Structured pruning and quantization are fundamental techniques used to reduce the size of deep neural networks (DNNs) and typically are applied independently. Applying these techniques jointly via co-optimization has the potential to produce smaller, high-quality models. However, existing joint schemes are not widely used because of (1) engineering difficulties (complicated multi-stage processes), (2) black-box optimization (extensive hyperparameter tuning to control the overall compression), and (3) insufficient architecture generalization. To address these limitations, we present the framework GETA, which automatically and efficiently performs joint structured pruning and quantization-aware training on any DNNs. GETA introduces three key innovations: (i) a quantization-aware dependency graph (QADG) that constructs a pruning search space for generic quantization-aware DNN, (ii) a partially projected stochastic gradient method that guarantees layerwise bit constraints are satisfied, and (iii) a new joint learning strategy that incorporates interpretable relationships between pruning and quantization. We present numerical experiments on both convolutional neural networks and transformer architectures that show that our approach achieves competitive (often superior) performance compared to existing joint pruning and quantization methods.
Friedrich-Alexander University Erlangen-Nürnberg (FAU)（埃尔朗根-纽伦堡大学）
For many applications, utilizing DNNs (Deep Neural Networks) requires their implementation on a target architecture in an optimized manner concerning energy consumption, memory requirement, throughput, etc. DNN compression is used to reduce the memory footprint and complexity of a DNN before its deployment on hardware. Recent efforts to understand and explain AI (Artificial Intelligence) methods have led to a new research area, termed as explainable AI. Explainable AI methods allow us to understand better the inner working of DNNs, such as the importance of different neurons and features. The …
While convolutional neural networks (CNN) have achieved impressive performance on various classification/recognition tasks, they typically consist of a massive number of parameters. This results in significant memory requirement as well as computational overheads. 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 filter-level pruning of CNNs. Our framework, called Play and Prune (PP), jointly prunes and f…
Quantization and pruning are core techniques used to reduce the inference costs of deep neural networks. State-of-the-art quantization techniques are currently applied to both the weights and activations; however, pruning is most often applied to only the weights of the network. In this work, we jointly apply novel uniform quantization and unstructured pruning methods to both the weights and activations of deep neural networks during training. Using our methods, we empirically evaluate the currently accepted prune-then-quantize paradigm across a wide range of computer vision tasks and observe …
University of California, Irvine（加利福尼亚大学尔湾分校）；Department of Mathematics（数学系）
We propose an adaptive projection-gradient descent-shrinkage-splitting method (APGDSSM) to integrate penalty based channel pruning into quantization-aware training (QAT). APGDSSM concurrently searches weights in both the quantized subspace and the sparse subspace. APGDSSM uses shrinkage operator and a splitting technique to create sparse weights, as well as the Group Lasso penalty to push the weight sparsity into channel sparsity. In addition, we propose a novel complementary transformed l1 penalty to stabilize the training for extreme compression.
When large scale training data is available, one can obtain compact and accurate networks to be deployed in resource-constrained environments effectively through quantization and pruning. However, training data are often protected due to privacy concerns and it is challenging to obtain compact networks without data. We study data-free quantization and pruning by transferring knowledge from trained large networks to compact networks. Auxiliary generators are simultaneously and adversarially trained with the targeted compact networks to generate synthetic inputs that maximize the discrepancy bet…
Soft Label Pruning and Quantization for Large-Scale Dataset Distillation
CFAR, Agency for Science, Technology and Research, Singapore（新加坡科技研究局应用科学与技术研究院）；IHPC, Agency for Science, Technology and Research, Singapore（新加坡科技研究局信息与通信技术研究院）；National University of Singapore（新加坡国立大学）
University of Science and Technology Beijing（北京科技大学）；Hua Xia General Processor Technologies（华夏通用处理器技术公司）；General Processor Technologies（通用处理器技术公司）
Deep neural networks have been applied in many applications exhibiting extraordinary abilities in the field of computer vision. However, complex network architectures challenge efficient real-time deployment and require significant computation resources and energy costs. These challenges can be overcome through optimizations such as network compression. Network compression can often be realized with little loss of accuracy. In some cases accuracy may even improve. This paper provides a survey on two types of network compression: pruning and quantization. Pruning can be categorized as static if…
University of Maryland（马里兰大学）；Shandong University（山东大学）
Network compression is crucial to making the deep networks to be more efficient, faster, and generalizable to low-end hardware. Current network compression methods have two open problems: first, there lacks a theoretical framework to estimate the maximum compression rate; second, some layers may get over-prunned, resulting in significant network performance drop. To solve these two problems, this study propose a gradient-matrix singularity analysis-based method to estimate the maximum network redundancy. Guided by that maximum rate, a novel and efficient hierarchical network pruning algorithm …
Syracuse University（雪城大学）；Peking University（北京大学）；MIT-IBM Watson AI Lab, IBM Research（IBM研究院麻省理工学院-IBM沃森人工智能实验室）；Northeastern University（东北大学）
Many model compression techniques of Deep Neural Networks (DNNs) have been investigated, including weight pruning, weight clustering and quantization, etc. Weight pruning leverages the redundancy in the number of weights in DNNs, while weight clustering/quantization leverages the redundancy in the number of bit representations of weights. They can be effectively combined in order to exploit the maximum degree of redundancy. However, there lacks a systematic investigation in literature towards this direction. In this paper, we fill this void and develop a unified, systematic framework of DNN we…
South China University of Technology（华南理工大学）；Monash University（莫纳什大学）
Model compression aims to reduce the redundancy of deep networks to obtain compact models. Recently, channel pruning has become one of the predominant compression methods to deploy deep models on resource-constrained devices. Most channel pruning methods often use a fixed compression rate for all the layers of the model, which, however, may not be optimal. To address this issue, given a target compression rate for the whole model, one can search for the optimal compression rate for each layer. Nevertheless, these methods perform channel pruning for a specific target compression rate. When we c…
Institute for Infocomm Research, Agency for Science, Technology and Research（新加坡科技研究局资讯通信研究院）；College of Computer Science, Sichuan University（四川大学计算机学院）；Nanyang Technological University（南洋理工大学）
As Deep Neural Networks (DNNs) usually are overparameterized and have millions of weight parameters, it is challenging to deploy these large DNN models on resource-constrained hardware platforms, e.g., smartphones. Numerous network compression methods such as pruning and quantization are proposed to reduce the model size significantly, of which the key is to find suitable compression allocation (e.g., pruning sparsity and quantization codebook) of each layer. Existing solutions obtain the compression allocation in an iterative/manual fashion while finetuning the compressed model, thus sufferin…
Network pruning is one of the most dominant methods for reducing the heavy inference cost of deep neural networks. Existing methods often iteratively prune networks to attain high compression ratio without incurring significant loss in performance. However, we argue that conventional methods for retraining pruned networks (i.e., using small, fixed learning rate) are inadequate as they completely ignore the benefits from snapshots of iterative pruning. In this work, we show that strong ensembles can be constructed from snapshots of iterative pruning, which achieve competitive performance and va…
Tencent Media Lab（腾讯媒体实验室）；Northeastern University（东北大学）
Compressing Deep Neural Network (DNN) models to alleviate the storage and computation requirements is essential for practical applications, especially for resource limited devices. Although capable of reducing a reasonable amount of model parameters, previous unstructured or structured weight pruning methods can hardly truly accelerate inference, either due to the poor hardware compatibility of the unstructured sparsity or due to the low sparse rate of the structurally pruned network. Aiming at reducing both storage and computation, as well as preserving the original task performance, we propo…
Northeastern University（东北大学）；Syracuse University（雪城大学）；DiDi AI Labs（滴滴人工智能实验室）；University of Michigan（密歇根大学）
Structured weight pruning is a representative model compression technique of DNNs to reduce the storage and computation requirements and accelerate inference. An automatic hyperparameter determination process is necessary due to the large number of flexible hyperparameters. This work proposes AutoCompress, an automatic structured pruning framework with the following key performance improvements: (i) effectively incorporate the combination of structured pruning schemes in the automatic process; (ii) adopt the state-of-art ADMM-based structured weight pruning as the core algorithm, and propose a…
Qualcomm AI Research（高通人工智能研究院）；University of California, Irvine（加利福尼亚大学尔湾分校）
We present a differentiable joint pruning and quantization (DJPQ) scheme. We frame neural network compression as a joint gradient-based optimization problem, trading off between model pruning and quantization automatically for hardware efficiency. DJPQ incorporates variational information bottleneck based structured pruning and mixed-bit precision quantization into a single differentiable loss function. In contrast to previous works which consider pruning and quantization separately, our method enables users to find the optimal trade-off between both in a single training procedure. To utilize …
Compression techniques for deep neural networks are important for implementing them on small embedded devices. In particular, channel-pruning is a useful technique for realizing compact networks. However, many conventional methods require manual setting of compression ratios in each layer. It is difficult to analyze the relationships between all layers, especially for deeper models. To address these issues, we propose a simple channel-pruning technique based on attention statistics that enables to evaluate the importance of channels. We improved the method by means of a criterion for automatic…
Object detectors used in autonomous vehicles can have high memory and computational overheads. In this paper, we introduce a novel semi-structured pruning framework called R-TOSS that overcomes the shortcomings of state-of-the-art model pruning techniques. Experimental results on the JetsonTX2 show that R-TOSS has a compression rate of 4.4x on the YOLOv5 object detector with a 2.15x speedup in inference time and 57.01% decrease in energy usage. R-TOSS also enables 2.89x compression on RetinaNet with a 1.86x speedup in inference time and 56.31% decrease in energy usage. We also demonstrate sign…
We propose the position-based scaled gradient (PSG) that scales the gradient depending on the position of a weight vector to make it more compression-friendly. First, we theoretically show that applying PSG to the standard gradient descent (GD), which is called PSGD, is equivalent to the GD in the warped weight space, a space made by warping the original weight space via an appropriately designed invertible function. Second, we empirically show that PSG acting as a regularizer to a weight vector is favorable for model compression domains such as quantization and pruning. PSG reduces the gap be…
Systematic Characterization of Minimal Deep Learning Architectures: A Unified Analysis of Convergence, Pruning, and Quantization
School of Computing, Newcastle University（新castle大学计算机学院）；VSB-Technical University of Ostrava（奥斯特拉瓦技术大学）；Queen Mary University of London（伦敦女王玛丽大学）；University of Florida（佛罗里达大学）；University of Catania（卡塔尼亚大学）
Sensetime Research（商汤科技研究院）；Tsinghua University（清华大学）；Syracuse University（雪城大学）；Northeastern University（东北大学）；Florida International University（佛罗里达国际大学）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；IBM Research（IBM研究院）
Weight pruning and weight quantization are two important categories of DNN model compression. Prior work on these techniques are mainly based on heuristics. A recent work developed a systematic frame-work of DNN weight pruning using the advanced optimization technique ADMM (Alternating Direction Methods of Multipliers), achieving one of state-of-art in weight pruning results. In this work, we first extend such one-shot ADMM-based framework to guarantee solution feasibility and provide fast convergence rate, and generalize to weight quantization as well. We have further developed a multi-step, …
Transformer architecture has gained popularity due to its ability to scale with large dataset. Consequently, there is a need to reduce the model size and latency, especially for on-device deployment. We focus on vision transformer proposed for image recognition task (Dosovitskiy et al., 2021), and explore the application of different compression techniques such as low rank approximation and pruning for this purpose. Specifically, we investigate a structured pruning method proposed recently in Zhu et al. (2021) and find that mostly feedforward blocks are pruned with this approach, that too, wit…
Fermi National Accelerator Laboratory（费米国家加速器实验室）；University of California San Diego（加州大学圣地亚哥分校）；Xilinx Research（赛灵思研究院）；Northwestern University（西北大学）
Efficient machine learning implementations optimized for inference in hardware have wide-ranging benefits, depending on the application, from lower inference latency to higher data throughput and reduced energy consumption. Two popular techniques for reducing computation in neural networks are pruning, removing insignificant synapses, and quantization, reducing the precision of the calculations. In this work, we explore the interplay between pruning and quantization during the training of neural networks for ultra low latency applications targeting high energy physics use cases. Techniques dev…
Iowa State University（爱荷华州立大学）；Technical University of Darmstadt（达姆施塔特工业大学）
Model compression is an essential technique for deploying deep neural networks (DNNs) on power and memory-constrained resources. However, existing model-compression methods often rely on human expertise and focus on parameters' local importance, ignoring the rich topology information within DNNs. In this paper, we propose a novel multi-stage graph embedding technique based on graph neural networks (GNNs) to identify DNN topologies and use reinforcement learning (RL) to find a suitable compression policy. We performed resource-constrained (i.e., FLOPs) channel pruning and compared our approach …
We introduce Bayesian Bits, a practical method for joint mixed precision quantization and pruning through gradient based optimization. Bayesian Bits employs a novel decomposition of the quantization operation, which sequentially considers doubling the bit width. At each new bit width, the residual error between the full precision value and the previously rounded value is quantized. We then decide whether or not to add this quantized residual error for a higher effective bit width and lower quantization noise. By starting with a power-of-two bit width, this decomposition will always produce har…
In this paper, we analyze two popular network compression techniques, i.e. filter pruning and low-rank decomposition, in a unified sense. By simply changing the way the sparsity regularization is enforced, filter pruning and low-rank decomposition can be derived accordingly. This provides another flexible choice for network compression because the techniques complement each other. For example, in popular network architectures with shortcut connections (e.g. ResNet), filter pruning cannot deal with the last convolutional layer in a ResBlock while the low-rank decomposition methods can. In addit…
National Key Laboratory for Novel Software Technology（计算机软件新技术国家重点实验室）；Nanjing University（南京大学）
This paper aims to simultaneously accelerate and compress off-the-shelf CNN models via filter pruning strategy. The importance of each filter is evaluated by the proposed entropy-based method first. Then several unimportant filters are discarded to get a smaller CNN model. Finally, fine-tuning is adopted to recover its generalization ability which is damaged during filter pruning. Our method can reduce the size of intermediate activations, which would dominate most memory footprint during model training stage but is less concerned in previous compression methods. Experiments on the ILSVRC-12 b…
Despite the recent progress of network pruning, directly applying it to the Internet of Things (IoT) applications still faces two challenges, i.e. the distribution divergence between end and cloud data and the missing of data label on end devices. One straightforward solution is to combine the unsupervised domain adaptation (UDA) technique and pruning. For example, the model is first pruned on the cloud and then transferred from cloud to end by UDA. However, such a naive combination faces high performance degradation. Hence this work proposes an Adversarial Double Masks based Pruning (ADMP) fo…
Attribution-Guided and Coverage-Maximized Pruning for Structural MoE Compression
School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院）；School of Artificial Intelligence, Beihang University（北京航空航天大学人工智能学院）；Nanyang Technological University（南洋理工大学）
We present a filter pruning approach for deep model compression, using a multitask network. Our approach is based on learning a a pruner network to prune a pre-trained target network. The pruner is essentially a multitask deep neural network with binary outputs that help identify the filters from each layer of the original network that do not have any significant contribution to the model and can therefore be pruned. The pruner network has the same architecture as the original network except that it has a multitask/multi-output last layer containing binary-valued outputs (one per filter), whic…
Deep neural networks are typically too computationally expensive to run in real-time on consumer-grade hardware and low-powered devices. In this paper, we investigate reducing the computational and memory requirements of neural networks through network pruning and quantisation. We examine their efficacy on large networks like AlexNet compared to recent compact architectures: ShuffleNet and MobileNet. Our results show that pruning and quantisation compresses these networks to less than half their original size and improves their efficiency, particularly on MobileNet with a 7x speedup. We also d…
Zhejiang University（浙江大学）；Fabu Inc.（法布公司）；Alibaba-Zhejiang University Joint Institute of Frontier Technologies（阿里巴巴-浙江大学前沿技术联合研究院）；GAC R&D Center（广汽研究院）
Neural network compression empowers the effective yet unwieldy deep convolutional neural networks (CNN) to be deployed in resource-constrained scenarios. Most state-of-the-art approaches prune the model in filter-level according to the "importance" of filters. Despite their success, we notice they suffer from at least two of the following problems: 1) The redundancy among filters is not considered because the importance is evaluated independently. 2) Cross-layer filter comparison is unachievable since the importance is defined locally within each layer. Consequently, we must manually specify l…
Qualcomm Technologies, Inc.（高通技术公司）；Qualcomm AI Research（高通人工智能研究院）
As edge devices become prevalent, deploying Deep Neural Networks (DNN) on edge devices has become a critical issue. However, DNN requires a high computational resource which is rarely available for edge devices. To handle this, we propose a novel model compression method for the devices with limited computational resources, called PQK consisting of pruning, quantization, and knowledge distillation (KD) processes. Unlike traditional pruning and KD, PQK makes use of unimportant weights pruned in the pruning process to make a teacher network for training a better student network without pre-train…
FGFP: A Fractional Gaussian Filter and Pruning for Deep Neural Networks Compression
Graduate School of Advanced Technology, National Taiwan University, Taipei, Taiwan（国家台湾大学高级科技研究所）；Graduate Institute of Electronics Engineering, National Taiwan University, Taipei, Taiwan（国家台湾大学电子工程研究所）
Structured pruning is a popular method for compressing a neural network: given a large trained network, one alternates between removing channel connections and fine-tuning; reducing the overall width of the network. However, the efficacy of structured pruning has largely evaded scrutiny. In this paper, we examine ResNets and DenseNets obtained through structured pruning-and-tuning and make two interesting observations: (i) reduced networks---smaller versions of the original network trained from scratch---consistently outperform pruned networks; (ii) if one takes the architecture of a pruned ne…
University of Liverpool（利物浦大学）；Huawei Ireland Research Center（华为爱尔兰研究中心）
Pruning aims to reduce the number of parameters while maintaining performance close to the original network. This work proposes a novel \emph{self-distillation} based pruning strategy, whereby the representational similarity between the pruned and unpruned versions of the same network is maximized. Unlike previous approaches that treat distillation and pruning separately, we use distillation to inform the pruning criteria, without requiring a separate student network as in knowledge distillation. We show that the proposed {\em cross-correlation objective for self-distilled pruning} implicitly …
In recent years, the growing size of neural networks has led to a vast amount of research concerning compression techniques to mitigate the drawbacks of such large sizes. Most of these research works can be categorized into three broad families : Knowledge Distillation, Pruning, and Quantization. While there has been steady research in this domain, adoption and commercial usage of the proposed techniques has not quite progressed at the rate. We present KD-Lib, an open-source PyTorch based library, which contains state-of-the-art modular implementations of algorithms from the three families on …
We study the neural network (NN) compression problem, viewing the tension between the compression ratio and NN performance through the lens of rate-distortion theory. We choose a distortion metric that reflects the effect of NN compression on the model output and derive the tradeoff between rate (compression) and distortion. In addition to characterizing theoretical limits of NN compression, this formulation shows that \emph{pruning}, implicitly or explicitly, must be a part of a good compression algorithm. This observation bridges a gap between parts of the literature pertaining to NN and dat…
When approaching a novel visual recognition problem in a specialized image domain, a common strategy is to start with a pre-trained deep neural network and fine-tune it to the specialized domain. If the target domain covers a smaller visual space than the source domain used for pre-training (e.g. ImageNet), the fine-tuned network is likely to be over-parameterized. However, applying network pruning as a post-processing step to reduce the memory requirements has drawbacks: fine-tuning and pruning are performed independently; pruning parameters are set once and cannot adapt over time; and the hi…
