Efficient Mobile-Cloud Collaborative Aggregation for Federated Learning With Latency Resilience
IEEE Transactions on Mobile Computing · 2026-05 · 25 (5) · 7391-7407
DOI: 10.1109/tmc.2025.3642433 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2026-05. Verfasst von Wei Tang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Engineering Research Center of Oil & Gas Exploration Computer Software, Natural Science Foundation of Sichuan Province.
Abstract (Originalsprache)
With the rapid growth of mobile and edge computing, federated learning (FL) has emerged as a key technology to enable collaborative model training on mobile devices while preserving user privacy. Secure aggregation is an essential component in FL to protect local gradients and compute the global model, but it is vulnerable to threats from high-latency. When some clients arrive late, the pairwise masks among clients cannot be canceled properly, forcing the server to learn the late clients’ masks in order to complete the aggregation. As a result, network uncertainty puts the aggregation process at risk of either service interruption or privacy leakage. While double masking is treated as the most effective solution to achieve both robustness and privacy, its computational and communication costs are prohibitive, especially for resource-constrained mobile devices. To address these challenges, we propose an Efficient Mobile-Cloud Collaborative Aggregation for Federated Learning with Latency Resilience (EFL-LR). We leverage Shamir’s secret sharing and a key-homomorphic pseudorandom function to ensure privacy for high-latency clients while reducing computation overheads to $\mathcal {O}(n\log ^{2} n + d)$ O ( n log 2 n + d ) for clients and $\mathcal {O}(n+d)$ O ( n + d ) for the server. Formal security analysis confirms its latency resilience and privacy guarantees. Experimental results show that EFL-LR achieves 2– $3\times$ 3 × lower client-side computation cost and accelerates server-side aggregation recovery by at least $10\times$ 10 × .
Förderung
- National Natural Science Foundation of China
- National Engineering Research Center of Oil & Gas Exploration Computer Software
- Natural Science Foundation of Sichuan Province
Zitieren
APA
Tang, W., Li, J., Zhang, X., Miao, Y., Su, Z., & Deng, R. H. (2026). Efficient Mobile-Cloud Collaborative Aggregation for Federated Learning With Latency Resilience. IEEE Transactions on Mobile Computing, 25(5), 7391-7407. https://doi.org/10.1109/tmc.2025.3642433
Vancouver
Tang W, Li J, Zhang X, Miao Y, Su Z, Deng RH. Efficient Mobile-Cloud Collaborative Aggregation for Federated Learning With Latency Resilience. IEEE Transactions on Mobile Computing. 2026;25(5):7391-7407. doi:10.1109/tmc.2025.3642433
BibTeX
@article{Tang2026,
author = {Tang, Wei and Li, Jiliang and Zhang, Xiaojun and Miao, Yinbin and Su, Zhou and Deng, Robert H.},
title = {Efficient Mobile-Cloud Collaborative Aggregation for Federated Learning With Latency Resilience},
journal = {IEEE Transactions on Mobile Computing},
year = {2026},
volume = {25},
number = {5},
pages = {7391--7407},
doi = {10.1109/tmc.2025.3642433}
}
EUVIMED