Delay Analysis of Wireless Federated Learning Based on Saddle Point Approximation and Large Deviation Theory
The DOI matches its Crossref record; 60 of the 60 references it cites were found in a registry or an index.
Abstract
Federated learning (FL) is a collaborative machine learning paradigm, which enables deep learning model training over a large volume of decentralized data residing in mobile devices without accessing clients’ private data. Driven by the ever increasing demand for model training of mobile applications or devices, a vast majority of FL tasks are implemented over wireless fading channels. Due to the time-varying nature of wireless channels, however, random delay occurs in both the uplink and downlink transmissions of FL. How to analyze the overall time consumption of a wireless FL task, or more specifically, a FL’s delay distribution, becomes a challenging but important open problem, especially for delay-sensitive model training. In this paper, we present a unified framework to calculate the approximate delay distributions of FL over arbitrary fading channels. Specifically, saddle point approximation, extreme value theory (EVT), and large deviation theory (LDT) are jointly exploited to find the approximate delay distribution along with its tail distribution, which characterizes the quality-of-service of a wireless FL system. Simulation results will demonstrate that our approximation method achieves a small approximation error, which vanishes with the increase of training accuracy.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Li et al. characterized the delay distribution for FL over arbitrary fading channels via the saddle point approximation method and large deviation theory [89].”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [89]
Citations
Cites
Communication-Efficient Learning of Deep Networks from Decentralized Data
McMahan, H. B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. Y. (2016) · arXiv · doi:10.48550/arxiv.1602.05629 · Cited by 14,215
Federated learning: Challenges, methods, and future directions
Li, T., Sahu, A. K., Talwalkar, A., & Smith, V. (2020) · IEEE Signal Processing Magazine · doi:10.1109/msp.2020.2975749 · Cited by 6,210 · cited 1×
“However, the deployment of FL in wireless networks, poses unique challenges in terms of system heterogeneity, statistical heterogeneity, and trustworthiness [9], [10].”
BackgroundA Survey on Mobile Edge Computing: The Communication Perspective
Mao, Y., You, C., Zhang, J., Huang, K., & Letaief, K. B. (2017) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2017.2745201 · Cited by 5,607 · cited 1×
“Meanwhile, as the computational power and storage of mobile devices keep growing, mobile edge computing (MEC) [2] is becoming a crucial technology for future networks to enable ultra-low power and ultra-low latency applications at the edge [3].”
BackgroundSelf-citationA Vision of 6G Wireless Systems: Applications, Trends, Technologies, and Open Research Problems
Saad, W., Bennis, M., & Chen, M. (2020) · IEEE Network · doi:10.1109/mnet.001.1900287 · Cited by 4,985 · cited 1×
“FL thus becomes a key technique to support the paradigm shift from “connected things” to “connected intelligence” in 6G, where humans, things, and intelligence are intertwined within a hyper-connected cyber-physical world [4], [5].”
Higher Transcendental Functions.
Truesdell, C., Bateman, H., Erdelyi, A., Magnus, W., Oberhettinger, F., & Tricomi, F. G. (1954) · The American Mathematical Monthly · doi:10.2307/2307622 · Cited by 4,393
Federated Learning in Mobile Edge Networks: A Comprehensive Survey
Lim, W. Y. B., Luong, N. C., Hoang, D. T., Jiao, Y., Liang, Y.-C., Yang, Q., Niyato, D., & Miao, C. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.2986024 · Cited by 2,565
Adaptive Federated Learning in Resource Constrained Edge Computing Systems
Wang, S., Tuor, T., Salonidis, T., Leung, K. K., Makaya, C., He, T., & Chan, K. (2019) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2019.2904348 · Cited by 2,232 · cited 2×
“, the training bottleneck caused by the slowest participating devices) [22]–[28], resource allocation for improving the transmission efficiency [27]–[30], adaptive aggregation for dynamically controlling the aggregation frequency [31] or calibrating aggregation weights [32], batchsize selection for improving learning…”
BackgroundThe Roadmap to 6G: AI Empowered Wireless Networks
Letaief, K. B., Chen, W., Shi, Y., Zhang, J., & Zhang, Y.-J. A. (2019) · IEEE Communications Magazine · doi:10.1109/mcom.2019.1900271 · Cited by 2,207
Self-citationThe Asymptotic Theory of Extreme Order Statistics
Angus, J. E. (1990) · Technometrics · doi:10.1080/00401706.1990.10484616 · Cited by 1,830
Federated Optimization: Distributed Machine Learning for On-Device Intelligence
Konečný, J., McMahan, H. B., Ramage, D., & Richtárik, P. (2016) · arXiv · doi:10.48550/arxiv.1610.02527 · Cited by 1,563 · cited 2×
“We shall adopt the FL algorithm in [29], [42] and [43] as presented in Alg.”
BackgroundMethod
Research works printed but not linked: 1
- lecun, 1998, The MNIST Database of Handwritten Digits
Cited by
Edge artificial intelligence for 6g: vision, enabling technologies, and applications
Letaief, K. B., Shi, Y., Lu, J., & Lu, J. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3126076 · Cited by 829
“Li et al. characterized the delay distribution for FL over arbitrary fading channels via the saddle point approximation method and large deviation theory [89].”
MethodSelf-citationMachine Learning for Large-Scale Optimization in 6G Wireless Networks
Shi, Y., Lian, L., Shi, Y., Wang, Z., Zhou, Y., Fu, L., Bai, L., Zhang, J., & Zhang, W. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3300664 · Cited by 205
“The practical orthogonal frequency division multiple access (OFDMA) and FDMA techniques are adopted to support interference-free uplink local model transmission and downlink global model transmission in [166], [167] through orthogonalized frequency allocation, which could increase the communication latency instead.”
MethodSelf-citationTrustworthy Federated Learning via Blockchain
Yang, Z., Shi, Y., Zhou, Y., Wang, Z., & Yang, K. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3201117 · Cited by 122
“Specifically, Li et al. [27] characterized the delay distribution for FL over arbitrary fading channels via the saddle point approximation method and large deviation theory.”
BackgroundMethodSelf-citationCommunication-efficient distributed learning: An overview
Cao, X., Başar, T., Diggavi, S., Eldar, Y. C., Letaief, K. B., Poor, H. V., & Zhang, J. (2023) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2023.3242710 · Cited by 139
“proposed in [178], and the delay of FL was analyzed in [179].”
BackgroundSelf-citationFederated Learning via Unmanned Aerial Vehicle
Fu, M., Shi, Y., & Zhou, Y. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3303492 · Cited by 105
“Moreover, in digital synchronous FL [8], [11], communication stragglers significantly slow down the model aggregation process and dominate cumulative communication delay since the PS must wait until receiving the training updates from all participants.”
BackgroundMethodSelf-citation
Metadata
- Authors
- Li, L., Yang, L., Guo, X., Shi, Y., Wang, H., Chen, W., & Letaief, K. B.
- Affiliations
- Beijing National Research Center for Information Science and Technology (CN)
- Lenovo (China) (CN)
- ShanghaiTech University (CN)
- Hong Kong University of Science and Technology (HK)
- Venue
- IEEE Journal on Selected Areas in Communications
- Published
- 2021-12
- Volume
- 39
- Issue
- 12
- Pages
- 3772-3789
- ISSN
- 0733-8716 (ISSN-L)
- 1558-0008
- OpenAlex
- W3202461677
- Cited by
- 37
- References
- 59
- Citations by year
- 2025: 8 · 2024: 6 · 2023: 11 · 2022: 7 · 2021: 5
- FWCI
- 2.56
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Journal on Selected Areas in Communications (publishedVersion)
- Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
- Funders
- National Key Research and Development Program of China (2018YFA0701601)
- National Natural Science Foundation of China (61971264)
- Beijing Natural Science Foundation (4191001)
- Hong Kong Research Grant Council of the Hong Kong Telecom Institute of Information Technology
- Lenovo Research
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Wireless Communication Technologies
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Keywords
- wireless federated learning, delay distribution, saddlepoint approximation, large deviations, extreme value theory, fading channels, tail distribution, quality of service, decentralized learning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Delay Analysis of Wireless Federated Learning Based on Saddle Point Approximation and Large Deviation Theory. https://app.cochat.ai/papers/10.1109/jsac.2021.3118431
- The paper
- Li, L., Yang, L., Guo, X., Shi, Y., Wang, H., Chen, W., & Letaief, K. B. (2021). Delay Analysis of Wireless Federated Learning Based on Saddle Point Approximation and Large Deviation Theory. IEEE Journal on Selected Areas in Communications. https://doi.org/10.1109/jsac.2021.3118431
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.