AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Journal of Computer Science and Technology Article
Article Link
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Regular Paper

Age-of-Information-Aware Federated Learning

Yin Xu1,2, Ming-Jun Xiao1,2,3( ), Chen Wu3, Jie Wu4, Jin-Rui Zhou1,2, He Sun1,2
School of Computer Science and Technology, University of Science and Technology of China, Hefei 230026, China
Suzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou 215123, China
School of Data Science, University of Science and Technology of China, Hefei 230026, China
Department of Computer and Information Sciences, Temple University, Philadelphia, PA 19122, U.S.A.
Show Author Information

Abstract

Federated learning (FL) is an emerging privacy-preserving distributed computing paradigm, enabling numerous clients to collaboratively train machine learning models without the necessity of transmitting clients’ private datasets to the central server. Unlike most existing research where the local datasets of clients are assumed to be unchanged over time throughout the whole FL process, our study addresses such scenarios in this paper where clients’ datasets need to be updated periodically, and the server can incentivize clients to employ as fresh as possible datasets for local model training. Our primary objective is to design a client selection strategy to minimize the loss of the global model for FL loss within a constrained budget. To this end, we introduce the concept of ‘‘Age of Information’’ (AoI) to quantitatively assess the freshness of local datasets and conduct a theoretical analysis of the convergence bound in our AoI-aware FL system. Based on the convergence bound, we further formulate our problem as a restless multi-armed bandit (RMAB) problem. Next, we relax the RMAB problem and apply the Lagrangian Dual approach to decouple it into multiple subproblems. Finally, we propose a Whittle’s Index Based Client Selection (WICS) algorithm to determine the set of selected clients. In addition, comprehensive simulations substantiate that the proposed algorithm can effectively reduce training loss and enhance the learning accuracy compared with some state-of-the-art methods.

Keywords

federated learningAge of Informationrestless multi-armed banditWhittle’s index

Electronic Supplementary Material

Download File(s)
JCST-2311-13914-Highlights.pdf (162.4 KB)

References

[1]

Yang Q, Liu Y, Chen T T, Tong Y X. Federated machine learning: Concept and applications. ACM Trans. Intelligent Systems and Technology, 2019, 10(2): Article No. 12. DOI: 10.1145/3298981.
Crossref Google Scholar
[2]

Li T, Sahu A K, Talwalkar A, Smith V. Federated learning: Challenges, methods, and future directions. IEEE Signal Processing Magazine, 2020, 37(3): 50–60. DOI: 10.1109/MSP.2020.2975749.
Crossref Google Scholar
[3]
Shi Y F, Liu Y Q, Wei K, Shen L, Wang X Q, Tao D C. Make landscape flatter in differentially private federated learning. In Proc. the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2023, pp.24552-24562. DOI: 10.1109/CVPR52729.2023.02352.
Crossref
[4]

Antunes R S, da Costa C A, Küderle A, Yari I A, Eskofier B M. Federated learning for healthcare: Systematic review and architecture proposal. ACM Trans. Intelligent Systems and Technology, 2022, 13(4): Article No. 54. DOI: 10.1145/3501813.
Crossref Google Scholar
[5]

Wang Z B, Huang Y T, Song M K, Wu L B, Xue F, Ren K. Poisoning-assisted property inference attack against federated learning. IEEE Trans. Dependable and Secure Computing, 2023, 20(4): 3328–3340. DOI: 10.1109/TDSC.2022.3196646.
Crossref Google Scholar
[6]

Lim W Y B, Luong N C, Hoang D T, Jiao Y T, Liang Y C, Yang Q, Niyato D, Miao C Y. Federated learning in mobile edge networks: A comprehensive survey. IEEE Communications Surveys & Tutorials, 2020, 22(3): 2031–2063. DOI: 10.1109/COMST.2020.2986024.
Crossref Google Scholar
[7]
Karimireddy S P, Kale S, Mohri M, Reddi S J, Stich S U, Suresh A T. SCAFFOLD: Stochastic controlled averaging for federated learning. In Proc. the 37th International Conference on Machine Learning, Jul. 2020, Article No. 476.
[8]
Wu X D, Huang F H, Hu Z M, Huang H. Faster adaptive federated learning. In Proc. the 37th AAAI Conference on Artificial Intelligence, Feb. 2023, pp.10379–10387. DOI: 10.1609/AAAI.V37I9.26235.
Crossref
[9]
Wang H, Kaplan Z, Niu D, Li B C. Optimizing federated learning on Non-IID data with reinforcement learning. In Proc. the 2020 IEEE Conference on Computer Communications (INFOCOM), Jul. 2020, pp.1698–1707. DOI: 10.1109/INFOCOM41043.2020.9155494.
Crossref
[10]
Chen C, Xu H, Wang W, Li B C, Li B, Chen L, Zhang G. Communication-efficient federated learning with adaptive parameter freezing. In Proc. the 41st IEEE International Conference on Distributed Computing Systems (ICDCS), Jul. 2021, pp.1–11. DOI: 10.1109/ICDCS51616.2021.00010.
Crossref
[11]

Wang Z B, Ma J J, Wang X, Hu J H, Qin Z, Ren K. Threats to training: A survey of poisoning attacks and defenses on machine learning systems. ACM Computing Surveys, 2023, 55(7): 134. DOI: 10.1145/3538707.
Crossref Google Scholar
[12]
Zhang X L, Li F T, Zhang Z Y, Li Q, Wang C, Wu J P. Enabling execution assurance of federated learning at untrusted participants. In Proc. the 2020 IEEE Conference on Computer Communications (INFOCOM), Jul. 2020, pp.1877–1886. DOI: 10.1109/INFOCOM41043.2020.9155414.
Crossref
[13]

Yuan X Y, Ma X Y, Zhang L, Fang Y G, Wu D P. Beyond class-level privacy leakage: Breaking record-level privacy in federated learning. IEEE Internet of Things Journal, 2022, 9(4): 2555–2565. DOI: 10.1109/JIOT.2021.3089 713.
Crossref Google Scholar
[14]
Tran N H, Bao W, Zomaya A, Nguyen M N H, Hong C S. Federated learning over wireless networks: Optimization model design and analysis. In Proc. the 2019 IEEE Conference on Computer Communications (INFOCOM), Apr. 2019, pp.1387–1395. DOI: 10.1109/INFOCOM.2019.8737464.
Crossref
[15]

Wang Z L, Hu Q, Li R N, Xu M H, Xiong Z H. Incentive mechanism design for joint resource allocation in blockchain-based federated learning. IEEE Trans. Parallel and Distributed Systems, 2023, 34(5): 1536–1547. DOI: 10.1109/TPDS.2023.3253604.
Crossref Google Scholar
[16]

Zhan Y F, Li P, Qu Z H, Zeng D Z, Guo S. A learning-based incentive mechanism for federated learning. IEEE Internet of Things Journal, 2020, 7(7): 6360–6368. DOI: 10.1109/JIOT.2020.2967772.
Crossref Google Scholar
[17]
Zeng R F, Zhang S X, Wang J Q, Chu X W. FMore: An incentive scheme of multi-dimensional auction for federated learning in MEC. In Proc. the 40th IEEE International Conference on Distributed Computing Systems (ICDCS), Nov. 29–Dec. 1, 2020, pp.278–288. DOI: 10.1109/ICDCS47774.2020.00094.
Crossref
[18]
Kaul S, Gruteser M, Rai V, Kenney J. Minimizing age of information in vehicular networks. In Proc. the 8th Annual IEEE Communications Society Conference on Sensor, Mesh and Ad Hoc Communications and Networks (SECON), Jun. 2011, pp.350–358. DOI: 10.1109/SAHCN.2011.5984917.
Crossref
[19]
Wu C, Xiao M J, Wu J, Xu Y, Zhou J R, Sun H. Towards federated learning on fresh datasets. In Proc. the 20th IEEE International Conference on Mobile Ad Hoc and Smart Systems (MASS), Sept. 2023, pp.320–328. DOI: 10.1109/MASS58611.2023.00046.
Crossref
[20]

Xu Y, Xiao M J, Wu J, Tan H S, Gao G J. A personalized privacy preserving mechanism for crowdsourced federated learning. IEEE Trans. Mobile Computing, 2024, 23(2): 1568–1585. DOI: 10.1109/TMC.2023.3237636.
Crossref Google Scholar
[21]

Zhou Y P, Liu X Z, Fu Y, Wu D, Wang J H, Yu S. Optimizing the numbers of queries and replies in convex federated learning with differential privacy. IEEE Trans. Dependable and Secure Computing, 2023, 20(6): 4823–4837. DOI: 10.1109/TDSC.2023.3234599.
Crossref Google Scholar
[22]
Hosmer D W, Lemeshow S. Applied Logistic Regression (2nd edition). Wiley, 2000. DOI: 10.1002/0471722146.
Crossref
[23]

Hearst M A, Dumais S T, Osuna E, Platt J, Scholkopf B. Support vector machines. IEEE Intelligent Systems and their Applications, 1998, 13(4): 18–28. DOI: 10.1109/5254.708428.
Crossref Google Scholar
[24]

Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks. Communications of the ACM, 2017, 60(6): 84–90. DOI: 10.1145/3065386.
Crossref Google Scholar
[25]

McCall B P. Multi-armed bandit allocation indices (J. C. Gittins). SIAM Review, 1991, 33(1): 154–155. DOI: 10.1137/1033039.
Crossref Google Scholar
[26]

Xu Y, Xiao M J, Wu J, Zhang S, Gao G J. Incentive mechanism for spatial crowdsourcing with unknown social-aware workers: A three-stage stackelberg game approach. IEEE Trans. Mobile Computing, 2023, 22(8): 4698–4713. DOI: 10.1109/TMC.2022.3157687.
Crossref Google Scholar
[27]

Whittle P. Restless bandits: Activity allocation in a changing world. Journal of Applied Probability, 1988, 25(A): 287–298. DOI: 10.2307/3214163.
Crossref Google Scholar
[28]

LeCun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 1998, 86(11): 2278–2324. DOI: 10.1109/5.726791.
Crossref Google Scholar
[29]
Xiao H, Rasul K, Vollgraf R. Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms. arXiv: 1708.07747, 2017. http://arxiv.org/abs/1708.07747, May 2024.
[30]
Wang S Q, Tuor T, Salonidis T, Leung K K, Makaya C, He T, Chan K. When edge meets learning: Adaptive control for resource-constrained distributed machine learning. In Proc. the 2018 IEEE Conference on Computer Communications (INFOCOM), Apr. 2018, pp.63–71. DOI: 10.1109/INFOCOM.2018.8486403.
Crossref
[31]
Yang H H, Arafa A, Quek T Q S, Poor H V. Age-based scheduling policy for federated learning in mobile edge networks. In Proc. the 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2020, pp.8743–8747. DOI: 10.1109/ICASSP40776.2020.9053740.
Crossref
[32]

Yang K, Jiang T, Shi Y M, Ding Z. Federated learning via over-the-air computation. IEEE Trans. Wireless Communications, 2020, 19(3): 2022–2035. DOI: 10.1109/TWC.2019.2961673.
Crossref Google Scholar
[33]
Wang E, Zhang M J, Yang B, Yang Y J, Wu J. Large-scale spatiotemporal fracture data completion in sparse crowdSensing. IEEE Trans. Mobile Computing, 2023. DOI: 10.1109/TMC.2023.3339089.
Crossref
[34]

Wang Z B, Hu J H, Lv R Z, Wei J, Wang Q, Yang D J, Qi H R. Personalized privacy-preserving task allocation for mobile crowdsensing. IEEE Trans. Mobile Computing, 2019, 18(6): 1330–1341. DOI: 10.1109/TMC.2018.2861393.
Crossref Google Scholar
[35]
Lai F, Zhu X F, Madhyastha H V, Chowdhury M. Oort: Efficient federated learning via guided participant selection. In Proc. the 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI), 2021, pp.19–35.
[36]

Xu Y, Xiao M J, Tan H S, Liu A, Gao G J, Yan Z Y. Incentive mechanism for differentially private federated learning in industrial internet of things. IEEE Trans. Industrial Informatics, 2022, 18(10): 6927–6939. DOI: 10.1109/TII.2021.3134257.
Crossref Google Scholar
[37]

Lee H, Lee J, Kim H, Pack S. Straggler-aware in-network aggregation for accelerating distributed deep learning. IEEE Trans. Services Computing, 2023, 16(6): 4198–4204. DOI: 10.1109/TSC.2023.3309318.
Crossref Google Scholar
[38]
Dai Z P, Wang H, Liu C H, Han R, Tang J, Wang G R. Mobile crowdsensing for data freshness: A deep reinforcement learning approach. In Proc. the 2021 IEEE Conference on Computer Communications (INFOCOM), May 2021. DOI: 10.1109/INFOCOM42981.2021.9488791.
Crossref
[39]
Tripathi V, Modiano E. Age debt: A general framework for minimizing age of information. In Proc. the 2021 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), May 2021. DOI: 10.1109/INFOCOMWKSHPS51825.2021.9484621.
Crossref
[40]
Fang M B, Wang X J, Xu C, Yang H H, Quek T Q S. Computing-aided update for information freshness in the internet of things. In Proc. the 2021 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), May 2021. DOI: 10.1109/INFOCOMWKSHPS51825.2021.9484521.
Crossref
[41]

Tang H Y, Wang J T, Song L Q, Song J. Minimizing age of information with power constraints: Multi-user opportunistic scheduling in multi-state time-varying channels. IEEE Journal on Selected Areas in Communications, 2020, 38(5): 854–868. DOI: 10.1109/JSAC.2020.2980911.
Crossref Google Scholar
[42]

Xu Y, Xiao M J, Zhu Y, Wu J, Zhang S, Zhou J R. Aoi-guaranteed incentive mechanism for mobile crowdsensing with freshness concerns. IEEE Trans. Mobile Computing, 2024, 23(5): 4107–4125. DOI: 10.1109/TMC.2023.3285779.
Crossref Google Scholar
Journal of Computer Science and Technology
Volume 39 Issue 3,
May 2024
Pages 637-653
DOI: 10.1007/s11390-024-3914-x
Cite this article:
Xu Y, Xiao M-J, Wu C, et al. Age-of-Information-Aware Federated Learning. Journal of Computer Science and Technology, 2024, 39(3): 637-653. https://doi.org/10.1007/s11390-024-3914-x

209

Views

0

Crossref

0

Web of Science

0

Scopus

0

CSCD

Altmetrics
Received: 02 November 2023
Accepted: 06 February 2024
Published: 22 July 2024
© Institute of Computing Technology, Chinese Academy of Sciences 2024
Return