DropNet: Reducing Neural Network Complexity via Iterative Pruning (original) (raw)

Pruning Filters while Training for Efficiently Optimizing Deep Learning Networks

2020 International Joint Conference on Neural Networks (IJCNN), 2020

Deep Neural Networks are an important class of machine learning algorithms that have demonstrated state-ofthe-art accuracy for different cognitive tasks like image and speech recognition. Modern deep networks have millions to billions of parameters, which leads to high memory and energy requirements during training as well as during inference on resource-constrained edge devices. Consequently, pruning techniques have been proposed that remove less significant weights in deep networks, thereby reducing their memory and computational requirements. Pruning is usually performed after training the original network, and is followed by further retraining to compensate for the accuracy loss incurred during pruning. The prune-and-retrain procedure is repeated iteratively until an optimum tradeoff between accuracy and efficiency is reached. However, such iterative retraining adds to the overall training complexity of the network. In this work, we propose a dynamic pruning-while-training procedure, wherein we prune filters of the convolutional layers of a deep network during training itself, thereby precluding the need for separate retraining. We evaluate our dynamic pruning-while-training approach with three different pre-existing pruning strategies, viz. mean activationbased pruning, random pruning, and L1 normalization-based pruning. Our results for VGG-16 trained on CIFAR10 shows that L1 normalization provides the best performance among all the techniques explored in this work with less than 1% drop in accuracy after pruning 80% of the filters compared to the original network. We further evaluated the L1 normalization based pruning mechanism on CIFAR100. Results indicate that pruning while training yields a compressed network with almost no accuracy loss after pruning 50% of the filters compared to the original network and ∼5% loss for high pruning rates (> 80%). The proposed pruning methodology yields 41% reduction in the number of computations and memory accesses during training for CIFAR10, CIFAR100 and ImageNet compared to training with retraining for 10 epochs .

Retraining-Free Methods for Fast On-the-fly Pruning of Convolutional Neural Networks

Neurocomputing

Modern Convolutional Neural Networks (CNNs) are complex, encompassing millions of parameters. Their deployment exerts computational, storage and energy demands, particularly on embedded platforms. Existing approaches to prune or sparsify CNNs require retraining to maintain inference accuracy. Such retraining is not feasible in some contexts. In this paper, we explore the sparsification of CNNs by proposing three model-independent methods. Our methods are applied on-thefly and require no retraining. We show that the state-of-the-art models' weights can be reduced by up to 73% (compression factor of 3.7×) without incurring more than 5% loss in Top-5 accuracy. Additional fine-tuning gains only 8% in sparsity, which indicates that our fast on-the-fly methods are effective.

DropNeuron: Simplifying the Structure of Deep Neural Networks

ArXiv, 2016

Deep learning using multi-layer neural networks (NNs) architecture manifests superb power in modern machine learning systems. The trained Deep Neural Networks (DNNs) are typically large. The question we would like to address is whether it is possible to simplify the NN during training process to achieve a reasonable performance within an acceptable computational time. We presented a novel approach of optimising a deep neural network through regularisation of net- work architecture. We proposed regularisers which support a simple mechanism of dropping neurons during a network training process. The method supports the construction of a simpler deep neural networks with compatible performance with its simplified version. As a proof of concept, we evaluate the proposed method with examples including sparse linear regression, deep autoencoder and convolutional neural network. The valuations demonstrate excellent performance. The code for this work can be found in this http URL

Acceleration of Deep Convolutional Neural Networks Using Adaptive Filter Pruning

IEEE Journal of Selected Topics in Signal Processing, 2020

While convolutional neural networks (CNNs) have achieved remarkable performance on various supervised and unsupervised learning tasks, they typically consist of a massive number of parameters. This results in significant memory requirements as well as a computational burden. Consequently, there is a growing need for filter-level pruning approaches for compressing CNN based models that not only reduce the total number of parameters but reduce the overall computation as well. We present a new min-max framework for the filter-level pruning of CNNs. Our framework jointly prunes and fine-tunes CNN model parameters, with an adaptive pruning rate, while maintaining the model's predictive performance. Our framework consists of two modules: (1) An adaptive filter pruning (AFP) module, which minimizes the number of filters in the model; and (2) A pruning rate controller (PRC) module, which maximizes the accuracy during pruning. In addition, we also introduce orthogonality regularization in training of CNNs to reduce redundancy across filters of a particular layer. In the proposed approach, we prune the least important filters and, at the same time, reduce the redundancy level in the model by using orthogonality constraints during training. Moreover, unlike most previous approaches, our approach allows directly specifying the desired error tolerance instead of the pruning level. We perform extensive experiments for object classification (LeNet, VGG, MobileNet, and ResNet) and object detection (SSD, and Faster-RCNN) over benchmarked datasets such as MNIST, CIFAR, GTSDB, ImageNet, and MS-COCO. We also present several ablation studies to validate the proposed approach. Our compressed models can be deployed at run-time, without requiring any special libraries or hardware. Our approach reduces the number of parameters of VGG-16 by an impressive factor of 17.5X, and the number of FLOPS by 6.43X, with no loss of accuracy, significantly outperforming other state-of-the-art filter pruning methods.

Learn & drop: fast learning of cnns based on layer dropping

Neural computing & applications, 2024

This paper proposes a new method to improve the training efficiency of deep convolutional neural networks. During training, the method evaluates scores to measure how much each layer's parameters change and whether the layer will continue learning or not. Based on these scores, the network is scaled down such that the number of parameters to be learned is reduced, yielding a speed-up in training. Unlike state-of-the-art methods that try to compress the network to be used in the inference phase or to limit the number of operations performed in the back-propagation phase, the proposed method is novel in that it focuses on reducing the number of operations performed by the network in the forward propagation during training. The proposed training strategy has been validated on two widely used architecture families: VGG and ResNet. Experiments on MNIST, CIFAR-10 and Imagenette show that, with the proposed method, the training time of the models is more than halved without significantly impacting accuracy. The FLOPs reduction in the forward propagation during training ranges from 17.83% for VGG-11 to 83.74% for ResNet-152. As for the accuracy, the impact depends on the depth of the model and the decrease is between 0.26% and 2.38% for VGGs and between 0.4 and 3.2% for ResNets. These results demonstrate the effectiveness of the proposed technique in speeding up learning of CNNs. The technique will be especially useful in applications where fine-tuning or online training of convolutional models is required, for instance because data arrive sequentially.

Pruning Weightless Neural Networks

ESANN 2022 proceedings

Weightless neural networks (WNNs) are a type of machine learning model which perform prediction using lookup tables (LUTs) instead of arithmetic operations. Recent advancements in WNNs have reduced model sizes and improved accuracies, reducing the gap in accuracy with deep neural networks (DNNs). Modern DNNs leverage "pruning" techniques to reduce model size, but this has not previously been explored for WNNs. We propose a WNN pruning strategy based on identifying and culling the LUTs which contribute least to overall model accuracy. We demonstrate an average 40% reduction in model size with at most 1% reduction in accuracy.

Pruning at a Glance: Global Neural Pruning for Model Compression

2019

Deep Learning models have become the dominant approach in several areas due to their high performance. Unfortunately, the size and hence computational requirements of operating such models can be considerably high. Therefore, this constitutes a limitation for deployment on memory and battery constrained devices such as mobile phones or embedded systems. To address these limitations, we propose a novel and simple pruning method that compresses neural networks by removing entire filters and neurons according to a global threshold across the network without any pre-calculation of layer sensitivity. The resulting model is compact, non-sparse, with the same accuracy as the non-compressed model, and most importantly requires no special infrastructure for deployment. We prove the viability of our method by producing highly compressed models, namely VGG-16, ResNet-56, and ResNet-110 respectively on CIFAR10 without losing any performance compared to the baseline, as well as ResNet-34 and ResNet-50 on ImageNet without a significant loss of accuracy. We also provide a wellretrained 30% compressed ResNet-50 that slightly surpasses the base model accuracy. Additionally, compressing more than 56% and 97% of AlexNet and LeNet-5 respectively. Interestingly, the resulted models' pruning patterns are highly similar to the other methods using layer sensitivity pre-calculation step. Our method does not only exhibit good performance but what is more also easy to implement.

On Activation Function Coresets for Network Pruning

ArXiv, 2019

Model compression provides a means to efficiently deploy deep neural networks (DNNs) on devices that limited computation resources and tight power budgets, such as mobile and IoT (Internet of Things) devices. Consequently, model compression is one of the most critical topics in modern deep learning. Typically, the state-of-the-art model compression methods suffer from a big limitation: they are only based on heuristics rather than theoretical foundation and thus offer no worst-case guarantees. To bridge this gap, Baykal et. al. [2018a] suggested using a coreset, a small weighted subset of the data that provably approximates the original data set, to sparsify the parameters of a trained fully-connected neural network by sampling a number of neural network parameters based on the importance of the data. However, the sampling procedure is data-dependent and can only be only be performed after an expensive training phase. We propose the use of data-independent coresets to perform provab...

Zero-Keep Filter Pruning for Energy/Power Efficient Deep Neural Networks

Electronics, 2021

Recent deep learning models succeed in achieving high accuracy and fast inference time, but they require high-performance computing resources because they have a large number of parameters. However, not all systems have high-performance hardware. Sometimes, a deep learning model needs to be run on edge devices such as IoT devices or smartphones. On edge devices, however, limited computing resources are available and the amount of computation must be reduced to launch the deep learning models. Pruning is one of the well-known approaches for deriving light-weight models by eliminating weights, channels or filters. In this work, we propose “zero-keep filter pruning” for energy-efficient deep neural networks. The proposed method maximizes the number of zero elements in filters by replacing small values with zero and pruning the filter that has the lowest number of zeros. In the conventional approach, the filters that have the highest number of zeros are generally pruned. As a result, th...

One-Cycle Pruning: Pruning ConvNets Under a Tight Training Budget

ArXiv, 2021

Introducing sparsity in a neural network has been an efficient way to reduce its complexity while keeping its performance almost intact. Most of the time, sparsity is introduced using a three-stage pipeline: 1) train the model to convergence, 2) prune the model according to some criterion, 3) fine-tune the pruned model to recover performance. The last two steps are often performed iteratively, leading to reasonable results but also to a time-consuming and complex process. In our work, we propose to get rid of the first step of the pipeline and to combine the two other steps in a single pruning-training cycle, allowing the model to jointly learn for the optimal weights while being pruned. We do this by introducing a novel pruning schedule, named One-Cycle Pruning, which starts pruning from the beginning of the training, and until its very end. Adopting such a schedule not only leads to better performing pruned models but also drastically reduces the training budget required to prune ...