Only Train Once: A One-Shot Neural Network Training And Pruning Framework

• URL: http://arxiv.org/abs/2107.07467v1
• Date: Thu, 15 Jul 2021 17:15:20 GMT
• Title: Only Train Once: A One-Shot Neural Network Training And Pruning Framework
• Authors: Tianyi Chen, Bo Ji, Tianyu Ding, Biyi Fang, Guanyi Wang, Zhihui Zhu, Luming Liang, Yixin Shi, Sheng Yi, Xiao Tu
• Abstract summary: Structured pruning is a commonly used technique in deploying deep neural networks (DNNs) onto resource-constrained devices. We propose a framework that DNNs are slimmer with competitive performances and significant FLOPs reductions by Only-Train-Once (OTO) OTO contains two keys: (i) we partition the parameters of DNNs into zero-invariant groups, enabling us to prune zero groups without affecting the output; and (ii) to promote zero groups, we then formulate a structured-Image optimization algorithm, Half-Space Projected (HSPG) To demonstrate the effectiveness of OTO, we train and
• Score: 31.959625731943675
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Structured pruning is a commonly used technique in deploying deep neural networks (DNNs) onto resource-constrained devices. However, the existing pruning methods are usually heuristic, task-specified, and require an extra fine-tuning procedure. To overcome these limitations, we propose a framework that compresses DNNs into slimmer architectures with competitive performances and significant FLOPs reductions by Only-Train-Once (OTO). OTO contains two keys: (i) we partition the parameters of DNNs into zero-invariant groups, enabling us to prune zero groups without affecting the output; and (ii) to promote zero groups, we then formulate a structured-sparsity optimization problem and propose a novel optimization algorithm, Half-Space Stochastic Projected Gradient (HSPG), to solve it, which outperforms the standard proximal methods on group sparsity exploration and maintains comparable convergence. To demonstrate the effectiveness of OTO, we train and compress full models simultaneously from scratch without fine-tuning for inference speedup and parameter reduction, and achieve state-of-the-art results on VGG16 for CIFAR10, ResNet50 for CIFAR10/ImageNet and Bert for SQuAD.

Related papers

• HESSO: Towards Automatic Efficient and User Friendly Any Neural Network Training and Pruning [38.01465387364115]
  Only-Train-Once (OTO) series has been recently proposed to resolve the many pain points by streamlining the workflow. We numerically demonstrate the efficacy of HESSO and its enhanced version HESSO-CRIC on a variety of applications.
  arXiv  Detail & Related papers  (2024-09-11T05:28:52Z)
• Structure-Preserving Network Compression Via Low-Rank Induced Training Through Linear Layers Composition [11.399520888150468]
  We present a theoretically-justified technique termed Low-Rank Induced Training (LoRITa) LoRITa promotes low-rankness through the composition of linear layers and compresses by using singular value truncation. We demonstrate the effectiveness of our approach using MNIST on Fully Connected Networks, CIFAR10 on Vision Transformers, and CIFAR10/100 and ImageNet on Convolutional Neural Networks.
  arXiv  Detail & Related papers  (2024-05-06T00:58:23Z)
• Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch [72.26822499434446]
  Auto-Train-Once (ATO) is an innovative network pruning algorithm designed to automatically reduce the computational and storage costs of DNNs. We provide a comprehensive convergence analysis as well as extensive experiments, and the results show that our approach achieves state-of-the-art performance across various model architectures.
  arXiv  Detail & Related papers  (2024-03-21T02:33:37Z)
• FALCON: FLOP-Aware Combinatorial Optimization for Neural Network Pruning [17.60353530072587]
  Network pruning offers a solution to reduce model size and computational cost while maintaining performance. Most current pruning methods focus primarily on improving sparsity by reducing the number of nonzero parameters. We propose FALCON, a novel-optimization-based framework for network pruning that jointly takes into account model accuracy (fidelity), FLOPs, and sparsity constraints.
  arXiv  Detail & Related papers  (2024-03-11T18:40:47Z)
• Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution [91.3781512926942]
  Image super-resolution (SR) has witnessed extensive neural network designs from CNN to transformer architectures. This work investigates the potential of network pruning for super-resolution iteration to take advantage of off-the-shelf network designs and reduce the underlying computational overhead. We propose a novel Iterative Soft Shrinkage-Percentage (ISS-P) method by optimizing the sparse structure of a randomly network at each and tweaking unimportant weights with a small amount proportional to the magnitude scale on-the-fly.
  arXiv  Detail & Related papers  (2023-03-16T21:06:13Z)
• On Model Compression for Neural Networks: Framework, Algorithm, and Convergence Guarantee [21.818773423324235]
  This paper focuses on two model compression techniques: low-rank approximation and weight approximation. In this paper, a holistic framework is proposed for model compression from a novel perspective of non optimization.
  arXiv  Detail & Related papers  (2023-03-13T02:14:42Z)
• Automatic Mapping of the Best-Suited DNN Pruning Schemes for Real-Time Mobile Acceleration [71.80326738527734]
  We propose a general, fine-grained structured pruning scheme and corresponding compiler optimizations. We show that our pruning scheme mapping methods, together with the general fine-grained structured pruning scheme, outperform the state-of-the-art DNN optimization framework.
  arXiv  Detail & Related papers  (2021-11-22T23:53:14Z)
• 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)
• Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch [75.69506249886622]
  Sparsity in Deep Neural Networks (DNNs) has been widely studied to compress and accelerate the models on resource-constrained environments. In this paper, we are the first to study training from scratch an N:M fine-grained structured sparse network.
  arXiv  Detail & Related papers  (2021-02-08T05:55:47Z)
• A Unified DNN Weight Compression Framework Using Reweighted Optimization Methods [31.869228048294445]
  We propose a unified DNN weight pruning framework with dynamically updated regularization terms bounded by the designated constraint. We also extend our method to an integrated framework for the combination of different DNN compression tasks.
  arXiv  Detail & Related papers  (2020-04-12T02:59:06Z)
• BLK-REW: A Unified Block-based DNN Pruning Framework using Reweighted Regularization Method [69.49386965992464]
  We propose a new block-based pruning framework that comprises a general and flexible structured pruning dimension as well as a powerful and efficient reweighted regularization method. Our framework is universal, which can be applied to both CNNs and RNNs, implying complete support for the two major kinds ofintensive computation layers. It is the first time that the weight pruning framework achieves universal coverage for both CNNs and RNNs with real-time mobile acceleration and no accuracy compromise.
  arXiv  Detail & Related papers  (2020-01-23T03:30:56Z)

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.