# Differentiable Network Pruning for Microcontrollers

arXiv: https://arxiv.org/abs/2110.08350 · HTML: https://mlsanity.com/paper/2110.08350/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 67 references that are in the map.
- First posted on arXiv 15 Oct 2021.

## Builds on (most cited first, 30 of 38)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [SNIP: Single-shot Network Pruning based on Connection Sensitivity](https://mlsanity.com/paper/1810.02340/) (2018)
- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [Learning Efficient Convolutional Networks through Network Slimming](https://mlsanity.com/paper/1708.06519/) (2017)
- [What is the State of Neural Network Pruning?](https://mlsanity.com/paper/2003.03033/) (2020)
- [Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks](https://mlsanity.com/paper/2102.00554/) (2021)
- [Picking Winning Tickets Before Training by Preserving Gradient Flow](https://mlsanity.com/paper/2002.07376/) (2020)
- [MCUNet: Tiny Deep Learning on IoT Devices](https://mlsanity.com/paper/2007.10319/) (2020)
- [Efficient Object Localization Using Convolutional Networks](https://mlsanity.com/paper/1411.4280/) (2014)
- [TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systems](https://mlsanity.com/paper/2010.08678/) (2020)
- [Structured Pruning of Deep Convolutional Neural Networks](https://mlsanity.com/paper/1512.08571/) (2015)
- [Dynamic Model Pruning with Feedback](https://mlsanity.com/paper/2006.07253/) (2020)
- [CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUs](https://mlsanity.com/paper/1801.06601/) (2018)
- [BRP-NAS: Prediction-based NAS using GCNs](https://mlsanity.com/paper/2007.08668/) (2020)
- [Hello Edge: Keyword Spotting on Microcontrollers](https://mlsanity.com/paper/1711.07128/) (2017)
- [A Flexible Framework for Multi-Objective Bayesian Optimization using Random Scalarizations](https://mlsanity.com/paper/1805.12168/) (2018)
- [MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks](https://mlsanity.com/paper/1711.06798/) (2017)
- [Faster gaze prediction with dense networks and Fisher pruning](https://mlsanity.com/paper/1801.05787/) (2018)
- [Deep Residual Learning for Small-Footprint Keyword Spotting](https://mlsanity.com/paper/1710.10361/) (2017)
- [μNAS: Constrained Neural Architecture Search for Microcontrollers](https://mlsanity.com/paper/2010.14246/) (2020)
- [SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers](https://mlsanity.com/paper/1905.12107/) (2019)
- [AutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Rates](https://mlsanity.com/paper/1907.03141/) (2019)
- [DSA: More Efficient Budgeted Pruning via Differentiable Sparsity Allocation](https://mlsanity.com/paper/2004.02164/) (2020)
- [Visual Wake Words Dataset](https://mlsanity.com/paper/1906.05721/) (2019)

## Built on by (most cited first, 16 of 16)

- [Machine Learning for Microcontroller-Class Hardware: A Review](https://mlsanity.com/paper/2205.14550/) (2022)
- [Model Compression in Practice: Lessons Learned from Practitioners Creating On-device Machine Learning Experiences](https://mlsanity.com/paper/2310.04621/) (2023)
- [TinyML: Tools, Applications, Challenges, and Future Research Directions](https://mlsanity.com/paper/2303.13569/) (2023)
- [Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review](https://mlsanity.com/paper/2311.11883/) (2023)
- [MicroNAS: Memory and Latency Constrained Hardware-Aware Neural Architecture Search for Time Series Classification on Microcontrollers](https://mlsanity.com/paper/2310.18384/) (2023)
- [Pex: Memory-efficient Microcontroller Deep Learning through Partial Execution](https://mlsanity.com/paper/2211.17246/) (2022)
- [Test-Time Adaptation with Binary Feedback](https://mlsanity.com/paper/2505.18514/) (2025)
- [DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators](https://mlsanity.com/paper/2412.06566/) (2024)
- [γ-Quant: Towards Learnable Quantization for Low-bit Pattern Recognition](https://mlsanity.com/paper/2509.22448/) (2025)
- [Synergy: Towards On-Body AI via Tiny AI Accelerator Collaboration on Wearables](https://mlsanity.com/paper/2401.08637/) (2023)
- [Cost-Driven Hardware-Software Co-Optimization of Machine Learning Pipelines](https://mlsanity.com/paper/2310.07940/) (2023)
- [Value Prediction for Spatiotemporal Gait Data Using Deep Learning](https://mlsanity.com/paper/2403.07926/) (2024)
- [DiTMoS: Delving into Diverse Tiny-Model Selection on Microcontrollers](https://mlsanity.com/paper/2403.09035/) (2024)
- [Scaling Laws in the Tiny Regime: How Small Models Change Their Mistakes](https://mlsanity.com/paper/2603.07365/) (2026)
- [Embedded Arena: Iterative Optimization via Hardware Feedback](https://mlsanity.com/paper/2606.16190/) (2026)
- [16-bit Precision of Convolutional Neural Networks on Microcontroller Units for 8-bit Costs](https://mlsanity.com/paper/2610.03402/) (2026)

## Abstract (arXiv)

Embedded and personal IoT devices are powered by microcontroller units (MCUs), whose extreme resource scarcity is a major obstacle for applications relying on on-device deep learning inference. Orders of magnitude less storage, memory and computational capacity, compared to what is typically required to execute neural networks, impose strict structural constraints on the network architecture and call for specialist model compression methodology. In this work, we present a differentiable structured network pruning method for convolutional neural networks, which integrates a model's MCU-specific resource usage and parameter importance feedback to obtain highly compressed yet accurate classification models. Our methodology (a) improves key resource usage of models up to 80x; (b) prunes iteratively while a model is trained, resulting in little to no overhead or even improved training time; (c) produces compressed models with matching or improved resource usage up to 1.4x in less time compared to prior MCU-specific methods. Compressed models are available for download.