Designing Semi-Structured Pruning of Graph Convolutional Networks for Skeleton-based Recognition

• URL: http://arxiv.org/abs/2412.11813v1
• Date: Mon, 16 Dec 2024 14:29:31 GMT
• Title: Designing Semi-Structured Pruning of Graph Convolutional Networks for Skeleton-based Recognition
• Authors: Hichem Sahbi,
• Abstract summary: Pruning is one of the lightweight network design techniques that operate by removing unnecessary network parts. In this paper, we devise a novel semi-structured method that discards the downsides of structured and unstructured pruning. The proposed solution is based on a differentiable cascaded parametrization which combines (i) a band-stop mechanism that prunes weights depending on their magnitudes, (ii) a weight-sharing parametrization that prunes connections either individually or group-wise, and (iii) a gating mechanism which arbitrates between different group-wise and entry-wise pruning.
• Score: 5.656581242851759
• License:
• Abstract: Deep neural networks (DNNs) are nowadays witnessing a major success in solving many pattern recognition tasks including skeleton-based classification. The deployment of DNNs on edge-devices, endowed with limited time and memory resources, requires designing lightweight and efficient variants of these networks. Pruning is one of the lightweight network design techniques that operate by removing unnecessary network parts, in a structured or an unstructured manner, including individual weights, neurons or even entire channels. Nonetheless, structured and unstructured pruning methods, when applied separately, may either be inefficient or ineffective. In this paper, we devise a novel semi-structured method that discards the downsides of structured and unstructured pruning while gathering their upsides to some extent. The proposed solution is based on a differentiable cascaded parametrization which combines (i) a band-stop mechanism that prunes weights depending on their magnitudes, (ii) a weight-sharing parametrization that prunes connections either individually or group-wise, and (iii) a gating mechanism which arbitrates between different group-wise and entry-wise pruning. All these cascaded parametrizations are built upon a common latent tensor which is trained end-to-end by minimizing a classification loss and a surrogate tensor rank regularizer. Extensive experiments, conducted on the challenging tasks of action and hand-gesture recognition, show the clear advantage of our proposed semi-structured pruning approach against both structured and unstructured pruning, when taken separately, as well as the related work.

Related papers

• CoNNect: A Swiss-Army-Knife Regularizer for Pruning of Neural Networks [0.0]
  CoNNect is a novel differentiable regularizer for sparse NN training. CoNNect integrates with established pruning strategies and supports both structured and unstructured pruning.
  arXiv  Detail & Related papers  (2025-02-02T10:32:55Z)
• Learning Coarse-to-Fine Pruning of Graph Convolutional Networks for Skeleton-based Recognition [5.656581242851759]
  Magnitude Pruning is a lightweight network design method which seeks to remove connections with the smallest magnitude. We devise a novel coarse-to-fine (CTF) method that gathers the advantages of structured and unstructured pruning. Our method relies on a novel CTF parametrization that models the mask of each connection as the Hadamard product.
  arXiv  Detail & Related papers  (2024-12-17T13:11:48Z)
• Semantic Loss Functions for Neuro-Symbolic Structured Prediction [74.18322585177832]
  We discuss the semantic loss, which injects knowledge about such structure, defined symbolically, into training. It is agnostic to the arrangement of the symbols, and depends only on the semantics expressed thereby. It can be combined with both discriminative and generative neural models.
  arXiv  Detail & Related papers  (2024-05-12T22:18:25Z)
• Structurally Prune Anything: Any Architecture, Any Framework, Any Time [84.6210631783801]
  We introduce Structurally Prune Anything (SPA), a versatile structured pruning framework for neural networks. SPA supports pruning at any time, either before training, after training with fine-tuning, or after training without fine-tuning. In extensive experiments, SPA shows competitive to state-of-the-art pruning performance across various architectures.
  arXiv  Detail & Related papers  (2024-03-03T13:49:49Z)
• 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)
• DepGraph: Towards Any Structural Pruning [68.40343338847664]
  We study general structural pruning of arbitrary architecture like CNNs, RNNs, GNNs and Transformers. We propose a general and fully automatic method, emphDependency Graph (DepGraph), to explicitly model the dependency between layers and comprehensively group parameters for pruning. In this work, we extensively evaluate our method on several architectures and tasks, including ResNe(X)t, DenseNet, MobileNet and Vision transformer for images, GAT for graph, DGCNN for 3D point cloud, alongside LSTM for language, and demonstrate that, even with a
  arXiv  Detail & Related papers  (2023-01-30T14:02:33Z)
• Automatic Block-wise Pruning with Auxiliary Gating Structures for Deep Convolutional Neural Networks [9.293334856614628]
  This paper presents a novel structured network pruning method with auxiliary gating structures. Our experiments demonstrate that our method can achieve state-of-the-arts compression performance for the classification tasks.
  arXiv  Detail & Related papers  (2022-05-07T09:03:32Z)
• Compact Neural Networks via Stacking Designed Basic Units [38.10212043168065]
  This paper presents a new method termed TissueNet, which directly constructs compact neural networks with fewer weight parameters. We formulate TissueNet in diverse popular backbones for comparison with the state-of-the-art pruning methods on different benchmark datasets. Experiment results show that TissueNet can achieve comparable classification accuracy while saving up to around 80% FLOPs and 89.7% parameters.
  arXiv  Detail & Related papers  (2022-05-03T14:04:49Z)
• 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)
• Structured Convolutions for Efficient Neural Network Design [65.36569572213027]
  We tackle model efficiency by exploiting redundancy in the textitimplicit structure of the building blocks of convolutional neural networks. We show how this decomposition can be applied to 2D and 3D kernels as well as the fully-connected layers.
  arXiv  Detail & Related papers  (2020-08-06T04:38:38Z)

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.