Mutual Information Preserving Neural Network Pruning

• URL: http://arxiv.org/abs/2411.00147v2
• Date: Mon, 03 Feb 2025 11:55:40 GMT
• Title: Mutual Information Preserving Neural Network Pruning
• Authors: Charles Westphal, Stephen Hailes, Mirco Musolesi,
• Abstract summary: We introduce Mutual Information Preserving Pruning (MIPP), a structured activation-based pruning technique applicable before or after training. MIPP consistently outperforms state-of-the-art methods, regardless of whether pruning is performed before or after training.
• Score: 3.7414804164475983
• License:
• Abstract: Pruning has emerged as the primary approach used to limit the resource requirements of large neural networks (NNs). Since the proposal of the lottery ticket hypothesis, researchers have focused either on pruning at initialization or after training. However, recent theoretical findings have shown that the sample efficiency of robust pruned models is proportional to the mutual information (MI) between the pruning masks and the model's training datasets, \textit{whether at initialization or after training}. In this paper, starting from these results, we introduce Mutual Information Preserving Pruning (MIPP), a structured activation-based pruning technique applicable before or after training. The core principle of MIPP is to select nodes in a way that conserves MI shared between the activations of adjacent layers, and consequently between the data and masks. Approaching the pruning problem in this manner means we can prove that there exists a function that can map the pruned upstream layer's activations to the downstream layer's, implying re-trainability. We demonstrate that MIPP consistently outperforms state-of-the-art methods, regardless of whether pruning is performed before or after training.

Related papers

• Information Consistent Pruning: How to Efficiently Search for Sparse Networks? [5.524804393257921]
  Iterative magnitude pruning methods (IMPs) are proven to be successful in reducing the number of insignificant nodes in deep neural networks (DNNs) Despite IMPs popularity in pruning networks, a fundamental limitation of existing IMP algorithms is the significant training time required for each pruning gradient. Our paper introduces a novel textitstopping criterion for IMPs that monitors information and flows between networks layers and minimizes the training time.
  arXiv  Detail & Related papers  (2025-01-26T16:40:59Z)
• Learning effective pruning at initialization from iterative pruning [15.842658282636876]
  We present an end-to-end neural network-based PaI method to reduce training costs. Our approach outperforms existing methods in high-sparsity settings. As the first neural network-based PaI method, we conduct extensive experiments to validate the factors influencing this approach.
  arXiv  Detail & Related papers  (2024-08-27T03:17:52Z)
• Concurrent Training and Layer Pruning of Deep Neural Networks [0.0]
  We propose an algorithm capable of identifying and eliminating irrelevant layers of a neural network during the early stages of training. We employ a structure using residual connections around nonlinear network sections that allow the flow of information through the network once a nonlinear section is pruned.
  arXiv  Detail & Related papers  (2024-06-06T23:19:57Z)
• Neural Maximum A Posteriori Estimation on Unpaired Data for Motion Deblurring [87.97330195531029]
  We propose a Neural Maximum A Posteriori (NeurMAP) estimation framework for training neural networks to recover blind motion information and sharp content from unpaired data. The proposed NeurMAP is an approach to existing deblurring neural networks, and is the first framework that enables training image deblurring networks on unpaired datasets.
  arXiv  Detail & Related papers  (2022-04-26T08:09:47Z)
• Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask Training [55.43088293183165]
  Recent studies show that pre-trained language models (PLMs) like BERT contain matchingworks that have similar transfer learning performance as the original PLM. In this paper, we find that the BERTworks have even more potential than these studies have shown. We train binary masks over model weights on the pre-training tasks, with the aim of preserving the universal transferability of the subnetwork.
  arXiv  Detail & Related papers  (2022-04-24T08:42:47Z)
• Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients [36.078414964088196]
  Pruning neural networks at initialization would enable us to find sparse models that retain the accuracy of the original network. Current methods are insufficient to enable this optimization and lead to a large degradation in model performance. We propose Prospect Pruning (ProsPr), which uses meta-gradients through the first few steps of optimization to determine which weights to prune. Our method achieves state-of-the-art pruning performance on a variety of vision classification tasks, with less data and in a single shot compared to existing pruning-at-initialization methods.
  arXiv  Detail & Related papers  (2022-02-16T15:18:55Z)
• Sparse Training via Boosting Pruning Plasticity with Neuroregeneration [79.78184026678659]
  We study the effect of pruning throughout training from the perspective of pruning plasticity. We design a novel gradual magnitude pruning (GMP) method, named gradual pruning with zero-cost neuroregeneration (GraNet) and its dynamic sparse training (DST) variant (GraNet-ST) Perhaps most impressively, the latter for the first time boosts the sparse-to-sparse training performance over various dense-to-sparse methods by a large margin with ResNet-50 on ImageNet.
  arXiv  Detail & Related papers  (2021-06-19T02:09:25Z)
• Pruning neural networks without any data by iteratively conserving synaptic flow [27.849332212178847]
  Pruning the parameters of deep neural networks has generated intense interest due to potential savings in time, memory and energy. Recent works have identified, through an expensive sequence of training and pruning cycles, the existence of winning lottery tickets or sparse trainableworks. We provide an affirmative answer to this question through theory driven algorithm design.
  arXiv  Detail & Related papers  (2020-06-09T19:21:57Z)
• Revisiting Initialization of Neural Networks [72.24615341588846]
  We propose a rigorous estimation of the global curvature of weights across layers by approximating and controlling the norm of their Hessian matrix. Our experiments on Word2Vec and the MNIST/CIFAR image classification tasks confirm that tracking the Hessian norm is a useful diagnostic tool.
  arXiv  Detail & Related papers  (2020-04-20T18:12:56Z)
• Robust Pruning at Initialization [61.30574156442608]
  A growing need for smaller, energy-efficient, neural networks to be able to use machine learning applications on devices with limited computational resources. For Deep NNs, such procedures remain unsatisfactory as the resulting pruned networks can be difficult to train and, for instance, they do not prevent one layer from being fully pruned.
  arXiv  Detail & Related papers  (2020-02-19T17:09:50Z)
• 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.