Abstract
Nowadays, devices are equipped with advanced sensors with higher processing and computing capabilities. Besides, widespread Internet availability enables communication among sensing devices that results the generation of vast amounts of data on edge devices to drive Internet-of-Things (IoT), crowdsourcing, and other emerging technologies. The extensive amount of collected data can be preprocessed, scaled, classified, and finally, used for predicting future events with machine learning (ML) methods. In traditional ML approaches, data is sent to and processed in a central server, which encounters communication overhead, processing delay, privacy leakage, and security issues. To overcome these challenges, each client can be trained locally based on its available data and by learning from the global model. This decentralized learning approach is referred to as federated learning (FL). However, in large-scale networks, there may be clients with varying computational resource capabilities. This may lead to implementation and scalability challenges for FL techniques. In this paper, we first introduce some recently implemented real-life applications of FL underlying the applications that are suitable for FL-based resource-constrained IoT environments. We then emphasize the core challenges of implementing the FL algorithms from the perspective of resource limitations (e.g., memory, bandwidth, and energy budget) of client devices. We finally discuss open issues associated with FL for resource-constrained environments and highlight future directions in the FL domain concerning resource-constrained devices.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hard A, Rao K, Mathews R, Ramaswamy et al (2018) Federated learning for mobile keyboard prediction. arXiv:1811.03604
Leroy D, Coucke A et al (2019) Federated learning for keyword spotting. In: IEEE ICASSP
Lim WYB, Luong NC et al (2019) Federated learning in mobile edge networks: a comprehensive survey. arXiv:1909.11875
Park J, Wang S et al (2019) Distilling on-device intelligence at the network edge. arXiv:1908.05895
Das A, Brunschwiler T (2019) Privacy is what we care about: experimental investigation of federated learning on edge devices. In: AIChallengeIoT
Xu Z, Li L et al (2019) Exploring federated learning on battery-powered devices. In: ACM TURC
Imteaj A, Amini MH (2021) Fedparl: client activity and resource-oriented lightweight federated learning model for resource-constrained heterogeneous iot environment. Front Commun Netw 2:10
Xu Z, Yang Z et al (2019) Elfish: resource-aware federated learning on heterogeneous edge devices. arXiv:1912.01684
Wang S, Tuor T et al (2019) Adaptive federated learning in resource constrained edge computing systems. IEEE JSAC 37(6):1205–1221
What does it take to train deep learning models on-device? (2018)
Bonawitz K, Eichner et al (2019) Towards federated learning at scale: system design. arXiv:1902.01046
McMahan HB, Moore E et al (2016) Communication-efficient learning of deep networks from decentralized data. arXiv:1602.05629
Huang L, Yin Y et al (2018) Loadaboost: loss-based adaboost federated machine learning on medical data. arXiv:1811.12629
Yang T, Andrew G et al (2018) Applied federated learning: improving google keyboard query suggestions. arXiv:1812.02903
Chen F, Dong Z et al (2018) Federated meta-learning for recommendation. arXiv:1802.07876
Imteaj A, Khan I, Khazaei J, Amini MH (2021) Fedresilience: a federated learning application to improve resilience of resource-constrained critical infrastructures. Electronics, 10(16)
Yang Q, Liu Y et al (2019) Federated machine learning: concept and applications. ACM Trans TIST 10(2):12
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444
Esteva A, Robicquet A, Ramsundar B, Kuleshov V, DePristo M, Chou K, Cui C, Corrado G, Thrun S, Dean J (2019) A guide to deep learning in healthcare. Nat Med 25(1):24–29
Shen D, Guorong W, Suk H-I (2017) Deep learning in medical image analysis. Annu Rev Biomed Eng 19:221–248
Young T, Hazarika D, Poria S, Cambria E (2018) Recent trends in deep learning based natural language processing. IEEE Comput Intell Mag 13(3):55–75
General Data Protection Regulation (2018) General data protection regulation (gdpr). Intersoft Consulting Accessed in October, 24(1)
Zhan Y, Li P, Guo S (2020) Experience-driven computational resource allocation of federated learning by deep reinforcement learning. In: 2020 IEEE international parallel and distributed processing symposium (IPDPS). IEEE, pp 234–243
He C, Annavaram M, Avestimehr S (2020) Group knowledge transfer: federated learning of large cnns at the edge. arXiv:2007.14513
McMahan B, Moore E, Ramage D, Hampson S, y Arcas BA (2017) Communication-efficient learning of deep networks from decentralized data. In: Artificial intelligence and statistics. PMLR, pp 1273–1282
Gupta O, Raskar R (2018) Distributed learning of deep neural network over multiple agents. J Netw Comput Appl 116:1–8
Ahmed KM, Imteaj A, Amini MH (2021) Federated deep learning for heterogeneous edge computing. In: 2021 20th IEEE international conference on machine learning and applications (ICMLA). IEEE
Hu R, Guo Y, Ratazzi EP, Gong Y (2020) Differentially private federated learning for resource-constrained internet of things. arXiv:2003.12705
Khan S, Yairi T (2018) A review on the application of deep learning in system health management. Mech Syst Signal Process 107:241–265
Mahdavifar S, Ghorbani AA (2019) Application of deep learning to cybersecurity: a survey. Neurocomputing 347:149–176
Ahmed KM, Eslami T, Saeed F, Amini MH (2021) Deepcovidnet: deep convolutional neural network for covid-19 detection from chest radiographic images. In: 2021 IEEE international conference on bioinformatics and biomedicine (BIBM). IEEE, pp 1703–1710
Silver D, Huang A, Maddison CJ, Guez A, Sifre L, Van Den Driessche G, Schrittwieser J, Antonoglou I, Panneershelvam V, Lanctot M et al (2016) Mastering the game of go with deep neural networks and tree search. Nature 529(7587):484–489
Russakovsky O, Deng J, Hao S, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis 115(3):211–252
Pan SJ, Yang Q (2009) A survey on transfer learning. IEEE Trans Knowl Data Eng 22(10):1345–1359
Jiang J, Zhai CX (2007) Instance weighting for domain adaptation in nlp. ACL
Gao J, Fan W, Jiang J, Han J (2008) Knowledge transfer via multiple model local structure mapping. In: Proceedings of the 14th ACM SIGKDD international conference on knowledge discovery and data mining, pp 283–291
Argyriou A, Pontil M, Ying Y, Micchelli C (2007) A spectral regularization framework for multi-task structure learning. Adv Neural Inf Proc Syst 20
Mihalkova L, Huynh T, Mooney RJ (2007) Mapping and revising markov logic networks for transfer learning. Aaai 7:608–614
Li H, Ota K et al (2018) Learning iot in edge: deep learning for the internet of things with edge computing. IEEE Netw 32(1):96–101
Cui L, Yang S et al (2018) A survey on application of machine learning for internet of things. J M L Cybern 9(8):1399–1417
Haddadpour F, Kamani MM et al (2019) Trading redundancy for communication: speeding up distributed sgd for non-convex optimization. In: ICML
Huang J, Qian F et al (2013) An in-depth study of lte: effect of network protocol and application behavior on performance. ACM SIGCOMM CCR 43(4):363–374
Ma C, Konečnỳ J et al (2017) Distributed optimization with arbitrary local solvers. Optim Methods Softw 32(4):813–848
Imteaj A, Amini MH (2019) Distributed sensing using smart end-user devices: pathway to federated learning for autonomous iot. In: 2019 international conference on computational science and computational intelligence (CSCI). IEEE, pp 1156–1161
Konečnỳ J, McMahan HB et al (2016) Federated learning: strategies for improving communication efficiency. arXiv:1610.05492
Li T, Sahu AK et al (2019) Federated learning: challenges, methods, and future directions. arXiv:1908.07873
Thrun S et al (2012) Learning to learn. Springer Science & Business Media, Berlin
Caruana R (1997) Multitask learning. Mach Learn 28(1):41–75
Corinzia L et al (2019) Variational federated multi-task learning. arXiv:1906.06268
Wu S, Li G et al (2018) Training and inference with integers in deep neural networks. arXiv:1802.04680
Jiang Y, Wang S et al (2019) Model pruning enables efficient federated learning on edge devices. arXiv:1909.12326
Yan G, Wang H, Li J (2021) Critical learning periods in federated learning. arXiv:2109.05613
Thakker U, Beu J et al (2019) Compressing rnns for iot devices by 15-38x using kronecker products. arXiv:1906.02876
Thakker U, Whatmough P, Liu Z, Mattina M, Beu J (2021) Doping: a technique for extreme compression of lstm models using sparse structured additive matrices. In: Smola A, Dimakis A, Stoica I (eds), Proceedings of machine learning and systems, vol 3, pp 533–549
Gope D, Beu J, Thakker U, Mattina M (2020) Ternary mobilenets via per-layer hybrid filter banks. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR) workshops
Xiong G, Yan G, Li J (2021) Straggler-resilient distributed machine learning with dynamic backup workers. arXiv:2102.06280
Imteaj A, Amini MH (2020) Fedar: activity and resource-aware federated learning model for distributed mobile robots. In: 2020 19th IEEE international conference on machine learning and applications (ICMLA). IEEE, pp 1153–1160
Imteaj A (2020) Distributed machine learning for collaborative mobile robots: Phd forum abstract. In: Proceedings of the 18th conference on embedded networked sensor systems, SenSys ’20, New York, NY, USA, 2020. Association for Computing Machinery, pp 798–799
Gu Z, Jamjoom H et al (2019) Reaching data confidentiality and model accountability on the caltrain. In: IEEE DSN
Chen M, Yang Z et al (2019) A joint learning and communications framework for federated learning over wireless networks. arXiv:1909.07972
Sprague MR, Jalalirad A et al (2018) Asynchronous federated learning for geospatial applications. In: ECML-PKDD
Eliazar II, Sokolov IM (2010) Measuring statistical heterogeneity: the pietra index. Physica A: Stat Mech App 389(1):117–125
Kumar A, Goyal S et al (2017) Resource-efficient machine learning in 2 kb ram for the internet of things. In: ICML
Dettmers T, Lewis M, Shleifer S, Zettlemoyer L (2021) 8-bit optimizers via block-wise quantization
Anonymous (2022) Logarithmic unbiased quantization: practical 4-bit training in deep learning. In: Submitted to the tenth international conference on learning representations. Under review
Raju R, Gope D, Thakker U, Beu J (2020) Understanding the impact of dynamic channel pruning on conditionally parameterized convolutions. In: Proceedings of the 2nd international workshop on challenges in artificial intelligence and machine learning for internet of things, AIChallengeIoT ’20, New York, NY, USA, 2020. Association for Computing Machinery, pp 27–33
Huang X, Thakker U, Gope D, Beu J (2020) Pushing the envelope of dynamic spatial gating technologies. AIChallengeIoT ’20, New York, NY, USA, 2020. Association for Computing Machinery, pp 21–26
Zhang Y, Duchi J et al (2015) Divide and conquer kernel ridge regression: a distributed algorithm with minimax optimal rates. JMLR 16(1):3299–3340
Guha N, Talwlkar A et al (2019) One-shot federated learning. arXiv:1902.11175
Kim H, Park J et al (2019) Blockchained on-device federated learning. IEEE Commun Lett
Xu R, Chen Y, Li J (2020) MicroFL: a lightweight, secure-by-design edge network fabric for decentralized IoT systems. In: NDSS
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Imteaj, A., Mamun Ahmed, K., Thakker, U., Wang, S., Li, J., Amini, M.H. (2023). Federated Learning for Resource-Constrained IoT Devices: Panoramas and State of the Art. In: Razavi-Far, R., Wang, B., Taylor, M.E., Yang, Q. (eds) Federated and Transfer Learning. Adaptation, Learning, and Optimization, vol 27. Springer, Cham. https://doi.org/10.1007/978-3-031-11748-0_2
Download citation
DOI: https://doi.org/10.1007/978-3-031-11748-0_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-11747-3
Online ISBN: 978-3-031-11748-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)