Pruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers

• URL: http://arxiv.org/abs/2408.12568v2
• Date: Wed, 23 Oct 2024 17:53:24 GMT
• Title: Pruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers
• Authors: Sayed Mohammad Vakilzadeh Hatefi, Maximilian Dreyer, Reduan Achtibat, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin,
• Abstract summary: An effective approach to reduce computational requirements and increase efficiency is to prune unnecessary components of Deep Neural Networks. Previous work has shown that attribution methods from the field of eXplainable AI serve as effective means to extract and prune the least relevant network components in a few-shot fashion.
• Score: 14.756988176469365
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: To solve ever more complex problems, Deep Neural Networks are scaled to billions of parameters, leading to huge computational costs. An effective approach to reduce computational requirements and increase efficiency is to prune unnecessary components of these often over-parameterized networks. Previous work has shown that attribution methods from the field of eXplainable AI serve as effective means to extract and prune the least relevant network components in a few-shot fashion. We extend the current state by proposing to explicitly optimize hyperparameters of attribution methods for the task of pruning, and further include transformer-based networks in our analysis. Our approach yields higher model compression rates of large transformer- and convolutional architectures (VGG, ResNet, ViT) compared to previous works, while still attaining high performance on ImageNet classification tasks. Here, our experiments indicate that transformers have a higher degree of over-parameterization compared to convolutional neural networks. Code is available at https://github.com/erfanhatefi/Pruning-by-eXplaining-in-PyTorch.

Related papers

• A Generalization of Continuous Relaxation in Structured Pruning [0.3277163122167434]
  Trends indicate that deeper and larger neural networks with an increasing number of parameters achieve higher accuracy than smaller neural networks. We generalize structured pruning with algorithms for network augmentation, pruning, sub-network collapse and removal. The resulting CNN executes efficiently on GPU hardware without computationally expensive sparse matrix operations.
  arXiv  Detail & Related papers  (2023-08-28T14:19:13Z)
• Deep Multi-Threshold Spiking-UNet for Image Processing [51.88730892920031]
  This paper introduces the novel concept of Spiking-UNet for image processing, which combines the power of Spiking Neural Networks (SNNs) with the U-Net architecture. To achieve an efficient Spiking-UNet, we face two primary challenges: ensuring high-fidelity information propagation through the network via spikes and formulating an effective training strategy. Experimental results show that, on image segmentation and denoising, our Spiking-UNet achieves comparable performance to its non-spiking counterpart.
  arXiv  Detail & Related papers  (2023-07-20T16:00:19Z)
• 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)
• Rewarded meta-pruning: Meta Learning with Rewards for Channel Pruning [19.978542231976636]
  This paper proposes a novel method to reduce the parameters and FLOPs for computational efficiency in deep learning models. We introduce accuracy and efficiency coefficients to control the trade-off between the accuracy of the network and its computing efficiency.
  arXiv  Detail & Related papers  (2023-01-26T12:32:01Z)
• Neural Nets with a Newton Conjugate Gradient Method on Multiple GPUs [0.0]
  Training deep neural networks consumes increasing computational resource shares in many compute centers. We introduce a novel second-order optimization method that requires the effect of the Hessian on a vector only. We compare the proposed second-order method with two state-of-the-arts on five representative neural network problems.
  arXiv  Detail & Related papers  (2022-08-03T12:38:23Z)
• The Lighter The Better: Rethinking Transformers in Medical Image Segmentation Through Adaptive Pruning [26.405243756778606]
  We propose to employ adaptive pruning to transformers for medical image segmentation and propose a lightweight network APFormer. To our best knowledge, this is the first work on transformer pruning for medical image analysis tasks. We prove, through ablation studies, that adaptive pruning can work as a plug-n-play module for performance improvement on other hybrid-/transformer-based methods.
  arXiv  Detail & Related papers  (2022-06-29T05:49:36Z)
• Transformer Network-based Reinforcement Learning Method for Power Distribution Network (PDN) Optimization of High Bandwidth Memory (HBM) [4.829921419076774]
  We propose a transformer network-based reinforcement learning (RL) method for power distribution network (PDN) optimization of high bandwidth memory (HBM) The proposed method can provide an optimal decoupling capacitor (decap) design to maximize the reduction of PDN self- and transfer seen at multiple ports.
  arXiv  Detail & Related papers  (2022-03-29T16:27:54Z)
• nnFormer: Interleaved Transformer for Volumetric Segmentation [50.10441845967601]
  We introduce nnFormer, a powerful segmentation model with an interleaved architecture based on empirical combination of self-attention and convolution. nnFormer achieves tremendous improvements over previous transformer-based methods on two commonly used datasets Synapse and ACDC.
  arXiv  Detail & Related papers  (2021-09-07T17:08:24Z)
• Manifold Regularized Dynamic Network Pruning [102.24146031250034]
  This paper proposes a new paradigm that dynamically removes redundant filters by embedding the manifold information of all instances into the space of pruned networks. The effectiveness of the proposed method is verified on several benchmarks, which shows better performance in terms of both accuracy and computational cost.
  arXiv  Detail & Related papers  (2021-03-10T03:59:03Z)
• DHP: Differentiable Meta Pruning via HyperNetworks [158.69345612783198]
  This paper introduces a differentiable pruning method via hypernetworks for automatic network pruning. Latent vectors control the output channels of the convolutional layers in the backbone network and act as a handle for the pruning of the layers. Experiments are conducted on various networks for image classification, single image super-resolution, and denoising.
  arXiv  Detail & Related papers  (2020-03-30T17:59:18Z)
• MSE-Optimal Neural Network Initialization via Layer Fusion [68.72356718879428]
  Deep neural networks achieve state-of-the-art performance for a range of classification and inference tasks. The use of gradient combined nonvolutionity renders learning susceptible to novel problems. We propose fusing neighboring layers of deeper networks that are trained with random variables.
  arXiv  Detail & Related papers  (2020-01-28T18:25:15Z)

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.