MASA: Multimodal Federated Learning Through Modality-Aware and Secure Aggregation
IEEE Transactions on Mobile Computing · 2025-08 · 24 (8) · 7328-7344
DOI: 10.1109/tmc.2025.3548954 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2025-08. Verfasst von Jialin Guo und 8 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Postdoctoral Innovative Talent Support Program, China Postdoctoral Science Foundation.
Abstract (Originalsprache)
As a promising paradigm, federated learning has been applied to multimodal sensing tasks due to its deployment convenience. However, the recent advances in multimodal federated learning emphasize learning a high-quality multimodal model but overlook the model usage requirements of massive unimodal clients. Moreover, the privacy risk in model sharing and client data heterogeneity impact the efficacy of federated learning. In this paper, we propose a novel multimodal federated learning system named MASA. As a departure from existing approaches, MASA simultaneously enhances the model learning efficiency of both multimodal and unimodal clients while ensuring their data privacy. First, we employ a gated cross-modal distillation scheme to achieve performance-aware knowledge transfer across modality-heterogeneous clients. To enhance the system security, MASA integrates a lightweight split-shuffle mechanism to realize the anonymization and encryption of model aggregation. Moreover, to reach personalized collaboration while protecting privacy, MASA features an attention-based spontaneous client clustering mechanism to form client cluster structures securely and distributedly. We evaluate our MASA on four public multimodal datasets for human activity recognition. The results show that our MASA outperforms leading multimodal federated learning methods on the model performance of both multimodal and unimodal clients.
Förderung
- National Natural Science Foundation of China
- Postdoctoral Innovative Talent Support Program
- China Postdoctoral Science Foundation
Zitieren
APA
Guo, J., Fu, Y., Zhai, Z., Li, X., Deng, Y., Yue, S., Chen, L., Pan, H., & Ren, J. (2025). MASA: Multimodal Federated Learning Through Modality-Aware and Secure Aggregation. IEEE Transactions on Mobile Computing, 24(8), 7328-7344. https://doi.org/10.1109/tmc.2025.3548954
Vancouver
Guo J, Fu Y, Zhai Z, Li X, Deng Y, Yue S, et al. MASA: Multimodal Federated Learning Through Modality-Aware and Secure Aggregation. IEEE Transactions on Mobile Computing. 2025;24(8):7328-7344. doi:10.1109/tmc.2025.3548954
BibTeX
@article{Guo2025,
author = {Guo, Jialin and Fu, Yongjian and Zhai, Zhiwei and Li, Xinyi and Deng, Yongheng and Yue, Sheng and Chen, Lili and Pan, Hao and Ren, Ju},
title = {MASA: Multimodal Federated Learning Through Modality-Aware and Secure Aggregation},
journal = {IEEE Transactions on Mobile Computing},
year = {2025},
volume = {24},
number = {8},
pages = {7328--7344},
doi = {10.1109/tmc.2025.3548954}
}
EUVIMED