The DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index.
FedSN: A Federated Learning Framework Over Heterogeneous LEO Satellite Networks
Open accessPublished version of a preprint
Abstract
Recently, a large number of Low Earth Orbit (LEO) satellites have been launched and deployed successfully in space. Due to multimodal sensors equipped by the LEO satellites, they serve not only for communications but also for various machine learning applications. However, a ground station (GS) may be incapable of downloading such a large volume of raw sensing data for centralized model training due to the limited contact time with LEO satellites (e.g. 5 minutes). Therefore,federated learning(FL) has emerged as the promising solution to address this problem via on-device training. Unfortunately, enabling FL on LEO satellites still face three critical challenges: i) heterogeneous computing and memory capabilities, ii) limited downlink/uplink rate, and iii) model staleness. To this end, we proposeFedSNas a general FL framework to tackle the above challenges. Specifically, we first present a novel sub-structure scheme to enable heterogeneous local model training considering different computing, memory, and communication constraints on LEO satellites. Additionally, we propose a pseudo-synchronous model aggregation strategy to dynamically schedule model aggregation for compensating model staleness. Extensive experiments with real-world satellite data demonstrate that FedSN framework achieves higher accuracy, lower computing, and communication overhead than the state-of-the-art benchmarks.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Zagoruyko, S., & Komodakis, N. (2016) · Procedings of the British Machine Vision Conference 2016 · doi:10.5244/c.30.87 · Cited by 7,244
A Joint Learning and Communications Framework for Federated Learning over Wireless Networks
Chen, M., Yang, Z., Saad, W., Yin, C., Poor, H. V., & Cui, S. (2019) · arXiv · doi:10.48550/arxiv.1909.07972 · Cited by 1,547
A Joint Learning and Communications Framework for Federated Learning Over Wireless Networks
Chen, M., Yang, Z., Saad, W., Yin, C., Poor, H. V., & Cui, S. (2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2020.3024629 · Cited by 1,547
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 · cited 1×
“It is relatively easy to train deep learning models using plen-tiful data in terrestrial networks in a timely and synchronous fashion [9], [10], [11], [12], [13].”
Spatial analysis and GIS in the study of COVID-19. A review
Franch-Pardo, I., Napoletano, B. M., Rosete-Verges, F., & Billa, L. (2020) · Science of The Total Environment · doi:10.1016/j.scitotenv.2020.140033 · Cited by 655
Xu, J., & Wang, H. (2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2020.3031503 · Cited by 466
Duggen, S., Croot, P., Schacht, U., & Hoffmann, L. (2007) · Geophysical Research Letters · doi:10.1029/2006gl027522 · Cited by 283
Helber, P., Bischke, B., Dengel, A., & Borth, D. (2018) · IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium · doi:10.1109/igarss.2018.8519248 · Cited by 232
Split Learning in 6G Edge Networks
Lin, Z., Qu, G., Chen, X., & Huang, K. (2024) · IEEE Wireless Communications · doi:10.1109/mwc.014.2300319 · Cited by 199
Self-citationEfficient Parallel Split Learning Over Resource-Constrained Wireless Edge Networks
Lin, Z., Zhu, G., Deng, Y., Chen, X., Gao, Y., Huang, K., & Fang, Y. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3359040 · Cited by 165
Self-citationVasisht, D., Shenoy, J., & Chandra, R. (2021) · ACM SIGCOMM Conference (SIGCOMM) · doi:10.1145/3452296.3472932 · Cited by 149
Using ground relays for low-latency wide-area routing in megaconstellations
Handley, M. J. (2019) · ACM Workshop on Hot Topics in Networks (HotNets) · doi:10.1145/3365609.3365859 · Cited by 133
RF-Based Human Activity Recognition Using Signal Adapted Convolutional Neural Network
Chen, Z., Cai, C., Zheng, T., Luo, J., Xiong, J., & Wang, X. (2021) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2021.3073969 · Cited by 125
Self-citationGround-Assisted Federated Learning in LEO Satellite Constellations
Razmi, N., Matthiesen, B., Dekorsy, A., & Popovski, P. (2022) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2022.3141120 · Cited by 124
Object Detection Based on VGG with ResNet Network
Haque, M. F., Lim, H.-Y., & Kang, D.-S. (2019) · International Conference on Electronics, Information, and Communication (ICEIC) · doi:10.23919/elinfocom.2019.8706476 · Cited by 98
CubeSats Enable High Spatiotemporal Retrievals of Crop-Water Use for Precision Agriculture
Aragon, B., Houborg, R., Tu, K. P., Fisher, J. B., & McCabe, M. F. (2018) · Remote Sensing · doi:10.3390/rs10121867 · Cited by 92
The Digital Divide in Canada and the Role of LEO Satellites in Bridging the Gap
Ahmmed, T., Shamsabadi, A. A., Zhang, Z., Chaudhry, A. U., & Yanıkömeroğlu, H. (2022) · IEEE Communications Magazine · doi:10.1109/mcom.001.2100795 · Cited by 70
Optimal Resource Allocation for U-Shaped Parallel Split Learning
Lyu, S., Lin, Z., Qu, G., Chen, X., Huang, X., & Li, P. (2023) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshps58843.2023.10465123 · Cited by 67
Self-citationFederated Learning Over Multihop Wireless Networks With In-Network Aggregation
Chen, X., Zhu, G., Deng, Y., & Fang, Y. M. (2022) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2022.3168538 · Cited by 66
Self-citationAutomated Federated Pipeline for Parameter-Efficient Fine-Tuning of Large Language Models
Fang, Z., Lin, Z., Chen, Z., Chen, X., Gao, Y., & Fang, Y. M. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3649881 · Cited by 63
Self-citationTech giants race to build orbital internet [News]
(2018) · doi:10.1109/mspec.2018.8362213 · Cited by 53
Robust Task Scheduling for Delay-Aware IoT Applications in Civil Aircraft-Augmented SAGIN
Chen, Q., Meng, W., Han, S., Li, C., & Chen, H. (2022) · IEEE Transactions on Communications · doi:10.1109/tcomm.2022.3186997 · Cited by 52
Accelerating Handover in Mobile Satellite Network
Wu, J., Su, S., Wang, X., Zhang, J., & Gao, Y. (2024) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom52122.2024.10621115 · Cited by 46
Self-citationElmahallawy, M., & Luo, T. (2022) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata55660.2022.10021101 · Cited by 45
FedHAP: Fast Federated Learning for LEO Constellations using Collaborative HAPs
Elmahallawy, M., & Luo, T. (2022) · International Conference on Wireless Communications and Signal Processing (WCSP) · doi:10.1109/wcsp55476.2022.10039157 · Cited by 42
Scheduling for Ground-Assisted Federated Learning in LEO Satellite Constellations
Razmi, N., Matthiesen, B., Dekorsy, A., & Popovski, P. (2022) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco55093.2022.9909556 · Cited by 30
FedGSM: Efficient Federated Learning for LEO Constellations with Gradient Staleness Mitigation
Wu, L., & Zhang, J. (2023) · IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) · doi:10.1109/spawc53906.2023.10304545 · Cited by 23
Shukla, S., Macharia, D., Husak, G. J., Landsfeld, M. F., Nakalembe, C., Blakeley, S. L., Adams, E. C., & Way-Henthorne, J. (2021) · Frontiers in Sustainable Food Systems · doi:10.3389/fsufs.2021.504063 · Cited by 9
Graph Learning for Multi-Satellite based Spectrum Sensing
Yuan, H., Chen, Z., Lin, Z., Peng, J., Fang, Z., Zhong, Y., Song, Z., Wang, X., & Gao, Y. (2023) · IEEE International Conference on Communication Technology (ICCT) · doi:10.1109/icct59356.2023.10419549 · Cited by 7
Self-citation
Research works printed but not linked: 7
- McMahan, Communication-efficient learning of deep networks from decentralized data, 1273
- Simonyan, Very deep convolutional networks for large-scale image recognition
- Devaraj, Planet high speed radio: Crossing Gbps from a 3U CubeSat
- Hubert, 2002, Linux advanced routing & traffic control HOWTO, Netherlabs BV, 1, 99
- Tan, Efficientnet: Rethinking model scaling for convolutional neural networks, 6105
- Diao, HeteroFL: Computation and communication efficient federated learning for heterogeneous clients
- Krizhevsky, ImageNet classification with deep convolutional neural networks, 1106
Metadata
- Authors
- Lin, Z., Chen, Z., Fang, Z., Chen, X., Wang, X., & Gao, Y.
- Affiliations
- Fudan University (CN)
- University of Hong Kong (HK)
- Venue
- IEEE Transactions on Mobile Computing
- Published
- 2025-03
- Volume
- 24
- Issue
- 3
- Pages
- 1293-1307
- ISSN
- 1536-1233 (ISSN-L)
- 1558-0660
- 2161-9875
- OpenAlex
- W4403420278
- Cited by
- 66
- References
- 29
- Citations by year
- 2026: 27 · 2025: 31
- FWCI
- 9.74
- Type
- journal article
- Language
- en
- Open access
- green
- doi.org
- Licence
- Locations
- IEEE Transactions on Mobile Computing (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- The HKU Scholars Hub (University of Hong Kong) (submittedVersion, cc-by-nc-nd)
- arXiv (Cornell University)
- Funders
- National Key R&D Program of China (2023YFE0116600)
- Research Grants Council of Hong Kong (27213824)
- HKU IDS Research Seed Fund (IDS-RSF2023-0012)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Engineering › Aerospace Engineering › Satellite Communication Systems
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Keywords
- federated learning, low Earth orbit satellites, heterogeneous computing, model staleness, on-device learning, communication constraints, satellite networks
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
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.