Learnable Mixed-precision and Dimension Reduction Co-design for Low-storage Activation

• URL: http://arxiv.org/abs/2207.07931v2
• Date: Tue, 19 Jul 2022 02:36:17 GMT
• Title: Learnable Mixed-precision and Dimension Reduction Co-design for Low-storage Activation
• Authors: Yu-Shan Tai, Cheng-Yang Chang, Chieh-Fang Teng, and AnYeu (Andy) Wu
• Abstract summary: Deep convolutional neural networks (CNNs) have achieved many eye-catching results. deploying CNNs on resource-constrained edge devices is constrained by limited memory bandwidth for transmitting large intermediated data during inference. We propose a learnable mixed-precision and dimension reduction co-design system, which separates channels into groups and allocates compression policies according to their importance.
• Score: 9.838135675969026
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recently, deep convolutional neural networks (CNNs) have achieved many eye-catching results. However, deploying CNNs on resource-constrained edge devices is constrained by limited memory bandwidth for transmitting large intermediated data during inference, i.e., activation. Existing research utilizes mixed-precision and dimension reduction to reduce computational complexity but pays less attention to its application for activation compression. To further exploit the redundancy in activation, we propose a learnable mixed-precision and dimension reduction co-design system, which separates channels into groups and allocates specific compression policies according to their importance. In addition, the proposed dynamic searching technique enlarges search space and finds out the optimal bit-width allocation automatically. Our experimental results show that the proposed methods improve 3.54%/1.27% in accuracy and save 0.18/2.02 bits per value over existing mixed-precision methods on ResNet18 and MobileNetv2, respectively.

Related papers

• Towards Resource-Efficient Federated Learning in Industrial IoT for Multivariate Time Series Analysis [50.18156030818883]
  Anomaly and missing data constitute a thorny problem in industrial applications. Deep learning enabled anomaly detection has emerged as a critical direction. The data collected in edge devices contain user privacy.
  arXiv  Detail & Related papers  (2024-11-06T15:38:31Z)
• Edge-device Collaborative Computing for Multi-view Classification [9.047284788663776]
  We explore collaborative inference at the edge, in which edge nodes and end devices share correlated data and the inference computational burden. We introduce selective schemes that decrease bandwidth resource consumption by effectively reducing data redundancy. Experimental results highlight that selective collaborative schemes can achieve different trade-offs between the above performance metrics.
  arXiv  Detail & Related papers  (2024-09-24T11:07:33Z)
• Differential error feedback for communication-efficient decentralized learning [48.924131251745266]
  We propose a new decentralized communication-efficient learning approach that blends differential quantization with error feedback. We show that the resulting communication-efficient strategy is stable both in terms of mean-square error and average bit rate. The results establish that, in the small step-size regime and with a finite number of bits, it is possible to attain the performance achievable in the absence of compression.
  arXiv  Detail & Related papers  (2024-06-26T15:11:26Z)
• LitE-SNN: Designing Lightweight and Efficient Spiking Neural Network through Spatial-Temporal Compressive Network Search and Joint Optimization [48.41286573672824]
  Spiking Neural Networks (SNNs) mimic the information-processing mechanisms of the human brain and are highly energy-efficient. We propose a new approach named LitE-SNN that incorporates both spatial and temporal compression into the automated network design process.
  arXiv  Detail & Related papers  (2024-01-26T05:23:11Z)
• Self-Attentive Pooling for Efficient Deep Learning [6.822466048176652]
  We propose a novel non-local self-attentive pooling method that can be used as a drop-in replacement to the standard pooling layers. We surpass the test accuracy of existing pooling techniques on different variants of MobileNet-V2 on ImageNet by an average of 1.2%. Our approach achieves 1.43% higher test accuracy compared to SOTA techniques with iso-memory footprints.
  arXiv  Detail & Related papers  (2022-09-16T00:35:14Z)
• Compression-aware Projection with Greedy Dimension Reduction for Convolutional Neural Network Activations [3.6188659868203388]
  We propose a compression-aware projection system to improve the trade-off between classification accuracy and compression ratio. Our test results show that the proposed methods effectively reduce 2.91x5.97x memory access with negligible accuracy drop on MobileNetV2/ResNet18/VGG16.
  arXiv  Detail & Related papers  (2021-10-17T14:02:02Z)
• Compact representations of convolutional neural networks via weight pruning and quantization [63.417651529192014]
  We propose a novel storage format for convolutional neural networks (CNNs) based on source coding and leveraging both weight pruning and quantization. We achieve a reduction of space occupancy up to 0.6% on fully connected layers and 5.44% on the whole network, while performing at least as competitive as the baseline.
  arXiv  Detail & Related papers  (2021-08-28T20:39:54Z)
• 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)
• 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)
• Resolution Adaptive Networks for Efficient Inference [53.04907454606711]
  We propose a novel Resolution Adaptive Network (RANet), which is inspired by the intuition that low-resolution representations are sufficient for classifying "easy" inputs. In RANet, the input images are first routed to a lightweight sub-network that efficiently extracts low-resolution representations. High-resolution paths in the network maintain the capability to recognize the "hard" samples.
  arXiv  Detail & Related papers  (2020-03-16T16:54:36Z)
• Mixed-Precision Quantized Neural Network with Progressively Decreasing Bitwidth For Image Classification and Object Detection [21.48875255723581]
  A mixed-precision quantized neural network with progressively ecreasing bitwidth is proposed to improve the trade-off between accuracy and compression. Experiments on typical network architectures and benchmark datasets demonstrate that the proposed method could achieve better or comparable results.
  arXiv  Detail & Related papers  (2019-12-29T14:11:33Z)

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.