CoChat
Sign Up
Cited by 86Privacy-Preserving Technologies in DataIoT and Edge/Fog ComputingInternet of Things and AI

Federated Learning for Resource-Constrained IoT Devices: Panoramas and State of the Art

Open access
Imteaj, Ahmed, Mamun Ahmed, Khandaker, Thakker, Urmish, Wang, Shiqiang, Li, Jian, Amini, M. Hadi·2023·Adaptation, Learning, and Optimization
DOI 10.1007/978-3-031-11748-0_2
Open this paper in CoChat — free accountOpen PDF

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1007/978-3-031-11748-0_2

Cites

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

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?

  • There are mainly three types of federated learning: horizontal, vertical, and transfer learning.

    “There are mainly three types of federated learning: horizontal , vertical , and transfer learning [95].”

    From Machine Unlearning: A Survey (2024) · cites this paper as [95]

    The Background of Federated Learning (p. 2) describes how federated learning works but does not classify its types. Federated Learning Applications (p. 2) mentions combining federated learning with transfer learning, but does not identify horizontal, vertical, and transfer learning as its three main types. Searches for those terms found no passage stating the claimed classification. (LLM, conf=0.72)

    Experimental — accuracy not yet measured

  • Imteaj et al. [95] show that model providers are more likely to receive requests to remove specific samples from a model trained in a federated learning setting.

    “Imteaj et al. [95] show that model providers are more likely to receive requests to remove specific samples from a model trained in a federated learning setting.”

    From Machine Unlearning: A Survey (2024) · cites this paper as [95]

    The Background of Federated Learning (p. 2) describes training on local samples and aggregating model updates, but does not discuss requests to remove samples. A search for sample-removal requests and machine unlearning found no passage supporting the claim that model providers are more likely to receive such requests in federated learning. (LLM, conf=0.72)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

The citation lists haven’t been fetched yet

References 69 · Cited by 86

Research works printed but not linked: 29

  1. [Bonawitz et al. , 2019] Keith Bonawitz, Eichner, et al. Towards federated learning at scale: System design. arXiv preprint arXiv:1902.01046 , 2019. · arXiv
  2. [Chen et al. , 2018] Fei Chen, Zhenhua Dong, et al. Federated meta-learning for recommendation. arXiv:1802.07876 , 2018. · arXiv
  3. [Chen et al. , 2019] Mingzhe Chen, Zhaohui Yang, et al. A joint learning and communications framework for federated learning over wireless networks. arXiv:1909.07972 , 2019. · arXiv
  4. [Cui et al. , 2018] Laizhong Cui, Shu Yang, et al. A survey on application of machine learning for internet of things. J. M. L. Cybernetics , 9(8):1399-1417, 2018.
  5. [Gu et al. , 2019] Zhongshu Gu, Hani Jamjoom, et al. Reaching data confidentiality and model accountability on the caltrain. In IEEE DSN , 2019.
  6. [Guha et al. , 2019] Neel Guha, Ameet Talwlkar, et al. Oneshot federated learning. arXiv:1902.11175 , 2019. · arXiv
  7. [Haddadpour et al. , 2019] Farzin Haddadpour, Mohammad Mahdi Kamani, et al. Trading redundancy for communication: Speeding up distributed sgd for nonconvex optimization. In ICML , 2019.
  8. [Hard et al. , 2018] Andrew Hard, Kanishka Rao, Rajiv Mathews, Ramaswamy, et al. Federated learning for mobile keyboard prediction. arXiv:1811.03604 , 2018. · arXiv
  9. [Huang and others, 2013] Junxian Huang et al. An in-depth study of lte: effect of network protocol and application behavior on performance. ACM SIGCOMM CCR , 43(4):363-374, 2013.
  10. [Huang et al. , 2018] Li Huang, Yifeng Yin, et al. Loadaboost: Loss-based adaboost federated machine learning on medical data. arXiv:1811.12629 , 2018. · arXiv
  11. [Jiang et al. , 2019] Yuang Jiang, Shiqiang Wang, et al. Model pruning enables efficient federated learning on edge devices. arXiv:1909.12326 , 2019. · arXiv
  12. [Kim et al. , 2019] Hyesung Kim, Jihong Park, et al. Blockchained on-device federated learning. IEEE Communications Letters , 2019.
  13. [Koneˇ cn` y et al. , 2016] Jakub Koneˇ cn` y, H Brendan McMahan, et al. Federated learning: Strategies for improving communication efficiency. arXiv:1610.05492 , 2016. · arXiv
  14. [Kumar et al. , 2017] Ashish Kumar, Saurabh Goyal, et al. Resource-efficient machine learning in 2 kb ram for the internet of things. In ICML , 2017.
  15. [Li et al. , 2018] HeLi, Kaoru Ota, et al. Learning iot in edge: Deep learning for the internet of things with edge computing. IEEE network , 32(1):96-101, 2018.
  16. [Li et al. , 2019] Tian Li, Anit Kumar Sahu, et al. Federated learning: Challenges, methods, and future directions. arXiv:1908.07873 , 2019. · arXiv
  17. [Lim et al. , 2019] Wei Yang Bryan Lim, Nguyen Cong Luong, et al. Federated learning in mobile edge networks: A comprehensive survey. arXiv:1909.11875 , 2019. · arXiv
  18. [Ma et al. , 2017] Chenxin Ma, Jakub Koneˇ cn` y, et al. Distributed optimization with arbitrary local solvers. Optimization Methods and Software , 32(4):813-848, 2017.
  19. [Park et al. , 2019] Jihong Park, Shiqiang Wang, et al. Distilling on-device intelligence at the network edge. arXiv:1908.05895 , 2019. · arXiv
  20. [Sprague et al. , 2018] Michael R Sprague, Amir Jalalirad, et al. Asynchronous federated learning for geospatial applications. In ECML-PKDD , 2018.
  21. [Thakker et al. , 2019] Urmish Thakker, Jesse Beu, et al. Compressing rnns for iot devices by 15-38x using kronecker products. arXiv preprint arXiv:1906.02876 , 2019. · arXiv
  22. [Wang et al. , 2019] Shiqiang Wang, Tiffany Tuor, et al. Adaptive federated learning in resource constrained edge computing systems. IEEE JSAC , 37(6):1205-1221, 2019.
  23. [Wu et al. , 2018] Shuang Wu, Guoqi Li, et al. Training and inference with integers in deep neural networks. arXiv:1802.04680 , 2018. · arXiv
  24. [Xu et al. , 2019a] Zichen Xu, Li Li, et al. Exploring federated learning on battery-powered devices. In ACM TURC , 2019.
  25. [Xu et al. , 2019b] Zirui Xu, Zhao Yang, et al. Elfish: Resource-aware federated learning on heterogeneous edge devices. arXiv:1912.01684 , 2019. · arXiv
  26. [Xu et al. , 2020] Ronghua Xu, Yu Chen, and Jian Li. MicroFL: A lightweight, secure-by-design edge network fabric for decentralized IoT systems. In NDSS , 2020.
  27. [Yang et al. , 2018] Timothy Yang, Galen Andrew, et al. Applied federated learning: Improving google keyboard query suggestions. arXiv:1812.02903 , 2018. · arXiv
  28. [Yang et al. , 2019] Qiang Yang, Yang Liu, et al. Federated machine learning: Concept and applications. ACM Trans. on TIST , 10(2):12, 2019.
  29. [Zhang et al. , 2015] Yuchen Zhang, John Duchi, et al. Divide and conquer kernel ridge regression: A distributed algorithm with minimax optimal rates. JMLR , 16(1):32993340, 2015.

Authors
Imteaj, A., Mamun Ahmed, K., Thakker, U., Wang, S., Li, J., & Amini, M. H.
Affiliations
  • Florida International University (US)
  • IBM (United States) (US)
  • Binghamton University (US)
Corresponding author
Amini, M. Hadi
ORCID
Venue
Adaptation, Learning, and Optimization
Publisher
Springer International Publishing
Published
2022-10-01
Pages
7-27
ISSN
  • 1867-4534 (ISSN-L)
  • 1867-4542
DOI
10.1007/978-3-031-11748-0_2
OpenAlex
W3008856552
Cited by
86
References
69
Citations by year
2026: 5 · 2025: 19 · 2024: 25 · 2023: 15 · 2022: 9 · 2021: 9 · 2020: 4
FWCI
31.57
Type
book chapter
Language
en
Open access
Licence
Locations
  • Adaptation, learning, and optimization (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
  • Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
  • Physical Sciences › Computer Science › Information Systems › Internet of Things and AI
Keywords
federated learning, resource-constrained devices, Internet of Things, edge computing, decentralized learning, energy constraints, memory constraints, bandwidth constraints, privacy preservation, scalability

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