18","author":"X Xu","year":"2021","unstructured":"Xu X, Peng H, Bhuiyan MZA, Hao Z, Liu L, Sun L et al (2021) Privacy-Preserving Federated Depression Detection From Multisource Mobile Health Data. IEEE Trans Industr Inf 18(7):4788\u20134797","journal-title":"IEEE Trans Industr Inf"},{"key":"11815_CR85","unstructured":"Yu H, Chen Z, Zhang X, Chen X, Zhuang F, Xiong H, et al (2021) FedHAR: Semi-Supervised Online Learning for Personalized Federated Human Activity Recognition. IEEE Transactions on Mobile Computing"},{"key":"11815_CR86","doi-asserted-by":"crossref","unstructured":"Wang Bq, Yang F, Wang Y, Zhao F, Han Yf, Ma Yp (2025) Federated Learning for Fall Detection with Multimodal Residual Fusion and Pareto-Optimized Client Selection. IEEE Access","DOI":"10.1109\/ACCESS.2025.3553419"},{"key":"11815_CR87","doi-asserted-by":"crossref","DOI":"10.1016\/j.comcom.2025.108152","volume":"237","author":"G Rjoub","year":"2025","unstructured":"Rjoub G, Elmekki H, Islam S, Bentahar J, Dssouli R (2025) A hybrid swarm intelligence approach for optimizing Multimodal Large Language Models deployment in edge-cloud-based Federated Learning environments. Comput Commun 237:108152","journal-title":"Comput Commun"},{"key":"11815_CR88","volume":"113","author":"J Chen","year":"2024","unstructured":"Chen J, Pan R (2024) Medical Report Generation Based on Multimodal Federated Learning. Comput Med Imaging Graph 113:102342","journal-title":"Comput Med Imaging Graph"},{"key":"11815_CR89","doi-asserted-by":"crossref","unstructured":"Chen H, Zhang Y, Krompass D, Gu J, Tresp V (2024) Feddat: an Approach for Foundation Model Finetuning in Multi-Modal Heterogeneous Federated Learning. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a038, p. 11285\u201311293","DOI":"10.1609\/aaai.v38i10.29007"},{"key":"11815_CR90","doi-asserted-by":"crossref","unstructured":"Saha P, Mishra D, Wagner F, Kamnitsas K, Noble JA (2025) Fedpia\u2013permuting and integrating adapters leveraging wasserstein barycenters for finetuning foundation models in multi-modal federated learning. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a039, p. 20228\u201320236","DOI":"10.1609\/aaai.v39i19.34228"},{"key":"11815_CR91","doi-asserted-by":"crossref","unstructured":"Chen D, Tang S, Shen Z, Wang G, Xiao J, Zhuang Y et al (2023) FedAA: Using Non-sensitive Modalities to Improve Federated Learning while Preserving Image Privacy. pp 3796\u20133806","DOI":"10.1145\/3581783.3611953"},{"key":"11815_CR92","doi-asserted-by":"crossref","unstructured":"Zong L, Xie Q, Zhou J, Wu P, Zhang X, Fedcmr XB (2021). Federated Cross-Modal Retrieval. Virtual Event, Canada, pp 1672\u20131676","DOI":"10.1145\/3404835.3462989"},{"issue":"4","key":"11815_CR93","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1007\/s11280-024-01249-4","volume":"27","author":"A Li","year":"2024","unstructured":"Li A, Li Y, Shao Y (2024) Federated Learning for Supervised Cross-Modal Retrieval. World Wide Web 27(4):41","journal-title":"World Wide Web"},{"key":"11815_CR94","doi-asserted-by":"crossref","unstructured":"Zhou X, Yang Q, Zheng X, Liang W, Kevin I, Wang K, et al (2024) Personalized Federation Learning with Model-Contrastive Learning for Multi-Modal User Modeling in Human-Centric Metaverse. IEEE Journal on Selected Areas in Communications","DOI":"10.1109\/JSAC.2023.3345431"},{"key":"11815_CR95","doi-asserted-by":"crossref","unstructured":"Yan B, Chen Q, Chen Y, Jiang X, Huang W, Wang B et al (2024) Buffalo: Biomedical Vision-Language Understanding with Cross-Modal Prototype and Federated Foundation Model Collaboration. pp 2775\u20132785","DOI":"10.1145\/3627673.3679627"},{"key":"11815_CR96","doi-asserted-by":"crossref","unstructured":"Le HQ, Thwal CM, Qiao Y, Tun YL, Nguyen MN, Huh EN, et al (2025) Cross-modal prototype based multimodal federated learning under severely missing modality. Information Fusion. p. 103219","DOI":"10.1016\/j.inffus.2025.103219"},{"issue":"9","key":"11815_CR97","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3674507","volume":"20","author":"R Zuo","year":"2024","unstructured":"Zuo R, Zheng C, Li F, Zhu L, Zhang Z (2024) Privacy-Enhanced Prototype-Based Federated Cross-Modal Hashing for Cross-Modal Retrieval. ACM Trans Multimed Comput Commun Appl 20(9):1\u201319","journal-title":"ACM Trans Multimed Comput Commun Appl"},{"key":"11815_CR98","doi-asserted-by":"crossref","unstructured":"Zuo R, Zheng C, Zhu L, Lu W, Xiang Y, Li Z, et al (2025) Learning Together Securely: Prototype-Based Federated Multi-Modal Hashing for Safe and Efficient Multi-Modal Retrieval. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a039, p. 23108\u201323116","DOI":"10.1609\/aaai.v39i21.34475"},{"key":"11815_CR99","doi-asserted-by":"crossref","unstructured":"Li J, Li F, Zhu L, Cui H, Li J (2023) Prototype-Guided Knowledge Transfer for Federated Unsupervised Cross-Modal Hashing. pp 1013\u20131022","DOI":"10.1145\/3581783.3613837"},{"key":"11815_CR100","doi-asserted-by":"crossref","unstructured":"Che L, Wang J, Liu X, Ma F (2024) Leveraging Foundation Models for Multi-modal Federated Learning with Incomplete Modality. In: Bifet A, Krilavicius T, Miliou I, Nowaczyk S, editors. Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track - European Conference, ECML PKDD 2024, Vilnius, Lithuania, September 9-13, 2024, Proceedings, Part IX. vol. 14949 of Lecture Notes in Computer Science. Springer. p. 401\u2013417. Available from: https:\/\/doi.org\/10.1007\/978-3-031-70378-2_25","DOI":"10.1007\/978-3-031-70378-2_25"},{"key":"11815_CR101","unstructured":"Liang PP, Liu T, Liu Z, Salakhutdinov R, Morency L (2020) Think Locally, Act Globally: Federated Learning with Local and Global Representations. arXiv preprint. arxiv:2001.01523"},{"key":"11815_CR102","doi-asserted-by":"crossref","unstructured":"Liu Y, Wang C, FedMobile YX (2025, 2025,) Enabling Knowledge Contribution-aware Multi-modal Federated Learning with Incomplete Modalities. pp 2775\u20132786","DOI":"10.1145\/3696410.3714623"},{"key":"11815_CR103","unstructured":"Reddi S, Charles Z, Zaheer M, Garrett Z, Rush K, Kone\u010dn\u1ef3 J, et al (2020) Adaptive Federated Optimization. arXiv preprint. arxiv:2003.00295"},{"key":"11815_CR104","first-page":"429","volume":"2","author":"T Li","year":"2020","unstructured":"Li T, Sahu AK, Zaheer M, Sanjabi M, Talwalkar A, Smith V (2020) Federated Optimization in Heterogeneous Networks. Proceedings of Machine Learning and Systems 2:429\u2013450","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"11815_CR105","doi-asserted-by":"crossref","unstructured":"Barata C, Celebi ME, Marques JS, Melanoma detection algorithm based on feature fusion. In, (2015) 37th Annual international conference of the IEEE engineering in medicine and biology society (EMBC). IEEE 2015:2653\u20132656","DOI":"10.1109\/EMBC.2015.7318937"},{"issue":"6","key":"11815_CR106","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1109\/MSP.2017.2738401","volume":"34","author":"D Ramachandram","year":"2017","unstructured":"Ramachandram D, Taylor GW (2017) Deep Multimodal Learning: a Survey on Recent Advances and Trends. IEEE Signal Process Mag 34(6):96\u2013108","journal-title":"IEEE Signal Process Mag"},{"key":"11815_CR107","doi-asserted-by":"crossref","unstructured":"Yang HM, Zhang XY, Yin F, Liu CL (2018) Robust classification with convolutional prototype learning. pp 3474\u20133482","DOI":"10.1109\/CVPR.2018.00366"},{"key":"11815_CR108","unstructured":"Snell J, Swersky K, Zemel R (2017) Prototypical networks for few-shot learning. Advances in neural information processing systems. 30"},{"issue":"6","key":"11815_CR109","doi-asserted-by":"crossref","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","volume":"129","author":"J Gou","year":"2021","unstructured":"Gou J, Yu B, Maybank SJ, Tao D (2021) Knowledge distillation: A survey. Int J Comput Vision 129(6):1789\u20131819","journal-title":"Int J Comput Vision"},{"key":"11815_CR110","doi-asserted-by":"crossref","unstructured":"Li C, Liu W (2023) Multimodal Transport Demand Forecasting via Federated Learning. IEEE Transactions on Intelligent Transportation Systems","DOI":"10.1109\/TITS.2023.3325936"},{"key":"11815_CR111","doi-asserted-by":"crossref","unstructured":"Qi F, Li S (2024) Adaptive Hyper-graph Aggregation for Modality-Agnostic Federated Learning. pp 12312\u201312321","DOI":"10.1109\/CVPR52733.2024.01170"},{"key":"11815_CR112","doi-asserted-by":"crossref","unstructured":"Yang X, Xiong B, Huang Y, Xu C (2024) Cross-Modal Federated Human Activity Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence","DOI":"10.1109\/TPAMI.2024.3367412"},{"key":"11815_CR113","doi-asserted-by":"crossref","unstructured":"Li S, Qi F, Zhang Z, Xu C (2024) Cross-Modal Meta Consensus for Heterogeneous Federated Learning. pp 975\u2013984","DOI":"10.1145\/3664647.3681510"},{"key":"11815_CR114","doi-asserted-by":"crossref","unstructured":"Ouyang X, Shuai X, Li Y, Pan L, Zhang X, Fu H et al (2024) ADMarker: A Multi-Modal Federated Learning System for Monitoring Digital Biomarkers of Alzheimer\u2019s Disease. pp 404\u2013419","DOI":"10.1145\/3636534.3649370"},{"key":"11815_CR115","doi-asserted-by":"crossref","unstructured":"Poudel P, Shrestha P, Amgain S, Shrestha YR, Gyawali P, Bhattarai BCAR-MFL (2024) Cross-Modal Augmentation by Retrieval for Multimodal Federated Learning with Missing Modalities. pp 102\u2013112","DOI":"10.1007\/978-3-031-72117-5_10"},{"key":"11815_CR116","doi-asserted-by":"crossref","unstructured":"Wang S, Qu Z, Liu Y, Kan S, Liang Y, FedMMR WJ (2024) Multi-Modal Federated Learning via Missing Modality Reconstruction. pp 1\u20136","DOI":"10.1109\/ICME57554.2024.10688162"},{"key":"11815_CR117","doi-asserted-by":"crossref","unstructured":"Yan Y, Feng CM, Li Y, Li P, Goh RSM, Lei B, et al (2025) Federated pseudo modality generation for incomplete multi-modal mri reconstruction. IEEE Journal of Biomedical and Health Informatics","DOI":"10.1109\/JBHI.2025.3566217"},{"key":"11815_CR118","doi-asserted-by":"crossref","unstructured":"Guo J, Fu Y, Zhai Z, Li X, Deng Y, Yue S, et al (2025) MASA: Multimodal Federated Learning through Modality-Aware and Secure Aggregation. IEEE Transactions on Mobile Computing","DOI":"10.1109\/TMC.2025.3548954"},{"key":"11815_CR119","doi-asserted-by":"crossref","unstructured":"Yan Y, Wang H, Huang Y, He N, Zhu L, Xu Y, et al (2024) Cross-Modal Vertical Federated Learning for MRI Reconstruction. IEEE Journal of Biomedical and Health Informatics","DOI":"10.1109\/JBHI.2024.3360720"},{"key":"11815_CR120","unstructured":"Bernecker T, Peters A, Schlett CL, Bamberg F, Theis FJ, Rueckert D, et al (2022) FedNorm: Modality-Based Normalization in Federated Learning for Multi-Modal Liver Segmentation. arXiv preprint. arxiv:2205.11096"},{"issue":"21","key":"11815_CR121","doi-asserted-by":"publisher","first-page":"34055","DOI":"10.1109\/JIOT.2024.3443267","volume":"11","author":"Y Peng","year":"2024","unstructured":"Peng Y, Wu Y, Bian J, Xu J (2024) Hybrid Federated Learning for Multimodal IoT Systems. IEEE Internet Things J 11(21):34055\u201334064. https:\/\/doi.org\/10.1109\/JIOT.2024.3443267","journal-title":"IEEE Internet Things J"},{"key":"11815_CR122","doi-asserted-by":"crossref","unstructured":"Feng T, Zhang T, Avestimehr S, ModalityMirror NS (2025) Enhancing Audio Classification in Modality Heterogeneity Federated Learning via Multimodal Distillation. pp 78\u201383","DOI":"10.1145\/3712678.3721885"},{"key":"11815_CR123","doi-asserted-by":"crossref","first-page":"40844","DOI":"10.1109\/ACCESS.2025.3548001","volume":"13","author":"SM Sheikholeslami","year":"2025","unstructured":"Sheikholeslami SM, Ng PC, Abouei J, Plataniotis KN (2025) Multi-Modal Federated Learning Over Cell-Free Massive MIMO Systems for Activity Recognition. IEEE Access 13:40844\u201340858","journal-title":"IEEE Access"},{"key":"11815_CR124","unstructured":"Yuan L, Han DJ, Chellapandi VP, \u017bak SH, Brinton CG (2023) FedMFS: Federated Multimodal Fusion Learning with Selective Modality Communication. arXiv preprint. arxiv:2310.07048"},{"key":"11815_CR125","doi-asserted-by":"crossref","unstructured":"Fan Y, Xu W, Wang H, Huo F, Chen J, Guo S (2024) Overcome Modal Bias in Multi-modal Federated Learning via Balanced Modality Selection. In: European Conference on Computer Vision. p. 178\u2013195","DOI":"10.1007\/978-3-031-73004-7_11"},{"key":"11815_CR126","doi-asserted-by":"crossref","unstructured":"Gao M, Zheng H, Du M, Feng X (2024) Multimodal Fusion With Block Term Decomposition for Asynchronous Federated Learning. IEEE Transactions on Industrial Informatics","DOI":"10.1109\/TII.2024.3441634"},{"key":"11815_CR127","doi-asserted-by":"crossref","unstructured":"Gao M, Zheng H, Feng X, Tao R (2025) Multimodal Fusion Using Multi-View Domains for Data Heterogeneity in Federated Learning. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a039, p. 16736\u201316744","DOI":"10.1609\/aaai.v39i16.33839"},{"key":"11815_CR128","doi-asserted-by":"crossref","unstructured":"Nie X, Yi L, Yang LT, Deng X, Fan F, Zhang H (2024) Tensor Dynamic Fusion Based Modality-Imbalanced Multimodal Federated Learning in Mobile Edge Computing for Consumer Applications. IEEE Transactions on Consumer Electronics","DOI":"10.1109\/TCE.2024.3470243"},{"key":"11815_CR129","doi-asserted-by":"crossref","unstructured":"Thapa C, Arachchige PCM, Camtepe S, Sun L (2022) Splitfed: When Federated Learning Meets Split Learning. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a036. Virtual Event; p. 8485\u20138493","DOI":"10.1609\/aaai.v36i8.20825"},{"key":"11815_CR130","unstructured":"Deecke L, Murray I, Bilen H. (2018) Mode Normalization. arXiv preprint. arxiv:1810.05466"},{"key":"11815_CR131","unstructured":"Ioffe S, Batch SC, Normalization, (2015). Accelerating Deep Network Training by Reducing Internal Covariate Shift. Lille, France, pp 448\u2013456"},{"issue":"1","key":"11815_CR132","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","volume":"2","author":"SM Lundberg","year":"2020","unstructured":"Lundberg SM, Erion G, Chen H, DeGrave A, Prutkin JM, Nair B et al (2020) From Local Explanations to Global Understanding with Explainable AI for Trees. Nature Machine Intelligence 2(1):56\u201367","journal-title":"Nature Machine Intelligence"},{"key":"11815_CR133","unstructured":"Sundararajan M, Najmi A (2020) The Many Shapley Values for Model Explanation. In: International Conference on Machine Learning. Virtual Event. p. 9269\u20139278"},{"key":"11815_CR134","doi-asserted-by":"crossref","unstructured":"Wang X, Wang H, Wu F, Liu T, Cao Q, Su L (2024) Towards Efficient Heterogeneous Multi-Modal Federated Learning with Hierarchical Knowledge Disentanglement. pp 592\u2013605","DOI":"10.1145\/3666025.3699360"},{"key":"11815_CR135","unstructured":"Ha D, Dai A, Le QV (2016) Hypernetworks. arXiv preprint arXiv:1609.09106"},{"key":"11815_CR136","doi-asserted-by":"crossref","unstructured":"Ha Q, Watanabe K, Karasawa T, Ushiku Y, Harada T (2017) MFNet: Towards Real-Time Semantic Segmentation for Autonomous Vehicles with Multi-Spectral Scenes. pp 5108\u20135115","DOI":"10.1109\/IROS.2017.8206396"},{"key":"11815_CR137","doi-asserted-by":"crossref","first-page":"133583","DOI":"10.1109\/ACCESS.2019.2941419","volume":"7","author":"Q Cai","year":"2019","unstructured":"Cai Q, Wang H, Li Z, Liu X (2019) A Survey on Multimodal Data Driven Smart Healthcare Systems Approaches and Applications. IEEE Access 7:133583\u2013133599","journal-title":"IEEE Access"},{"key":"11815_CR138","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2021.106970","volume":"223","author":"SK Yadav","year":"2021","unstructured":"Yadav SK, Tiwari K, Pandey HM, Akbar SA (2021) A Review of Multimodal Human Activity Recognition with Special Emphasis on Classification Applications Challenges and Future Directions. Knowl-Based Syst 223:106970","journal-title":"Knowl-Based Syst"},{"key":"11815_CR139","doi-asserted-by":"crossref","unstructured":"Li XC, Fedrs ZDC (2021). Federated Learning with Restricted Softmax for Label Distribution Non-IID Data. Virtual Event, Singapore, pp 995\u20131005","DOI":"10.1145\/3447548.3467254"},{"key":"11815_CR140","unstructured":"Karimireddy SP, Kale S, Mohri M, Reddi S, Stich S, Scaffold SAT (2020) Stochastic controlled averaging for federated learning. pp 5132\u20135143"},{"issue":"4","key":"11815_CR141","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3631455","volume":"7","author":"Y Djebrouni","year":"2024","unstructured":"Djebrouni Y, Benarba N, Touat O, De Rosa P, Bouchenak S, Bonifati A et al (2024) Bias Mitigation in Federated Learning for Edge Computing. Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies 7(4):1\u201335","journal-title":"Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies"},{"key":"11815_CR142","doi-asserted-by":"crossref","first-page":"237802312096717","DOI":"10.1177\/2378023120967171","volume":"6","author":"C Schwemmer","year":"2020","unstructured":"Schwemmer C, Knight C, Bello-Pardo ED, Oklobdzija S, Schoonvelde M, Lockhart JW (2020) Diagnosing Gender Bias in Image Recognition Systems. Socius 6:2378023120967171","journal-title":"Socius"},{"issue":"1","key":"11815_CR143","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3517253","volume":"6","author":"D Li","year":"2022","unstructured":"Li D, Liu J, Lee SI, Xiong J (2022) Lasense: Pushing the Limits of Fine-Grained Activity Sensing Using Acoustic Signals. Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies 6(1):1\u201327","journal-title":"Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies"},{"issue":"25","key":"11815_CR144","doi-asserted-by":"crossref","first-page":"2477","DOI":"10.1056\/NEJMc2029240","volume":"383","author":"MW Sjoding","year":"2020","unstructured":"Sjoding MW, Dickson RP, Iwashyna TJ, Gay SE, Valley TS (2020) Racial Bias in Pulse Oximetry Measurement. N Engl J Med 383(25):2477\u20132478","journal-title":"N Engl J Med"},{"key":"11815_CR145","doi-asserted-by":"crossref","unstructured":"Booth BM, Hickman L, Subburaj SK, Tay L, Woo SE (2021). D\u2019Mello SK. Bias and Fairness in Multimodal Machine Learning: a Case Study of Automated Video Interviews. Montreal, QC, Canada, pp 268\u2013277","DOI":"10.1145\/3462244.3479897"},{"key":"11815_CR146","doi-asserted-by":"crossref","unstructured":"Srinivasan T, Bisk Y (2021) Worst of Both Worlds: Biases Compound in Pre-Trained Vision-And-Language Models. arXiv preprint. arxiv:2104.08666","DOI":"10.18653\/v1\/2022.gebnlp-1.10"},{"key":"11815_CR147","unstructured":"Ross C, Katz B, Barbu A (2020) Measuring Social Biases in Grounded Vision and Language Embeddings. arXiv preprint. arxiv:2002.08911"},{"key":"11815_CR148","doi-asserted-by":"crossref","unstructured":"Yan S, Huang D, Soleymani M (2020). Mitigating Biases in Multimodal Personality Assessment. The Netherlands, pp 361\u2013369","DOI":"10.1145\/3382507.3418889"},{"key":"11815_CR149","first-page":"3197","volume":"33","author":"I Gat","year":"2020","unstructured":"Gat I, Schwartz I, Schwing A, Hazan T (2020) Removing Bias in Multi-Modal Classifiers: Regularization by Maximizing Functional Entropies. Adv Neural Inf Process Syst 33:3197\u20133208","journal-title":"Adv Neural Inf Process Syst"},{"key":"11815_CR150","unstructured":"Mohri M, Sivek G, Suresh AT (2019) Agnostic Federated Learning. International Conference on Machine Learning. Long Beach, California, USA, pp 4615\u20134625"},{"issue":"4","key":"11815_CR151","doi-asserted-by":"crossref","first-page":"2039","DOI":"10.1109\/TNSE.2022.3169117","volume":"9","author":"Z Hu","year":"2022","unstructured":"Hu Z, Shaloudegi K, Zhang G, Yu Y (2022) Federated Learning Meets Multi-Objective Optimization. IEEE Transactions on Network Science and Engineering 9(4):2039\u20132051","journal-title":"IEEE Transactions on Network Science and Engineering"},{"key":"11815_CR152","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1007\/978-3-030-63076-8_14","volume-title":"Collaborative Fairness in Federated Learning","author":"L Lyu","year":"2020","unstructured":"Lyu L, Xu X, Wang Q, Yu H (2020) Collaborative Fairness in Federated Learning. Privacy and Incentive, Federated Learning, pp 189\u2013204"},{"key":"11815_CR153","doi-asserted-by":"crossref","unstructured":"Yu H, Liu Z, Liu Y, Chen T, Cong M, Weng X et al (2020). A Fairness-Aware Incentive Scheme for Federated Learning. and Society, New York, NY, USA, pp 393\u2013399","DOI":"10.1145\/3375627.3375840"},{"key":"11815_CR154","doi-asserted-by":"crossref","unstructured":"Agrawal A, Batra D, Parikh D (2016) Analyzing the Behavior of Visual Question Answering Models. arXiv preprint arXiv:1606.07356;","DOI":"10.18653\/v1\/D16-1203"},{"key":"11815_CR155","doi-asserted-by":"crossref","unstructured":"Liang PP, Cheng Y, Fan X, Ling CK, Nie S, Chen R, et al (2024) Quantifying & Modeling Multimodal Interactions: an Information Decomposition Framework. Advances in Neural Information Processing Systems. 36","DOI":"10.52202\/075280-1192"},{"key":"11815_CR156","doi-asserted-by":"crossref","unstructured":"Tolpegin V, Truex S, Gursoy ME, Data LL, Systems PAAFL, In: Computer Security-ESORICS, (2020) 25th European Symposium on Research in Computer Security, ESORICS 2020, Proceedings, Part I 25. Guildford UK 2020:480\u2013501","DOI":"10.1007\/978-3-030-58951-6_24"},{"issue":"6","key":"11815_CR157","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3460427","volume":"54","author":"X Yin","year":"2021","unstructured":"Yin X, Zhu Y, Hu J (2021) A Comprehensive Survey of Privacy-Preserving Federated Learning: a Taxonomy, Review, and Future Directions. ACM Computing Surveys (CSUR) 54(6):1\u201336","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"11815_CR158","doi-asserted-by":"crossref","unstructured":"Tolpegin V, Truex S, Gursoy ME, Data LL, Systems PAAFL, In: Computer security-ESORICs, (2020) 25th European symposium on research in computer security, ESORICs 2020, guildford, UK, September 14\u201318, 2020, proceedings, part i 25. Springer 2020:480\u2013501","DOI":"10.1007\/978-3-030-58951-6_24"},{"key":"11815_CR159","doi-asserted-by":"crossref","unstructured":"Ko M, Jin M, Wang C, Jia R (2023) Practical membership inference attacks against large-scale multi-modal models: A pilot study. pp 4871\u20134881","DOI":"10.1109\/ICCV51070.2023.00449"},{"key":"11815_CR160","doi-asserted-by":"crossref","unstructured":"Lai Y, Wu L, Lin H, Liu J (2025) Bad-MFL: A Cross-Modality Bi-Trigger Backdoor Attack Against Multi-Modal Federated Learning. IEEE Internet of Things Journal","DOI":"10.1109\/JIOT.2025.3589136"},{"key":"11815_CR161","doi-asserted-by":"crossref","unstructured":"Abu Jabal A, Bertino E, Lobo J, Verma D, Calo S, Russo A (2023) Flap-a federated learning framework for attribute-based access control policies. pp 263\u2013272","DOI":"10.1145\/3577923.3583641"},{"key":"11815_CR162","unstructured":"Lalitha A, Shekhar S, Javidi T, Koushanfar F.: Fully Decentralized Federated Learning"},{"key":"11815_CR163","unstructured":"Hu C, Jiang J, Wang Z (2019) Decentralized Federated Learning: A Segmented Gossip Approach. arXiv preprint. arxiv:1908.07782"},{"key":"11815_CR164","doi-asserted-by":"crossref","unstructured":"Yin B, Chen Z, Tao M (2024) Knowledge distillation and training balance for heterogeneous decentralized multi-modal learning over wireless networks. IEEE Transactions on Mobile Computing","DOI":"10.1109\/TMC.2024.3364673"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-025-11815-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-025-11815-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-025-11815-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T05:05:39Z","timestamp":1783055139000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-025-11815-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,27]]},"references-count":164,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["11815"],"URL":"https:\/\/doi.org\/10.1007\/s00521-025-11815-0","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,27]]},"assertion":[{"value":"29 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"425"}}