RockNet: Distributed Learning on Ultra-Low-Power Devices
Not on the map. Why?
Abstract (arXiv)
As Machine Learning (ML) becomes integral to Cyber-Physical Systems (CPS), there is growing interest in shifting training from traditional cloud-based to on-device processing (TinyML), for example, due to privacy and latency concerns. However, CPS often comprise ultra-low-power microcontrollers, whose limited compute resources make training challenging. This paper presents RockNet, a new TinyML method tailored for ultra-low-power hardware that achieves state-of-the-art accuracy in timeseries classification, such as fault or malware detection, without requiring offline pretraining. By leveraging that CPS consist of multiple devices, we design a distributed learning method that integrates ML and wireless communication. RockNet leverages all devices for distributed training of specialized compute efficient classifiers that need minimal communication overhead for parallelization. Combined with tailored and efficient wireless multi-hop communication protocols, our approach overcomes the communication bottleneck that often occurs in distributed learning. Hardware experiments on a testbed with 20 ultra-low-power devices demonstrate RockNet's effectiveness. It successfully learns timeseries classification tasks from scratch, surpassing the accuracy of the latest approach for neural network microcontroller training by up to 2x. RockNet's distributed ML architecture reduces memory, latency and energy consumption per device by up to 90 % when scaling from one central device to 20 devices. Our results show that a tight integration of distributed ML, distributed computing, and communication enables, for the first time, training on ultra-low-power hardware with state-of-the-art accuracy.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 33 of its 97 references that are in the map. First posted on arXiv 15 Oct 2025.
Builds on
33 of 97 references.
References · 33
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2018Federated Learning for Mobile Keyboard Predictioncited by 572
- 20218-bit Optimizers via Block-wise Quantizationcited by 403
- 2018Split learning for health: Distributed deep learning without sharing raw patient datacited by 395
- 2019ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernelscited by 339
- 2020SplitFed: When Federated Learning Meets Split Learningcited by 310
- 2019Model Pruning Enables Efficient Federated Learning on Edge Devicescited by 222
- 2020MINIROCKET: A Very Fast (Almost) Deterministic Transform for Time Series Classificationcited by 190
- 2020Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluationcited by 188
- 2022On-Device Training Under 256KB Memorycited by 160
- 2019Split Learning for collaborative deep learning in healthcarecited by 73
- 2019TS-CHIEF: A Scalable and Accurate Forest Algorithm for Time Series Classificationcited by 67
21 more
- 2021TinyOL: TinyML with Online-Learning on Microcontrollerscited by 65
- 2020End-to-End Evaluation of Federated Learning and Split Learning for Internet of Thingscited by 64
- 2017Deep Learning for IoT Big Data and Streaming Analytics: A Surveycited by 59
- 2022Assaying Out-Of-Distribution Generalization in Transfer Learningcited by 53
- 2022ID and OOD Performance Are Sometimes Inversely Correlated on Real-world Datasetscited by 44
- 2021A TinyML Platform for On-Device Continual Learning with Quantized Latent Replayscited by 37
- 2022A Survey on Collaborative DNN Inference for Edge Intelligencecited by 24
- 2021Evaluation and Optimization of Distributed Machine Learning Techniques for Internet of Thingscited by 20
- 2021On-device Federated Learning with Flowercited by 13
- 2023Applications of Distributed Machine Learning for the Internet-of-Things: A Comprehensive Surveycited by 11
- 2021Resilient Machine Learning for Networked Cyber Physical Systems: A Survey for Machine Learning Security to Securing Machine Learning for CPScited by 10
- 2024Achieving Linear Speedup in Asynchronous Federated Learning with Heterogeneous Clientscited by 7
- 2019One Pixel Image and RF Signal Based Split Learning for mmWave Received Power Predictioncited by 6
- 2021TinyFedTL: Federated Transfer Learning on Tiny Devicescited by 6
- 2020SEFR: A Fast Linear-Time Classifier for Ultra-Low Power Devicescited by 5
- 2020Synchronous Transmissions in Low-Power Wireless: A Survey of Communication Protocols and Network Servicescited by 4
- 2020Wireless Control for Smart Manufacturing: Recent Approaches and Open Challengescited by 4
- 2018Big Data Meet Cyber-Physical Systems: A Panoramic Surveycited by 3
- 2023A hybrid feature learning approach based on convolutional kernels for ATM fault prediction using event-log datacited by 2
- 2018Feedback Control Goes Wireless: Guaranteed Stability over Low-power Multi-hop Networkscited by 1
- 2021The Wireless Control Bus: Enabling Efficient Multi-hop Event-Triggered Control with Concurrent Transmissionscited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.