Differentiable Network Pruning for Microcontrollers

• URL: http://arxiv.org/abs/2110.08350v1
• Date: Fri, 15 Oct 2021 20:26:15 GMT
• Title: Differentiable Network Pruning for Microcontrollers
• Authors: Edgar Liberis, Nicholas D. Lane
• Abstract summary: We present a differentiable structured network pruning method for convolutional neural networks. It integrates a model's MCU-specific resource usage and parameter importance feedback to obtain highly compressed yet accurate classification models.
• Score: 14.864940447206871
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 1.7x in less time compared to prior MCU-specific methods. Compressed models are available for download.

Related papers

• A Survey on Transformer Compression [84.18094368700379]
  Transformer plays a vital role in the realms of natural language processing (NLP) and computer vision (CV) Model compression methods reduce the memory and computational cost of Transformer. This survey provides a comprehensive review of recent compression methods, with a specific focus on their application to Transformer-based models.
  arXiv  Detail & Related papers  (2024-02-05T12:16:28Z)
• Energy-efficient Deployment of Deep Learning Applications on Cortex-M based Microcontrollers using Deep Compression [1.4050836886292872]
  This paper investigates the efficient deployment of deep learning models on resource-constrained microcontrollers. We present a methodology for the systematic exploration of different DNN pruning, quantization, and deployment strategies. We show that we can compress them to below 10% of their original parameter count before their predictive quality decreases.
  arXiv  Detail & Related papers  (2022-05-20T10:55:42Z)
• LCS: Learning Compressible Subspaces for Adaptive Network Compression at Inference Time [57.52251547365967]
  We propose a method for training a "compressible subspace" of neural networks that contains a fine-grained spectrum of models. We present results for achieving arbitrarily fine-grained accuracy-efficiency trade-offs at inference time for structured and unstructured sparsity. Our algorithm extends to quantization at variable bit widths, achieving accuracy on par with individually trained networks.
  arXiv  Detail & Related papers  (2021-10-08T17:03:34Z)
• A New Clustering-Based Technique for the Acceleration of Deep Convolutional Networks [2.7393821783237184]
  Model Compression and Acceleration (MCA) techniques are used to transform large pre-trained networks into smaller models. We propose a clustering-based approach that is able to increase the number of employed centroids/representatives. This is achieved by imposing a special structure to the employed representatives, which is enabled by the particularities of the problem at hand.
  arXiv  Detail & Related papers  (2021-07-19T18:22:07Z)
• Efficient Micro-Structured Weight Unification and Pruning for Neural Network Compression [56.83861738731913]
  Deep Neural Network (DNN) models are essential for practical applications, especially for resource limited devices. Previous unstructured or structured weight pruning methods can hardly truly accelerate inference. We propose a generalized weight unification framework at a hardware compatible micro-structured level to achieve high amount of compression and acceleration.
  arXiv  Detail & Related papers  (2021-06-15T17:22:59Z)
• NAS-BERT: Task-Agnostic and Adaptive-Size BERT Compression with Neural Architecture Search [100.71365025972258]
  We propose NAS-BERT, an efficient method for BERT compression. NAS-BERT trains a big supernet on a search space and outputs multiple compressed models with adaptive sizes and latency. Experiments on GLUE and SQuAD benchmark datasets demonstrate that NAS-BERT can find lightweight models with better accuracy than previous approaches.
  arXiv  Detail & Related papers  (2021-05-30T07:20:27Z)
• Compact CNN Structure Learning by Knowledge Distillation [34.36242082055978]
  We propose a framework that leverages knowledge distillation along with customizable block-wise optimization to learn a lightweight CNN structure. Our method results in a state of the art network compression while being capable of achieving better inference accuracy. In particular, for the already compact network MobileNet_v2, our method offers up to 2x and 5.2x better model compression.
  arXiv  Detail & Related papers  (2021-04-19T10:34:22Z)
• A Variational Information Bottleneck Based Method to Compress Sequential Networks for Human Action Recognition [9.414818018857316]
  We propose a method to effectively compress Recurrent Neural Networks (RNNs) used for Human Action Recognition (HAR) We use a Variational Information Bottleneck (VIB) theory-based pruning approach to limit the information flow through the sequential cells of RNNs to a small subset. We combine our pruning method with a specific group-lasso regularization technique that significantly improves compression. It is shown that our method achieves over 70 times greater compression than the nearest competitor with comparable accuracy for the task of action recognition on UCF11.
  arXiv  Detail & Related papers  (2020-10-03T12:41:51Z)
• PowerGossip: Practical Low-Rank Communication Compression in Decentralized Deep Learning [62.440827696638664]
  We introduce a simple algorithm that directly compresses the model differences between neighboring workers. Inspired by the PowerSGD for centralized deep learning, this algorithm uses power steps to maximize the information transferred per bit.
  arXiv  Detail & Related papers  (2020-08-04T09:14:52Z)
• ALF: Autoencoder-based Low-rank Filter-sharing for Efficient Convolutional Neural Networks [63.91384986073851]
  We propose the autoencoder-based low-rank filter-sharing technique technique (ALF) ALF shows a reduction of 70% in network parameters, 61% in operations and 41% in execution time, with minimal loss in accuracy.
  arXiv  Detail & Related papers  (2020-07-27T09:01:22Z)

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.