# On-device Online Learning and Semantic Management of TinyML Systems

arXiv: https://arxiv.org/abs/2405.07601 · HTML: https://mlsanity.com/paper/2405.07601/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 55 references that are in the map.
- First posted on arXiv 13 May 2024.

## Builds on (most cited first, 28 of 28)

- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [Personalized Federated Learning: A Meta-Learning Approach](https://mlsanity.com/paper/2002.07948/) (2020)
- [How to train your MAML](https://mlsanity.com/paper/1810.09502/) (2018)
- [TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systems](https://mlsanity.com/paper/2010.08678/) (2020)
- [On-Device Training Under 256KB Memory](https://mlsanity.com/paper/2206.15472/) (2022)
- [Online Meta-Learning](https://mlsanity.com/paper/1902.08438/) (2019)
- [MLPerf Tiny Benchmark](https://mlsanity.com/paper/2106.07597/) (2021)
- [TinyOL: TinyML with Online-Learning on Microcontrollers](https://mlsanity.com/paper/2103.08295/) (2021)
- [Error-driven Input Modulation: Solving the Credit Assignment Problem without a Backward Pass](https://mlsanity.com/paper/2201.11665/) (2022)
- [The Omniglot challenge: a 3-year progress report](https://mlsanity.com/paper/1902.03477/) (2019)
- [SOSA: A Lightweight Ontology for Sensors, Observations, Samples, and Actuators](https://mlsanity.com/paper/1805.09979/) (2018)
- [Edge Impulse: An MLOps Platform for Tiny Machine Learning](https://mlsanity.com/paper/2212.03332/) (2022)
- [Intelligence at the Extreme Edge: A Survey on Reformable TinyML](https://mlsanity.com/paper/2204.00827/) (2022)
- [Distributed On-Sensor Compute System for AR/VR Devices: A Semi-Analytical Simulation Framework for Power Estimation](https://mlsanity.com/paper/2203.07474/) (2022)
- [Learning through structure: towards deep neuromorphic knowledge graph embeddings](https://mlsanity.com/paper/2109.10376/) (2021)
- [How to Manage Tiny Machine Learning at Scale: An Industrial Perspective](https://mlsanity.com/paper/2202.09113/) (2022)
- [Making Neural Networks FAIR](https://mlsanity.com/paper/1907.11569/) (2019)
- [TinyReptile: TinyML with Federated Meta-Learning](https://mlsanity.com/paper/2304.05201/) (2023)
- [TinyProp -- Adaptive Sparse Backpropagation for Efficient TinyML On-device Learning](https://mlsanity.com/paper/2308.09201/) (2023)
- [MetaLDC: Meta Learning of Low-Dimensional Computing Classifiers for Fast On-Device Adaption](https://mlsanity.com/paper/2302.12347/) (2023)
- [Benchmarking and modeling of analog and digital SRAM in-memory computing architectures](https://mlsanity.com/paper/2305.18335/) (2023)
- [TinyMetaFed: Efficient Federated Meta-Learning for TinyML](https://mlsanity.com/paper/2307.06822/) (2023)
- [SeLoC-ML: Semantic Low-Code Engineering for Machine Learning Applications in Industrial IoT](https://mlsanity.com/paper/2207.08818/) (2022)
- [Automatic Network Adaptation for Ultra-Low Uniform-Precision Quantization](https://mlsanity.com/paper/2212.10878/) (2022)

## Built on by (most cited first, 5 of 5)

- [LANCE: Low Rank Activation Compression for Efficient On-Device Continual Learning](https://mlsanity.com/paper/2509.21617/) (2025)
- [Integration of TinyML and LargeML: A Survey of 6G and Beyond](https://mlsanity.com/paper/2505.15854/) (2025)
- [On-Device Continual Learning for Unsupervised Visual Anomaly Detection in Dynamic Manufacturing](https://mlsanity.com/paper/2512.13497/) (2025)
- [On-Device Vision Training, Deployment, and Inference on a Thumb-Sized Microcontroller](https://mlsanity.com/paper/2604.23012/) (2026)
- [What changes after deployment? A survey on On-device Learning in TinyML](https://mlsanity.com/paper/2605.31226/) (2026)

## Abstract (arXiv)

Recent advances in Tiny Machine Learning (TinyML) empower low-footprint embedded devices for real-time on-device Machine Learning. While many acknowledge the potential benefits of TinyML, its practical implementation presents unique challenges. This study aims to bridge the gap between prototyping single TinyML models and developing reliable TinyML systems in production: (1) Embedded devices operate in dynamically changing conditions. Existing TinyML solutions primarily focus on inference, with models trained offline on powerful machines and deployed as static objects. However, static models may underperform in the real world due to evolving input data distributions. We propose online learning to enable training on constrained devices, adapting local models towards the latest field conditions. (2) Nevertheless, current on-device learning methods struggle with heterogeneous deployment conditions and the scarcity of labeled data when applied across numerous devices. We introduce federated meta-learning incorporating online learning to enhance model generalization, facilitating rapid learning. This approach ensures optimal performance among distributed devices by knowledge sharing. (3) Moreover, TinyML's pivotal advantage is widespread adoption. Embedded devices and TinyML models prioritize extreme efficiency, leading to diverse characteristics ranging from memory and sensors to model architectures. Given their diversity and non-standardized representations, managing these resources becomes challenging as TinyML systems scale up. We present semantic management for the joint management of models and devices at scale. We demonstrate our methods through a basic regression example and then assess them in three real-world TinyML applications: handwritten character image classification, keyword audio classification, and smart building presence detection, confirming our approaches' effectiveness.