Interspace Pruning: Using Adaptive Filter Representations to Improve Training of Sparse CNNs

• URL: http://arxiv.org/abs/2203.07808v1
• Date: Tue, 15 Mar 2022 11:50:45 GMT
• Title: Interspace Pruning: Using Adaptive Filter Representations to Improve Training of Sparse CNNs
• Authors: Paul Wimmer, Jens Mehnert and Alexandru Paul Condurache
• Abstract summary: Unstructured pruning is well suited to reduce the memory footprint of convolutional neural networks (CNNs) Standard unstructured pruning (SP) reduces the memory footprint of CNNs by setting filter elements to zero. We introduce interspace pruning (IP), a general tool to improve existing pruning methods.
• Score: 69.3939291118954
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Unstructured pruning is well suited to reduce the memory footprint of convolutional neural networks (CNNs), both at training and inference time. CNNs contain parameters arranged in $K \times K$ filters. Standard unstructured pruning (SP) reduces the memory footprint of CNNs by setting filter elements to zero, thereby specifying a fixed subspace that constrains the filter. Especially if pruning is applied before or during training, this induces a strong bias. To overcome this, we introduce interspace pruning (IP), a general tool to improve existing pruning methods. It uses filters represented in a dynamic interspace by linear combinations of an underlying adaptive filter basis (FB). For IP, FB coefficients are set to zero while un-pruned coefficients and FBs are trained jointly. In this work, we provide mathematical evidence for IP's superior performance and demonstrate that IP outperforms SP on all tested state-of-the-art unstructured pruning methods. Especially in challenging situations, like pruning for ImageNet or pruning to high sparsity, IP greatly exceeds SP with equal runtime and parameter costs. Finally, we show that advances of IP are due to improved trainability and superior generalization ability.

Related papers

• RL-Pruner: Structured Pruning Using Reinforcement Learning for CNN Compression and Acceleration [0.0]
  We propose RL-Pruner, which uses reinforcement learning to learn the optimal pruning distribution. RL-Pruner can automatically extract dependencies between filters in the input model and perform pruning, without requiring model-specific pruning implementations.
  arXiv  Detail & Related papers  (2024-11-10T13:35:10Z)
• CR-SFP: Learning Consistent Representation for Soft Filter Pruning [18.701621806529438]
  Soft filter pruning(SFP) has emerged as an effective pruning technique for allowing pruned filters to update and regrow to the network. We propose to mitigate this gap by learning consistent representation for soft filter pruning, dubbed as CR-SFP. CR-SFP is a simple yet effective training framework to improve the accuracy of P-NN without introducing any additional inference cost.
  arXiv  Detail & Related papers  (2023-12-17T06:41:04Z)
• Structured Network Pruning by Measuring Filter-wise Interactions [6.037167142826297]
  We propose a structured network pruning approach SNPFI (Structured Network Pruning by measuring Filter-wise Interaction) During the pruning, the SNPFI can automatically assign the proper sparsity based on the filter utilization strength. We empirically demonstrate the effectiveness of the SNPFI with several commonly used CNN models.
  arXiv  Detail & Related papers  (2023-07-03T05:26:05Z)
• Filter Pruning for Efficient CNNs via Knowledge-driven Differential Filter Sampler [103.97487121678276]
  Filter pruning simultaneously accelerates the computation and reduces the memory overhead of CNNs. We propose a novel Knowledge-driven Differential Filter Sampler(KDFS) with Masked Filter Modeling(MFM) framework for filter pruning.
  arXiv  Detail & Related papers  (2023-07-01T02:28:41Z)
• Trainability Preserving Neural Structured Pruning [64.65659982877891]
  We present trainability preserving pruning (TPP), a regularization-based structured pruning method that can effectively maintain trainability during sparsification. TPP can compete with the ground-truth dynamical isometry recovery method on linear networks. It delivers encouraging performance in comparison to many top-performing filter pruning methods.
  arXiv  Detail & Related papers  (2022-07-25T21:15:47Z)
• Feature Flow Regularization: Improving Structured Sparsity in Deep Neural Networks [12.541769091896624]
  Pruning is a model compression method that removes redundant parameters in deep neural networks (DNNs) We propose a simple and effective regularization strategy from a new perspective of evolution of features, which we call feature flow regularization (FFR) Experiments with VGGNets, ResNets on CIFAR-10/100, and Tiny ImageNet datasets demonstrate that FFR can significantly improve both unstructured and structured sparsity.
  arXiv  Detail & Related papers  (2021-06-05T15:00:50Z)
• Dynamic Probabilistic Pruning: A general framework for hardware-constrained pruning at different granularities [80.06422693778141]
  We propose a flexible new pruning mechanism that facilitates pruning at different granularities (weights, kernels, filters/feature maps) We refer to this algorithm as Dynamic Probabilistic Pruning (DPP) We show that DPP achieves competitive compression rates and classification accuracy when pruning common deep learning models trained on different benchmark datasets for image classification.
  arXiv  Detail & Related papers  (2021-05-26T17:01:52Z)
• Data Agnostic Filter Gating for Efficient Deep Networks [72.4615632234314]
  Current filter pruning methods mainly leverage feature maps to generate important scores for filters and prune those with smaller scores. In this paper, we propose a data filter pruning method that uses an auxiliary network named Dagger module to induce pruning. In addition, to help prune filters with certain FLOPs constraints, we leverage an explicit FLOPs-aware regularization to directly promote pruning filters toward target FLOPs.
  arXiv  Detail & Related papers  (2020-10-28T15:26:40Z)
• OrthoReg: Robust Network Pruning Using Orthonormality Regularization [7.754712828900727]
  We propose a principled regularization strategy that enforces orthonormality on a network's filters to reduce inter-filter correlation. When used for iterative pruning on VGG-13, MobileNet-V1, and ResNet-34, OrthoReg consistently outperforms five baseline techniques.
  arXiv  Detail & Related papers  (2020-09-10T17:21:21Z)
• Dependency Aware Filter Pruning [74.69495455411987]
  Pruning a proportion of unimportant filters is an efficient way to mitigate the inference cost. Previous work prunes filters according to their weight norms or the corresponding batch-norm scaling factors. We propose a novel mechanism to dynamically control the sparsity-inducing regularization so as to achieve the desired sparsity.
  arXiv  Detail & Related papers  (2020-05-06T07:41:22Z)

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.