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 addition, we propose to compress the whole network jointly instead of in a layer-wise manner. Our approach proves its potential as it compares favorably to the state-of-the-art on several benchmarks.
Budgeted pruning is the problem of pruning under resource constraints. In budgeted pruning, how to distribute the resources across layers (i.e., sparsity allocation) is the key problem. Traditional methods solve it by discretely searching for the layer-wise pruning ratios, which lacks efficiency. In this paper, we propose Differentiable Sparsity Allocation (DSA), an efficient end-to-end budgeted pruning flow. Utilizing a novel differentiable pruning process, DSA finds the layer-wise pruning ratios with gradient-based optimization. It allocates sparsity in continuous space, which is more effici…
Intel Labs（英特尔实验室）；University of Pittsburgh（匹兹堡大学）；Duke University（杜克大学）
Phenomenally successful in practical inference problems, convolutional neural networks (CNN) are widely deployed in mobile devices, data centers, and even supercomputers. The number of parameters needed in CNNs, however, are often large and undesirable. Consequently, various methods have been developed to prune a CNN once it is trained. Nevertheless, the resulting CNNs offer limited benefits. While pruning the fully connected layers reduces a CNN's size considerably, it does not improve inference speed noticeably as the compute heavy parts lie in convolutions. Pruning CNNs in a way that increa…
Vision transformer has achieved competitive performance on a variety of computer vision applications. However, their storage, run-time memory, and computational demands are hindering the deployment to mobile devices. Here we present a vision transformer pruning approach, which identifies the impacts of dimensions in each layer of transformer and then executes pruning accordingly. By encouraging dimension-wise sparsity in the transformer, important dimensions automatically emerge. A great number of dimensions with small importance scores can be discarded to achieve a high pruning ratio without …
The leap in performance in state-of-the-art computer vision methods is attributed to the development of deep neural networks. However it often comes at a computational price which may hinder their deployment. To alleviate this limitation, structured pruning is a well known technique which consists in removing channels, neurons or filters, and is commonly applied in order to produce more compact models. In most cases, the computations to remove are selected based on a relative importance criterion. At the same time, the need for explainable predictive models has risen tremendously and motivated…
Vision transformer (ViT) has achieved competitive accuracy on a variety of computer vision applications, but its computational cost impedes the deployment on resource-limited mobile devices. We explore the sparsity in ViT and observe that informative patches and heads are sufficient for accurate image recognition. In this paper, we propose a cascade pruning framework named CP-ViT by predicting sparsity in ViT models progressively and dynamically to reduce computational redundancy while minimizing the accuracy loss. Specifically, we define the cumulative score to reserve the informative patches…
Finding Sparse Subnetworks in One Training Cycle via Progressive Magnitude-Based Pruning
King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；University of Jeddah（吉达大学）；King Fahd University of Petroleum and Minerals（法赫德国王石油矿产大学）；King Saud University（沙特国王大学）
Northeastern University（东北大学）；College of William and Mary（威廉与玛丽学院）；DiDi AI Labs（滴滴人工智能实验室）；Syracuse University（雪城大学）；Tsinghua University（清华大学）
Model compression techniques on Deep Neural Network (DNN) have been widely acknowledged as an effective way to achieve acceleration on a variety of platforms, and DNN weight pruning is a straightforward and effective method. There are currently two mainstreams of pruning methods representing two extremes of pruning regularity: non-structured, fine-grained pruning can achieve high sparsity and accuracy, but is not hardware friendly; structured, coarse-grained pruning exploits hardware-efficient structures in pruning, but suffers from accuracy drop when the pruning rate is high. In this paper, w…
Modern deep neural networks rely on overparameterization to achieve state-of-the-art generalization. But overparameterized models are computationally expensive. Network pruning is often employed to obtain less demanding models for deployment. Fine-grained pruning removes individual weights in parameter tensors and can achieve a high model compression ratio with little accuracy degradation. However, it introduces irregularity into the computing dataflow and often does not yield improved model inference efficiency in practice. Coarse-grained model pruning, while realizing satisfactory inference …
Pushing the Limits of Sparsity: A Bag of Tricks for Extreme Pruning
Department of Computing Science University of Aberdeen, UK（计算科学系阿伯丁大学，英国）；Department of Computing Science & Interdisciplinary Institute University of Aberdeen, UK（计算科学系与跨学科研究所阿伯丁大学，英国）；Department of Computer Science University of Exeter, UK（计算机科学系埃克塞特大学，英国）；Intel Labs, USA（英特尔实验室，美国）；Department of Computer Science University of North Carolina at Chapel Hill, US（计算机科学系北卡罗来纳大学教堂山分校，美国）；School of Computer Science and Electronic Engineering University of Surrey, UK（计算机科学与电子工程学院 Surrey大学，英国）
The success of convolutional neural networks (CNNs) in computer vision applications has been accompanied by a significant increase of computation and memory costs, which prohibits its usage on resource-limited environments such as mobile or embedded devices. To this end, the research of CNN compression has recently become emerging. In this paper, we propose a novel filter pruning scheme, termed structured sparsity regularization (SSR), to simultaneously speedup the computation and reduce the memory overhead of CNNs, which can be well supported by various off-the-shelf deep learning libraries. …
Is Complexity Required for Neural Network Pruning? A Case Study on Global Magnitude Pruning
Institute for Infocomm Research (I2 R), A*STAR（资讯通信研究院 (I2R)，新加坡科技研究局 (A*STAR)）；National University of Singapore（新加坡国立大学）；Nanyang Technological University（南洋理工大学）
Structured pruning, especially channel pruning is widely used for the reduced computational cost and the compatibility with off-the-shelf hardware devices. Among existing works, weights are typically removed using a predefined global threshold, or a threshold computed from a predefined metric. The predefined global threshold based designs ignore the variation among different layers and weights distribution, therefore, they may often result in sub-optimal performance caused by over-pruning or under-pruning. In this paper, we present a simple yet effective method, termed Optimal Thresholding (OT…
Convolutional neural networks (CNNs) are typically over-parameterized, bringing considerable computational overhead and memory footprint in inference. Pruning a proportion of unimportant filters is an efficient way to mitigate the inference cost. For this purpose, identifying unimportant convolutional filters is the key to effective filter pruning. Previous work prunes filters according to either their weight norms or the corresponding batch-norm scaling factors, while neglecting the sequential dependency between adjacent layers. In this paper, we further develop the norm-based importance esti…
IIT Kanpur（印度理工学院坎普尔分校）；R&D Center, Hitachi India Pvt. Ltd.（日立印度私人有限公司研发中心）；Indian Institute of Technology, Kanpur（印度理工学院坎普尔分校）
We propose a framework for compressing state-of-the-art Single Shot MultiBox Detector (SSD). The framework addresses compression in the following stages: Sparsity Induction, Filter Selection, and Filter Pruning. In the Sparsity Induction stage, the object detector model is sparsified via an improved global threshold. In Filter Selection & Pruning stage, we select and remove filters using sparsity statistics of filter weights in two consecutive convolutional layers. This results in the model with the size smaller than most existing compact architectures. We evaluate the performance of our frame…
Weight pruning is a technique to make Deep Neural Network (DNN) inference more computationally efficient by reducing the number of model parameters over the course of training. However, most weight pruning techniques generally does not speed up DNN training and can even require more iterations to reach model convergence. In this work, we propose a novel Structured Data Gradient Pruning (SDGP) method that can speed up training without impacting model convergence. This approach enforces a specific sparsity structure, where only N out of every M elements in a matrix can be nonzero, making it amen…
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…
While vision transformers have achieved impressive results, effectively and efficiently accelerating these models can further boost performances. In this work, we propose a dense/sparse training framework to obtain a unified model, enabling weight sharing across various token densities. Thus one model offers a range of accuracy and throughput tradeoffs for different applications. Besides, we introduce adaptive token pruning to optimize the patch token sparsity based on the input image. In addition, we investigate knowledge distillation to enhance token selection capability in early transformer…
University of California, Santa Barbara（加州大学圣巴巴拉分校）；Tsinghua University（清华大学）
Crossbar architecture based devices have been widely adopted in neural network accelerators by taking advantage of the high efficiency on vector-matrix multiplication (VMM) operations. However, in the case of convolutional neural networks (CNNs), the efficiency is compromised dramatically due to the large amounts of data reuse. Although some mapping methods have been designed to achieve a balance between the execution throughput and resource overhead, the resource consumption cost is still huge while maintaining the throughput. Network pruning is a promising and widely studied leverage to shri…
The growing energy and performance costs of deep learning have driven the community to reduce the size of neural networks by selectively pruning components. Similarly to their biological counterparts, sparse networks generalize just as well, if not better than, the original dense networks. Sparsity can reduce the memory footprint of regular networks to fit mobile devices, as well as shorten training time for ever growing networks. In this paper, we survey prior work on sparsity in deep learning and provide an extensive tutorial of sparsification for both inference and training. We describe app…
University of Pisa（比萨大学）；TU Graz（格拉茨工业大学）；CSH Vienna（维也纳复杂科学中心）
We study the impact of different pruning techniques on the representation learned by deep neural networks trained with contrastive loss functions. Our work finds that at high sparsity levels, contrastive learning results in a higher number of misclassified examples relative to models trained with traditional cross-entropy loss. To understand this pronounced difference, we use metrics such as the number of PIEs (Hooker et al., 2019), Q-Score (Kalibhat et al., 2022), and PD-Score (Baldock et al., 2021) to measure the impact of pruning on the learned representation quality. Our analysis suggests …
University of Mons（蒙斯大学）；IP Paris（巴黎理工学院）；IMT Lille Douai（里尔杜埃国立高等矿业电信学院）
The advent of sparsity inducing techniques in neural networks has been of a great help in the last few years. Indeed, those methods allowed to find lighter and faster networks, able to perform more efficiently in resource-constrained environment such as mobile devices or highly requested servers. Such a sparsity is generally imposed on the weights of neural networks, reducing the footprint of the architecture. In this work, we go one step further by imposing sparsity jointly on the weights and on the input data. This can be achieved following a three-step process: 1) impose a certain structure…
Deep convolutional neural networks (CNNs) are deployed in various applications but demand immense computational requirements. Pruning techniques and Winograd convolution are two typical methods to reduce the CNN computation. However, they cannot be directly combined because Winograd transformation fills in the sparsity resulting from pruning. Li et al. (2017) propose sparse Winograd convolution in which weights are directly pruned in the Winograd domain, but this technique is not very practical because Winograd-domain retraining requires low learning rates and hence significantly longer traini…
MIT EECS（麻省理工学院电气工程与计算机科学系）；MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）
Magnitude pruning is a common, effective technique to identify sparse subnetworks at little cost to accuracy. In this work, we ask whether a particular architecture's accuracy-sparsity tradeoff can be improved by combining pruning information across multiple runs of training. From a shared ResNet-20 initialization, we train several network copies (\emph{siblings}) to completion using different SGD data orders on CIFAR-10. While the siblings' pruning masks are naively not much more similar than chance, starting sibling training after a few epochs of shared pretraining significantly increases pr…
Weight pruning methods of DNNs have been demonstrated to achieve a good model pruning rate without loss of accuracy, thereby alleviating the significant computation/storage requirements of large-scale DNNs. Structured weight pruning methods have been proposed to overcome the limitation of irregular network structure and demonstrated actual GPU acceleration. However, in prior work the pruning rate (degree of sparsity) and GPU acceleration are limited (to less than 50%) when accuracy needs to be maintained. In this work,we overcome these limitations by proposing a unified, systematic framework o…
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.
Teacher-Guided One-Shot Pruning via Context-Aware Knowledge Distillation
Apurba-NSU R&D Lab, Department of Electrical and Computer Engineering, North South University, Dhaka, Bangladesh（阿普尔巴-NSU研发实验室，电气与计算机工程系，北方南大学，达卡，孟加拉国）；Apurba Technologies, Sunnyvale, CA 94085, USA（阿普尔巴技术公司，硅谷，加利福尼亚州94085，美国）
We present a post-training weight pruning method for deep neural networks that achieves accuracy levels tolerable for the production setting and that is sufficiently fast to be run on commodity hardware such as desktop CPUs or edge devices. We propose a data-free extension of the approach for computer vision models based on automatically-generated synthetic fractal images. We obtain state-of-the-art results for data-free neural network pruning, with ~1.5% top@1 accuracy drop for a ResNet50 on ImageNet at 50% sparsity rate. When using real data, we are able to get a ResNet50 model on ImageNet w…
Beihang University（北京航空航天大学）；The University of Tokyo（东京大学）；RIKEN Center for AIP（理化学研究所人工智能研究中心）
People usually believe that network pruning not only reduces the computational cost of deep networks, but also prevents overfitting by decreasing model capacity. However, our work surprisingly discovers that network pruning sometimes even aggravates overfitting. We report an unexpected sparse double descent phenomenon that, as we increase model sparsity via network pruning, test performance first gets worse (due to overfitting), then gets better (due to relieved overfitting), and gets worse at last (due to forgetting useful information). While recent studies focused on the deep double descent …
One-Cycle Structured Pruning via Stability-Driven Subnetwork Search
IT Application Research Center, Korea Electronics Technology Institute（韩国电子技术研究所应用信息技术中心）；Department of Intelligent Semiconductors, Soongsil University（顺慈大学智能半导体系）；Department of Computer Science & Engineering, Seoul National University（首尔国立大学计算机科学与工程系）
Mix-and-Match Pruning: Globally Guided Layer-Wise Sparsification of DNNs
1 Brandenburg Technical University, Cottbus, Germany；2 University of Zanjan, Iran；3 Tallinn University of Technology, Estonia；4 Leibniz Institute for High Performance Microelectronics, Frankfurt Oder, Germany
The sheer size of modern neural networks makes model serving a serious computational challenge. A popular class of compression techniques overcomes this challenge by pruning or sparsifying the weights of pretrained networks. While useful, these techniques often face serious tradeoffs between computational requirements and compression quality. In this work, we propose a novel optimization-based pruning framework that considers the combined effect of pruning (and updating) multiple weights subject to a sparsity constraint. Our approach, CHITA, extends the classical Optimal Brain Surgeon framewor…
Pruning the parameters of deep neural networks has generated intense interest due to potential savings in time, memory and energy both during training and at test time. Recent works have identified, through an expensive sequence of training and pruning cycles, the existence of winning lottery tickets or sparse trainable subnetworks at initialization. This raises a foundational question: can we identify highly sparse trainable subnetworks at initialization, without ever training, or indeed without ever looking at the data? We provide an affirmative answer to this question through theory driven …
Pruning is a model compression method that removes redundant parameters in deep neural networks (DNNs) while maintaining accuracy. Most available filter pruning methods require complex treatments such as iterative pruning, features statistics/ranking, or additional optimization designs in the training process. In this paper, we propose a simple and effective regularization strategy from a new perspective of evolution of features, which we call feature flow regularization (FFR), for improving structured sparsity and filter pruning in DNNs. Specifically, FFR imposes controls on the gradient and …
We investigate pruning and quantization for deep neural networks. Our goal is to achieve extremely high sparsity for quantized networks to enable implementation on low cost and low power accelerator hardware. In a practical scenario, there are particularly many applications for dense prediction tasks, hence we choose stereo depth estimation as target. We propose a two stage pruning and quantization pipeline and introduce a Taylor Score alongside a new fine-tuning mode to achieve extreme sparsity without sacrificing performance. Our evaluation does not only show that pruning and quantization sh…
Beijing University of Posts and Telecommunications（北京邮电大学）；EBUPT Information Technology Co., Ltd.（亿阳信通股份有限公司）
Channel pruning can significantly accelerate and compress deep neural networks. Many channel pruning works utilize structured sparsity regularization to zero out all the weights in some channels and automatically obtain structure-sparse network in training stage. However, these methods apply structured sparsity regularization on each layer separately where the correlations between consecutive layers are omitted. In this paper, we first combine one out-channel in current layer and the corresponding in-channel in next layer as a regularization group, namely out-in-channel. Our proposed Out-In-Ch…
Tsinghua University（清华大学）；Shanghai AI Laboratory（上海人工智能实验室）；ETH Zürich（苏黎世联邦理工学院）；ByteDance Inc（字节跳动公司）；University of Texas at Dallas（德克萨斯大学达拉斯分校）
The high computational costs of video super-resolution (VSR) models hinder their deployment on resource-limited devices, (e.g., smartphones and drones). Existing VSR models contain considerable redundant filters, which drag down the inference efficiency. To prune these unimportant filters, we develop a structured pruning scheme called Structured Sparsity Learning (SSL) according to the properties of VSR. In SSL, we design pruning schemes for several key components in VSR models, including residual blocks, recurrent networks, and upsampling networks. Specifically, we develop a Residual Sparsity…
Compression of convolutional neural network models has recently been dominated by pruning approaches. A class of previous works focuses solely on pruning the unimportant filters to achieve network compression. Another important direction is the design of sparsity-inducing constraints which has also been explored in isolation. This paper presents a novel training scheme based on composite constraints that prune redundant filters and minimize their effect on overall network learning via sparsity promotion. Also, as opposed to prior works that employ pseudo-norm-based sparsity-inducing constraint…
Eindhoven University of Technology（埃因霍温理工大学）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；JD Explore Academy（京东探索研究院）；University of Twente（特文特大学）
Random pruning is arguably the most naive way to attain sparsity in neural networks, but has been deemed uncompetitive by either post-training pruning or sparse training. In this paper, we focus on sparse training and highlight a perhaps counter-intuitive finding, that random pruning at initialization can be quite powerful for the sparse training of modern neural networks. Without any delicate pruning criteria or carefully pursued sparsity structures, we empirically demonstrate that sparsely training a randomly pruned network from scratch can match the performance of its dense equivalent. Ther…
Northeastern University（东北大学）；College of William and Mary（威廉与玛丽学院）；Syracuse University（雪城大学）；IBM Research（IBM研究院）；Lehigh University（理海大学）；George Mason University（乔治梅森大学）；DiDi AI Labs（滴滴AI Labs）；Tsinghua University（清华大学）
Weight pruning has been widely acknowledged as a straightforward and effective method to eliminate redundancy in Deep Neural Networks (DNN), thereby achieving acceleration on various platforms. However, most of the pruning techniques are essentially trade-offs between model accuracy and regularity which lead to impaired inference accuracy and limited on-device acceleration performance. To solve the problem, we introduce a new sparsity dimension, namely pattern-based sparsity that comprises pattern and connectivity sparsity, and becoming both highly accurate and hardware friendly. With carefull…
School of Microelectronics, BDBC, Beihang University（北京航空航天大学微电子学院，大数据科学与脑机智能高精尖创新中心）；School of Computer Science and Engineering, BDBC, Beihang University（北京航空航天大学计算机科学与工程学院，大数据科学与脑机智能高精尖创新中心）；Department of Electrical and Computer Engineering, Duke University（杜克大学电气与计算机工程系）
Training Convolutional Neural Networks (CNNs) usually requires a large number of computational resources. In this paper, \textit{SparseTrain} is proposed to accelerate CNN training by fully exploiting the sparsity. It mainly involves three levels of innovations: activation gradients pruning algorithm, sparse training dataflow, and accelerator architecture. By applying a stochastic pruning algorithm on each layer, the sparsity of back-propagation gradients can be increased dramatically without degrading training accuracy and convergence rate. Moreover, to utilize both \textit{natural sparsity} …
William & Mary（威廉玛丽学院）；Northeastern University（东北大学）；North Carolina State University（北卡罗来纳州立大学）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）
Mobile devices are becoming an important carrier for deep learning tasks, as they are being equipped with powerful, high-end mobile CPUs and GPUs. However, it is still a challenging task to execute 3D Convolutional Neural Networks (CNNs) targeting for real-time performance, besides high inference accuracy. The reason is more complex model structure and higher model dimensionality overwhelm the available computation/storage resources on mobile devices. A natural way may be turning to deep learning weight pruning techniques. However, the direct generalization of existing 2D CNN weight pruning me…
Syracuse University（雪城大学）；Northeastern University（东北大学）；University of Connecticut（康涅狄格大学）；Alibaba Group（阿里巴巴集团）
To address the large model size and intensive computation requirement of deep neural networks (DNNs), weight pruning techniques have been proposed and generally fall into two categories, i.e., static regularization-based pruning and dynamic regularization-based pruning. However, the former method currently suffers either complex workloads or accuracy degradation, while the latter one takes a long time to tune the parameters to achieve the desired pruning rate without accuracy loss. In this paper, we propose a unified DNN weight pruning framework with dynamically updated regularization terms bo…
