An Experimental Study of Split-Learning TinyML on Ultra-Low-Power Edge/IoT Nodes

• URL: http://arxiv.org/abs/2507.16594v1
• Date: Tue, 22 Jul 2025 13:50:12 GMT
• Title: An Experimental Study of Split-Learning TinyML on Ultra-Low-Power Edge/IoT Nodes
• Abstract summary: Split learning (SL) executes part of the inference process on the sensor and off-loads the remainder to a companion device.<n>This paper presents the first end-to-end TinyML + SL testbed built on Espressif ESP32-S3 boards.<n>We benchmark the performance of a MobileNetV2 image recognition model, which is quantized to 8-bit integers, partitioned, and delivered to the nodes via over-the-air updates.
• Score: 2.624902795082451
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Running deep learning inference directly on ultra-low-power edge/IoT nodes has been limited by the tight memory and compute budgets of microcontrollers. Split learning (SL) addresses this limitation in which it executes part of the inference process on the sensor and off-loads the remainder to a companion device. In the context of constrained devices and the related impact of low-power, over-the-air transport protocols, the performance of split learning remains largely unexplored. TO the best of our knowledge, this paper presents the first end-to-end TinyML + SL testbed built on Espressif ESP32-S3 boards, designed to benchmark the over-the-air performance of split learning TinyML in edge/IoT environments. We benchmark the performance of a MobileNetV2 image recognition model, which is quantized to 8-bit integers, partitioned, and delivered to the nodes via over-the-air updates. The intermediate activations are exchanged through different wireless communication methods: ESP-NOW, BLE, and traditional UDP/IP and TCP/IP, enabling a head-to-head comparison on identical hardware. Measurements show that splitting the model after block_16_project_BN layer generates a 5.66 kB tensor that traverses the link in 3.2 ms, when UDP is used, achieving a steady-state round-trip latency of 5.8 s. ESP-NOW presents the most favorable RTT performance 3.7 s; BLE extends battery life further but increases latency beyond 10s.

Related papers

• Tiny Collaborative Inference for Occlusion-Robust Object Detection [0.5352699766206808]
  Edge AI nodes for search and rescue are increasingly expected to run computer vision locally.<n>Ultra-low-end hardware imposes hard constraints on memory, compute, and inter-device communication.<n>This work addresses occlusion-robust object detection devices with less than 1 MB by combining an MCU backbone, a YOLOv2 detection head, and Lite quantisation.
  arXiv  Detail & Related papers  (2026-06-01T21:10:08Z)
• Profiling-Driven Adaptive Distributed Transformer Inference on Embedded Edge Deployment [60.442064966340524]
  We present a prototype study on NVIDIA Jetson Orin Nano devices connected over WiFi.<n>Key finding is that the dominant bottleneck is not just network bandwidth but also the CPU- GPU staging during communication.<n>Experiments show that this strategy reduces latency by 65%-77% and energy consumption by 34%-52% relative to full-tensor exchange.
  arXiv  Detail & Related papers  (2026-05-25T10:39:28Z)
• WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference [56.297697169678095]
  WISV (Wireless-Informed Semantic Verification) is a novel distributed speculative decoding framework.<n>We show that WISV achieves up to a 60.8% increase in accepted length, a 37.3% reduction in interaction rounds, and a 31.4% improvement in end-to-end latency.<n>We validate WISV on a hardware testbed comprising an NVIDIA Jetson AGX Orin and an A40-equipped server.
  arXiv  Detail & Related papers  (2026-04-20T01:29:56Z)
• BWTA: Accurate and Efficient Binarized Transformer by Algorithm-Hardware Co-design [71.97035034203275]
  We analyze zero-point distortion in binarization and propose a Binary Weights & Ternary Activations (BWTA) quantization scheme.<n>For training, we propose Smooth Multi-Stage Quantization, combining a Levelwise Degradation Strategy and a MagnitudeAlignment Projection Factor.<n>Experiments show that BWTA approaches full-precision performance for Transformer-based models, with an average 3.5% drop on GLUE and less than 2% drop on five tasks.
  arXiv  Detail & Related papers  (2026-04-05T04:25:07Z)
• TinyML Enhances CubeSat Mission Capabilities [8.462623779881566]
  The paper presents a Convolutional Neural Networks (ConvNets) model optimization and deployment pipeline for onboard image classification.<n>Our pipeline integrates structured iterative pruning, post-training INT8 quantization, and hardware-aware operator mapping to compress models.<n>We demonstrate an average reduction in RAM usage of 89.55% and Flash memory of 709% for the optimized models.
  arXiv  Detail & Related papers  (2026-03-20T17:51:07Z)
• Real-Time Human Activity Recognition on Edge Microcontrollers: Dynamic Hierarchical Inference with Multi-Spectral Sensor Fusion [7.184610830886172]
  We propose a resource-aware hierarchical network based on multi-spectral fusion and interpretable modules.<n> Deployed on an ARM Cortex-M4 microcontroller for low-power real-time inference, HPPI-Net achieves 96.70% accuracy.<n>Compared with MobileNetV3, HPPI-Net improves accuracy by 1.22% and reduces RAM usage by 71.2% and ROM usage by 42.1%.
  arXiv  Detail & Related papers  (2026-01-29T15:21:45Z)
• Evaluating the Energy Efficiency of NPU-Accelerated Machine Learning Inference on Embedded Microcontrollers [0.0]
  This paper evaluates the impact of Neural Processing Units (NPUs) on machine learning (ML) execution on microcontrollers (MCUs)<n>It shows substantial efficiency gains when inference is offloaded to the NPU.<n>For moderate to large networks, latency improvements ranged from 7x to over 125x, with per-inference net energy reductions up to 143x.
  arXiv  Detail & Related papers  (2025-09-22T08:52:54Z)
• How Learnable Grids Recover Fine Detail in Low Dimensions: A Neural Tangent Kernel Analysis of Multigrid Parametric Encodings [106.3726679697804]
  We compare the two most common techniques for mitigating this spectral bias: Fourier feature encodings (FFE) and multigrid parametric encodings (MPE)<n>MPEs are seen as the standard for low dimensional mappings, but MPEs often outperform them and learn representations with higher resolution and finer detail.<n>We prove that MPEs improve a network's performance through the structure of their grid and not their learnable embedding.
  arXiv  Detail & Related papers  (2025-04-18T02:18:08Z)
• Task-Oriented Feature Compression for Multimodal Understanding via Device-Edge Co-Inference [54.53508601749513]
  We propose a task-oriented feature compression (TOFC) method for multimodal understanding in a device-edge co-inference framework.<n>To enhance compression efficiency, multiple entropy models are adaptively selected based on the characteristics of the visual features.<n>Results show that TOFC achieves up to 52% reduction in data transmission overhead and 63% reduction in system latency.
  arXiv  Detail & Related papers  (2025-03-17T08:37:22Z)
• TPI-LLM: Serving 70B-scale LLMs Efficiently on Low-resource Edge Devices [36.714057078457195]
  We present TPI-LLM, a compute- and memory-efficient tensor parallel inference system for 70B-scale models. TPI-LLM keeps sensitive raw data local in the users' devices and introduces a sliding window memory scheduler. We show that TPI-LLM demonstrated over 80% less time-to-first-token and token latency compared to Accelerate.
  arXiv  Detail & Related papers  (2024-10-01T09:18:56Z)
• Fostc3net:A Lightweight YOLOv5 Based On the Network Structure Optimization [11.969138981034247]
  This paper presents an enhanced lightweight YOLOv5 technique customized for mobile devices. The proposed model achieves a 1% increase in detection accuracy, a 13% reduction in FLOPs, and a 26% decrease in model parameters compared to the existing YOLOv5.
  arXiv  Detail & Related papers  (2024-03-20T16:07:04Z)
• Latency-aware Unified Dynamic Networks for Efficient Image Recognition [72.8951331472913]
  LAUDNet is a framework to bridge the theoretical and practical efficiency gap in dynamic networks. It integrates three primary dynamic paradigms-spatially adaptive computation, dynamic layer skipping, and dynamic channel skipping. It can notably reduce the latency of models like ResNet by over 50% on platforms such as V100,3090, and TX2 GPUs.
  arXiv  Detail & Related papers  (2023-08-30T10:57:41Z)
• Federated Split Learning with Only Positive Labels for resource-constrained IoT environment [4.055662817794178]
  Distributed collaborative machine learning (DCML) is a promising method in the Internet of Things (IoT) domain for training deep learning models. We propose splitfed learning, known as splitfed learning (SFL), is the most suitable for efficient training and testing when devices have limited computational capabilities. We show that SFPL outperforms SFL when resource-constrained IoT devices have only positive labeled data.
  arXiv  Detail & Related papers  (2023-07-25T05:33:06Z)
• DIVISION: Memory Efficient Training via Dual Activation Precision [60.153754740511864]
  State-of-the-art work combines a search of quantization bit-width with the training, which makes the procedure complicated and less transparent. We propose a simple and effective method to compress DNN training. Experiment results show DIVISION has better comprehensive performance than state-of-the-art methods, including over 10x compression of activation maps and competitive training throughput, without loss of model accuracy.
  arXiv  Detail & Related papers  (2022-08-05T03:15:28Z)
• Lightweight and Progressively-Scalable Networks for Semantic Segmentation [100.63114424262234]
  Multi-scale learning frameworks have been regarded as a capable class of models to boost semantic segmentation. In this paper, we thoroughly analyze the design of convolutional blocks and the ways of interactions across multiple scales. We devise Lightweight and Progressively-Scalable Networks (LPS-Net) that novelly expands the network complexity in a greedy manner.
  arXiv  Detail & Related papers  (2022-07-27T16:00:28Z)
• An Adaptive Device-Edge Co-Inference Framework Based on Soft Actor-Critic [72.35307086274912]
  High-dimension parameter model and large-scale mathematical calculation restrict execution efficiency, especially for Internet of Things (IoT) devices. We propose a new Deep Reinforcement Learning (DRL)-Soft Actor Critic for discrete (SAC-d), which generates the emphexit point, emphexit point, and emphcompressing bits by soft policy iterations. Based on the latency and accuracy aware reward design, such an computation can well adapt to the complex environment like dynamic wireless channel and arbitrary processing, and is capable of supporting the 5G URL
  arXiv  Detail & Related papers  (2022-01-09T09:31:50Z)
• A TinyML Platform for On-Device Continual Learning with Quantized Latent Replays [66.62377866022221]
  Latent Replay-based Continual Learning (CL) techniques enable online, serverless adaptation in principle. We introduce a HW/SW platform for end-to-end CL based on a 10-core FP32-enabled parallel ultra-low-power processor. Our results show that by combining these techniques, continual learning can be achieved in practice using less than 64MB of memory.
  arXiv  Detail & Related papers  (2021-10-20T11:01:23Z)
• FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation [81.76975488010213]
  Dense optical flow estimation plays a key role in many robotic vision tasks. Current networks often occupy large number of parameters and require heavy computation costs. Our proposed FastFlowNet works in the well-known coarse-to-fine manner with following innovations.
  arXiv  Detail & Related papers  (2021-03-08T03:09:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.