Meta-Learning Algorithms for Resource-Constrained Intelligent IoT Devices
Keywords:
Meta-Learning, TinyML, Resource-Constrained IoT Devices, Few-Shot Adaptation, Edge IntelligenceAbstract
The rapid expansion of the Internet of Things (IoT) requires devices that can operate intelligently in dynamic environments despite severe hardware and energy constraints. Traditional machine learning models deployed on microcontroller-class IoT devices often struggle to adapt to new tasks, handle sensor noise, and maintain accuracy under changing environmental conditions. This research proposes a lightweight meta-learning framework specifically optimized for resource-constrained IoT platforms, combining gradient-based meta-learning techniques with model compression strategies such as quantization and pruning. The objective is to enable rapid few-shot adaptation, reduce computational overhead, and ensure robust performance in real-world IoT deployments. The study adopts a hardware-aware design approach, implementing the proposed model on ultra-low-power microcontrollers such as ARM Cortex-M series and ESP32. A two-phase training pipeline meta-training and on-device fine-tuning is used to evaluate adaptation speed, latency, memory footprint, accuracy, and energy consumption. Experimental results demonstrate that the lightweight meta-learning model adapts to new sensor-based tasks significantly faster than conventional supervised learning models while consuming substantially less energy. The model also shows improved resilience to environmental variations and sensor noise, outperforming baseline TinyML and standard meta-learning architectures under constrained conditions. Despite these promising results, the research identifies limitations related to computational cost, memory usage during adaptation, and the trade-off between model complexity and predictive accuracy. Nonetheless, the findings highlight the potential of meta-learning as a transformative approach for building intelligent, adaptive, and energy-efficient IoT systems. This study contributes to the advancement of TinyML and edge intelligence by providing a practical and scalable meta-learning solution tailored for ultra-low-power IoT devices.
Downloads
References
I. Ficili, M. Giacobbe, G. Tricomi, and A. Puliafito, “From sensors to data intelligence: Leveraging IoT, cloud, and edge computing with AI,” Sensors, vol. 25, no. 6, p. 1763, 2025.
M. Capra, R. Peloso, G. Masera, M. Ruo Roch, and M. Martina, “Edge computing: A survey on the hardware requirements in the internet of things world,” Futur. Internet, vol. 11, no. 4, p. 100, 2019.
V. B. Parthasarathy, A. Zafar, A. Khan, and A. Shahid, “The ultimate guide to fine-tuning llms from basics to breakthroughs: An exhaustive review of technologies, research, best practices, applied research challenges and opportunities,” arXiv Prepr. arXiv2408.13296, 2024.
T. S. Ajani, A. L. Imoize, and A. A. Atayero, “An overview of machine learning within embedded and mobile devices–optimizations and applications,” Sensors, vol. 21, no. 13, p. 4412, 2021.
C. Finn, P. Abbeel, and S. Levine, “Model-agnostic meta-learning for fast adaptation of deep networks,” in International conference on machine learning, PMLR, 2017, pp. 1126–1135.
P. Zhang, Y. Bai, D. Wang, B. Bai, and Y. Li, “Few-shot classification of aerial scene images via meta-learning,” Remote Sens., vol. 13, no. 1, p. 108, 2020.
H. A. Abushahla, D. Varam, A. J. N. Panopio, and M. I. AlHajri, “Quantized Neural Networks for Microcontrollers: A Comprehensive Review of Methods, Platforms, and Applications,” arXiv Prepr. arXiv2508.15008, 2025.
J. Gao, D. Wu, F. Yin, Q. Kong, L. Xu, and S. Cui, “MetaLoc: Learning to learn wireless localization,” IEEE J. Sel. Areas Commun., vol. 41, no. 12, pp. 3831–3847, 2023.
Y. Wu et al., “Masinet: Network intrusion detection for iot security based on meta-learning framework,” IEEE Internet Things J., vol. 11, no. 14, pp. 25136–25146, 2024.
Y. Chen, B. Zheng, Z. Zhang, Q. Wang, C. Shen, and Q. Zhang, “Deep learning on mobile and embedded devices: State-of-the-art, challenges, and future directions,” ACM Comput. Surv., vol. 53, no. 4, pp. 1–37, 2020.
T. Choudhary, V. Mishra, A. Goswami, and J. Sarangapani, “A comprehensive survey on model compression and acceleration,” Artif. Intell. Rev., vol. 53, no. 7, pp. 5113–5155, 2020.
N. S. Murthy, P. Vrancx, N. Laubeuf, P. Debacker, F. Catthoor, and M. Verhelst, “Learn to learn on chip: Hardware-aware meta-learning for quantized few-shot learning at the edge,” in 2022 IEEE/ACM 7th Symposium on Edge Computing (SEC), IEEE, 2022, pp. 14–25.
A. Vettoruzzo, M.-R. Bouguelia, J. Vanschoren, T. Rögnvaldsson, and K. C. Santosh, “Advances and challenges in meta-learning: A technical review,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 46, no. 7, pp. 4763–4779, 2024.
Y. Liu, S. Duan, X. Xu, and S. Ren, “MetaLDC: Meta learning of low-dimensional computing classifiers for fast on-device adaption,” arXiv Prepr. arXiv2302.12347, 2023.
S. S. Saha, S. S. Sandha, and M. Srivastava, “Machine learning for microcontroller-class hardware: A review,” IEEE Sens. J., vol. 22, no. 22, pp. 21362–21390, 2022.
T. Mowbray, “A Survey of Deep Learning Architectures in Modern Machine Learning Systems: From CNNs to Transformers,” J. Comput. Technol. Softw., vol. 4, no. 8, 2025.
S. Popli, R. K. Jha, and S. Jain, “A survey on energy efficient narrowband internet of things (NBIoT): architecture, application and challenges,” IEEE access, vol. 7, pp. 16739–16776, 2018.
B. Qian et al., “Orchestrating the development lifecycle of machine learning-based IoT applications: A taxonomy and survey,” ACM Comput. Surv., vol. 53, no. 4, pp. 1–47, 2020.
S. H. Abdulhussain et al., “A comprehensive review of sensor technologies in IOT: Technical aspects, challenges, and future directions,” Computers, vol. 14, no. 8, p. 342, 2025.
A. Radovici, I. Culic, D. Rosner, and F. Oprea, “A model for the remote deployment, update, and safe recovery for commercial sensor-based iot systems,” Sensors, vol. 20, no. 16, p. 4393, 2020.
V. Sze, Y.-H. Chen, J. Emer, A. Suleiman, and Z. Zhang, “Hardware for machine learning: Challenges and opportunities,” in 2017 IEEE custom integrated circuits conference (CICC), IEEE, 2017, pp. 1–8.
B. Prince and D. Prince, Memories for the intelligent internet of things. John Wiley & Sons, 2018.
V. Sridharan et al., “Memory errors in modern systems: The good, the bad, and the ugly,” ACM SIGARCH Comput. Archit. News, vol. 43, no. 1, pp. 297–310, 2015.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Fristi Riandari, Jonhariono Sihotang
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
