mlsanityData to 14 Oct 2026

What changes after deployment? A survey on On-device Learning in TinyML

arXiv 2605.31226 ↗First posted 29 May 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Machine learning models on microcontroller-class devices (TinyML) face a fundamental challenge: post-deployment distribution change undermines static models. On-device learning (ODL) addresses this by running the learning process directly on the device. The existing literature has not characterized how distribution change occurs or how different change types require different solutions. Approximately 70 ODL works are surveyed under one principle: the distribution change regime. The survey analyzes how different types of distribution change influence the applications addressable on-device, the hardware employed, and the structure of the solutions. A persistent gap between methodological benchmarks and real-world deployment scenarios is also identified.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 42 of its 102 references that are in the map. First posted on arXiv 29 May 2026.

Builds on

42 of 102 references.

References · 42

  1. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  2. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  3. 2016Matching Networks for One Shot Learningcited by 2,255
  4. 2013Fine-Grained Visual Classification of Aircraftcited by 1,726
  5. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,330
  6. 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 752
  7. 2020Learning under Concept Drift: A Reviewcited by 477
  8. 2017CORe50: a New Dataset and Benchmark for Continuous Object Recognitioncited by 289
  9. 2022On-Device Training Under 256KB Memorycited by 160
  10. 2022SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptationcited by 146
  11. 2021MLPerf Tiny Benchmarkcited by 124
  12. 2018Federated Learning for Keyword Spottingcited by 95
30 more
  1. 2021TinyOL: TinyML with Online-Learning on Microcontrollerscited by 65
  2. 2020Challenges in Benchmarking Stream Learning Algorithms with Real-world Datacited by 59
  3. 2020DORY: Automatic End-to-End Deployment of Real-World DNNs on Low-Cost IoT MCUscited by 58
  4. 2019Visual Wake Words Datasetcited by 46
  5. 2021A TinyML Platform for On-Device Continual Learning with Quantized Latent Replayscited by 37
  6. 2020TinyTL: Reduce Activations, Not Trainable Parameters for Efficient On-Device Learningcited by 32
  7. 2022POET: Training Neural Networks on Tiny Devices with Integrated Rematerialization and Pagingcited by 26
  8. 2019Query-by-example on-device keyword spottingcited by 19
  9. 2023TinyTrain: Resource-Aware Task-Adaptive Sparse Training of DNNs at the Data-Scarce Edgecited by 18
  10. 2021Exploring System Performance of Continual Learning for Mobile and Embedded Sensing Applicationscited by 17
  11. 2017Overcoming data scarcity with transfer learningcited by 14
  12. 2022Intelligence at the Extreme Edge: A Survey on Reformable TinyMLcited by 13
  13. 2024On-Device Domain Learning for Keyword Spotting on Low-Power Extreme Edge Embedded Systemscited by 13
  14. 2023LifeLearner: Hardware-Aware Meta Continual Learning System for Embedded Computing Platformscited by 11
  15. 2023Few-Shot Open-Set Learning for On-Device Customization of KeyWord Spotting Systemscited by 9
  16. 2025DFDT: Dynamic Fast Decision Tree for IoT Data Stream Mining on Edge Devicescited by 9
  17. 2025On-device edge learning for IoT data streams: a surveycited by 8
  18. 2021Tiny Machine Learning for Concept Driftcited by 7
  19. 2024Self-Learning for Personalized Keyword Spotting on Ultra-Low-Power Audio Sensorscited by 7
  20. 2024On-device Online Learning and Semantic Management of TinyML Systemscited by 5
  21. 2024TinySV: Speaker Verification in TinyML with On-device Learningcited by 5
  22. 2024On-Device Training of Fully Quantized Deep Neural Networks on Cortex-M Microcontrollerscited by 5
  23. 2024A Continual and Incremental Learning Approach for TinyML On-device Training Using Dataset Distillation and Model Size Adaptioncited by 5
  24. 2023TinyProp -- Adaptive Sparse Backpropagation for Efficient TinyML On-device Learningcited by 4
  25. 2024On-device Self-supervised Learning of Visual Perception Tasks aboard Hardware-limited Nano-quadrotorscited by 4
  26. 2024Boosting keyword spotting through on-device learnable user speech characteristicscited by 4
  27. 2024Training on the Fly: On-device Self-supervised Learning aboard Nano-drones within 20 mWcited by 4
  28. 2024Advancing On-Device Neural Network Training with TinyPropv2: Dynamic, Sparse, and Efficient Backpropagationcited by 3
  29. 2024An Ultra-Low Power Wearable BMI System with Continual Learning Capabilitiescited by 3
  30. 2025TActiLE: Tiny Active LEarning for wearable devicescited by 1

Built on by

Not cited yet.