Learning Sparse Neural Networks with Identity Layers

• URL: http://arxiv.org/abs/2307.07389v1
• Date: Fri, 14 Jul 2023 14:58:44 GMT
• Title: Learning Sparse Neural Networks with Identity Layers
• Authors: Mingjian Ni, Guangyao Chen, Xiawu Zheng, Peixi Peng, Li Yuan, Yonghong Tian
• Abstract summary: We investigate the intrinsic link between network sparsity and interlayer feature similarity. We propose a plug-and-play CKA-based Sparsity Regularization for sparse network training, dubbed CKA-SR. We find that CKA-SR consistently improves the performance of several State-Of-The-Art sparse training methods.
• Score: 33.11654855515443
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The sparsity of Deep Neural Networks is well investigated to maximize the performance and reduce the size of overparameterized networks as possible. Existing methods focus on pruning parameters in the training process by using thresholds and metrics. Meanwhile, feature similarity between different layers has not been discussed sufficiently before, which could be rigorously proved to be highly correlated to the network sparsity in this paper. Inspired by interlayer feature similarity in overparameterized models, we investigate the intrinsic link between network sparsity and interlayer feature similarity. Specifically, we prove that reducing interlayer feature similarity based on Centered Kernel Alignment (CKA) improves the sparsity of the network by using information bottleneck theory. Applying such theory, we propose a plug-and-play CKA-based Sparsity Regularization for sparse network training, dubbed CKA-SR, which utilizes CKA to reduce feature similarity between layers and increase network sparsity. In other words, layers of our sparse network tend to have their own identity compared to each other. Experimentally, we plug the proposed CKA-SR into the training process of sparse network training methods and find that CKA-SR consistently improves the performance of several State-Of-The-Art sparse training methods, especially at extremely high sparsity. Code is included in the supplementary materials.

Related papers

• Enhancing Diversity in Bayesian Deep Learning via Hyperspherical Energy Minimization of CKA [20.463933005601003]
  Centered Kernel Alignment (CKA) on feature kernels has been proposed to compare deep networks but has not been used as an optimization objective in Bayesian deep learning. We propose adopting the approach of hyperspherical energy (HE) on top of CKA kernels to address this drawback and improve training stability.
  arXiv  Detail & Related papers  (2024-10-31T23:33:23Z)
• SGLP: A Similarity Guided Fast Layer Partition Pruning for Compressing Large Deep Models [19.479746878680707]
  Layer pruning is a potent approach to reduce network size and improve computational efficiency. We propose a Similarity Guided fast Layer Partition pruning for compressing large deep models. Our method outperforms the state-of-the-art methods in both accuracy and computational efficiency.
  arXiv  Detail & Related papers  (2024-10-14T04:01:08Z)
• Reparameterization through Spatial Gradient Scaling [69.27487006953852]
  Reparameterization aims to improve the generalization of deep neural networks by transforming convolutional layers into equivalent multi-branched structures during training. We present a novel spatial gradient scaling method to redistribute learning focus among weights in convolutional networks.
  arXiv  Detail & Related papers  (2023-03-05T17:57:33Z)
• Pushing the Efficiency Limit Using Structured Sparse Convolutions [82.31130122200578]
  We propose Structured Sparse Convolution (SSC), which leverages the inherent structure in images to reduce the parameters in the convolutional filter. We show that SSC is a generalization of commonly used layers (depthwise, groupwise and pointwise convolution) in efficient architectures'' Architectures based on SSC achieve state-of-the-art performance compared to baselines on CIFAR-10, CIFAR-100, Tiny-ImageNet, and ImageNet classification benchmarks.
  arXiv  Detail & Related papers  (2022-10-23T18:37:22Z)
• Image Superresolution using Scale-Recurrent Dense Network [30.75380029218373]
  Recent advances in the design of convolutional neural network (CNN) have yielded significant improvements in the performance of image super-resolution (SR) We propose a scale recurrent SR architecture built upon units containing series of dense connections within a residual block (Residual Dense Blocks (RDBs)) Our scale recurrent design delivers competitive performance for higher scale factors while being parametrically more efficient as compared to current state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-01-28T09:18:43Z)
• Compare Where It Matters: Using Layer-Wise Regularization To Improve Federated Learning on Heterogeneous Data [0.0]
  Federated Learning is a widely adopted method to train neural networks over distributed data. One main limitation is the performance degradation that occurs when data is heterogeneously distributed. We present FedCKA: a framework that out-performs previous state-of-the-art methods on various deep learning tasks.
  arXiv  Detail & Related papers  (2021-12-01T10:46:13Z)
• Local Critic Training for Model-Parallel Learning of Deep Neural Networks [94.69202357137452]
  We propose a novel model-parallel learning method, called local critic training. We show that the proposed approach successfully decouples the update process of the layer groups for both convolutional neural networks (CNNs) and recurrent neural networks (RNNs) We also show that trained networks by the proposed method can be used for structural optimization.
  arXiv  Detail & Related papers  (2021-02-03T09:30:45Z)
• Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks [78.47459801017959]
  Sparsity can reduce the memory footprint of regular networks to fit mobile devices. We describe approaches to remove and add elements of neural networks, different training strategies to achieve model sparsity, and mechanisms to exploit sparsity in practice.
  arXiv  Detail & Related papers  (2021-01-31T22:48:50Z)
• HALO: Learning to Prune Neural Networks with Shrinkage [5.283963846188862]
  Deep neural networks achieve state-of-the-art performance in a variety of tasks by extracting a rich set of features from unstructured data. Modern techniques for inducing sparsity and reducing model size are (1) network pruning, (2) training with a sparsity inducing penalty, and (3) training a binary mask jointly with the weights of the network. We present a novel penalty called Hierarchical Adaptive Lasso which learns to adaptively sparsify weights of a given network via trainable parameters.
  arXiv  Detail & Related papers  (2020-08-24T04:08:48Z)
• ReMarNet: Conjoint Relation and Margin Learning for Small-Sample Image Classification [49.87503122462432]
  We introduce a novel neural network termed Relation-and-Margin learning Network (ReMarNet) Our method assembles two networks of different backbones so as to learn the features that can perform excellently in both of the aforementioned two classification mechanisms. Experiments on four image datasets demonstrate that our approach is effective in learning discriminative features from a small set of labeled samples.
  arXiv  Detail & Related papers  (2020-06-27T13:50:20Z)
• Fitting the Search Space of Weight-sharing NAS with Graph Convolutional Networks [100.14670789581811]
  We train a graph convolutional network to fit the performance of sampled sub-networks. With this strategy, we achieve a higher rank correlation coefficient in the selected set of candidates.
  arXiv  Detail & Related papers  (2020-04-17T19:12:39Z)

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.