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, progressive DNN weight pruning and quantization framework, with dual benefits of (i) achieving further weight pruning/quantization thanks to the special property of ADMM regularization, and (ii) reducing the search space within each step. Extensive experimental results demonstrate the superior performance compared with prior work. Some highlights: (i) we achieve 246x,36x, and 8x weight pruning on LeNet-5, AlexNet, and ResNet-50 models, respectively, with (almost) zero accuracy loss; (ii) even a significant 61x weight pruning in AlexNet (ImageNet) results in only minor degradation in actual accuracy compared with prior work; (iii) we are among the first to derive notable weight pruning results for ResNet and MobileNet models; (iv) we derive the first lossless, fully binarized (for all layers) LeNet-5 for MNIST and VGG-16 for CIFAR-10; and (v) we derive the first fully binarized (for all layers) ResNet for ImageNet with reasonable accuracy loss.
We introduce ADMM-pruned Compressive AutoEncoder (CAE-ADMM) that uses Alternative Direction Method of Multipliers (ADMM) to optimize the trade-off between distortion and efficiency of lossy image compression. Specifically, ADMM in our method is to promote sparsity to implicitly optimize the bitrate, different from entropy estimators used in the previous research. The experiments on public datasets show that our method outperforms the original CAE and some traditional codecs in terms of SSIM/MS-SSIM metrics, at reasonable inference speed.
We present a systematic weight pruning framework of deep neural networks (DNNs) using the alternating direction method of multipliers (ADMM). We first formulate the weight pruning problem of DNNs as a constrained nonconvex optimization problem, and then adopt the ADMM framework for systematic weight pruning. We show that ADMM is highly suitable for weight pruning due to the computational efficiency it offers. We achieve a much higher compression ratio compared with prior work while maintaining the same test accuracy, together with a faster convergence rate. Our models are released at https://g…
Syracuse University（雪城大学）；Northeastern University（东北大学）；George Mason University（乔治梅森大学）；MIT-IBM Watson AI Lab, IBM Research（IBM研究院MIT-IBM沃森人工智能实验室）
Deep neural networks (DNNs) although achieving human-level performance in many domains, have very large model size that hinders their broader applications on edge computing devices. Extensive research work have been conducted on DNN model compression or pruning. However, most of the previous work took heuristic approaches. This work proposes a progressive weight pruning approach based on ADMM (Alternating Direction Method of Multipliers), a powerful technique to deal with non-convex optimization problems with potentially combinatorial constraints. Motivated by dynamic programming, the proposed…
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…
Syracuse University（雪城大学）；Florida International University（佛罗里达国际大学）；Northeastern University（东北大学）
Weight pruning methods for deep neural networks (DNNs) have been investigated recently, but prior work in this area is mainly heuristic, iterative pruning, thereby lacking guarantees on the weight reduction ratio and convergence time. To mitigate these limitations, we present a systematic weight pruning framework of DNNs using the alternating direction method of multipliers (ADMM). We first formulate the weight pruning problem of DNNs as a nonconvex optimization problem with combinatorial constraints specifying the sparsity requirements, and then adopt the ADMM framework for systematic weight …
Northeastern University（东北大学）；Syracuse University（雪城大学）；SUNY University at Buffalo（纽约州立大学布法罗分校）；University of Southern California（南加利福尼亚大学）
To facilitate efficient embedded and hardware implementations of deep neural networks (DNNs), two important categories of DNN model compression techniques: weight pruning and weight quantization are investigated. The former leverages the redundancy in the number of weights, whereas the latter leverages the redundancy in bit representation of weights. However, there lacks a systematic framework of joint weight pruning and quantization of DNNs, thereby limiting the available model compression ratio. Moreover, the computation reduction, energy efficiency improvement, and hardware performance over…
The state-of-art DNN structures involve high computation and great demand for memory storage which pose intensive challenge on DNN framework resources. To mitigate the challenges, weight pruning techniques has been studied. However, high accuracy solution for extreme structured pruning that combines different types of structured sparsity still waiting for unraveling due to the extremely reduced weights in DNN networks. In this paper, we propose a DNN framework which combines two different types of structured weight pruning (filter and column prune) by incorporating alternating direction method…
This paper describes a channel-selection approach for simplifying deep neural networks. Specifically, we propose a new type of generic network layer, called pruning layer, to seamlessly augment a given pre-trained model for compression. Each pruning layer, comprising $1 \times 1$ depth-wise kernels, is represented with a dual format: one is real-valued and the other is binary. The former enables a two-phase optimization process of network pruning to operate with an end-to-end differentiable network, and the latter yields the mask information for channel selection. Our method progressively perf…
Large deep neural network (DNN) models pose the key challenge to energy efficiency due to the significantly higher energy consumption of off-chip DRAM accesses than arithmetic or SRAM operations. It motivates the intensive research on model compression with two main approaches. Weight pruning leverages the redundancy in the number of weights and can be performed in a non-structured, which has higher flexibility and pruning rate but incurs index accesses due to irregular weights, or structured manner, which preserves the full matrix structure with lower pruning rate. Weight quantization leverag…
Mila - Quebec AI Institute（米拉-魁北克人工智能研究所）；Landskape AI（Landskape人工智能）；UdeM（蒙特利尔大学）；IIT-Delhi（印度理工学院德里分校）；UT-Austin（德克萨斯大学奥斯汀分校）
With the latest advances in deep learning, there has been a lot of focus on the online learning paradigm due to its relevance in practical settings. Although many methods have been investigated for optimal learning settings in scenarios where the data stream is continuous over time, sparse networks training in such settings have often been overlooked. In this paper, we explore the problem of training a neural network with a target sparsity in a particular case of online learning: the anytime learning at macroscale paradigm (ALMA). We propose a novel way of progressive pruning, referred to as \…
Structured weight pruning is a representative model compression technique of DNNs for hardware efficiency and inference accelerations. Previous works in this area leave great space for improvement since sparse structures with combinations of different structured pruning schemes are not exploited fully and efficiently. To mitigate the limitations, we propose SS-Auto, a single-shot, automatic structured pruning framework that can achieve row pruning and column pruning simultaneously. We adopt soft constraint-based formulation to alleviate the strong non-convexity of l0-norm constraints used in s…
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）
The Chinese University of Hong Kong（香港中文大学）；SenseTime Research（商汤科技研究院）；École Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院）；Qing Yuan Research Institute, Shanghai Jiao Tong University（上海交通大学清源研究院）
Correspondence selection aims to correctly select the consistent matches (inliers) from an initial set of putative correspondences. The selection is challenging since putative matches are typically extremely unbalanced, largely dominated by outliers, and the random distribution of such outliers further complicates the learning process for learning-based methods. To address this issue, we propose to progressively prune the correspondences via a local-to-global consensus learning procedure. We introduce a ``pruning'' block that lets us identify reliable candidates among the initial matches accor…
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…
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…
Back to Fundamentals: Low-Level Visual Features Guided Progressive Token Pruning
Xidian University（西安电子科技大学）；University of Michigan – Shanghai Jiao Tong University Joint Institute（密歇根大学-上海交通大学联合学院）；Shanghai Jiao Tong University（上海交通大学）；Norwegian University of Science and Technology（挪威科技大学）；Xi’an Jiaotong-Liverpool University（西交利物浦大学）
University of Tennessee（田纳西大学）；Sun Yat-Sen University（中山大学）
Channel pruning has been identified as an effective approach to constructing efficient network structures. Its typical pipeline requires iterative pruning and fine-tuning. In this work, we propose a novel single-shot channel pruning approach based on alternating direction methods of multipliers (ADMM), which can eliminate the need for complex iterative pruning and fine-tuning procedure and achieve a target compression ratio with only one run of pruning and fine-tuning. To the best of our knowledge, this is the first study of single-shot channel pruning. The proposed method introduces filter-le…
Northeastern University（东北大学）；Syracuse University（雪城大学）；College of William and Mary（威廉与玛丽学院）；DiDi AI Labs（滴滴人工智能实验室）
Accelerating DNN execution on various resource-limited computing platforms has been a long-standing problem. Prior works utilize l1-based group lasso or dynamic regularization such as ADMM to perform structured pruning on DNN models to leverage the parallel computing architectures. However, both of the pruning dimensions and pruning methods lack universality, which leads to degraded performance and limited applicability. To solve the problem, we propose a new block-based pruning framework that comprises a general and flexible structured pruning dimension as well as a powerful and efficient rew…
Northeastern University（东北大学）；The College of William and Mary（威廉与玛丽学院）；University of Connecticut（康涅狄格大学）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）
Weight pruning of deep neural networks (DNNs) has been proposed to satisfy the limited storage and computing capability of mobile edge devices. However, previous pruning methods mainly focus on reducing the model size and/or improving performance without considering the privacy of user data. To mitigate this concern, we propose a privacy-preserving-oriented pruning and mobile acceleration framework that does not require the private training dataset. At the algorithm level of the proposed framework, a systematic weight pruning technique based on the alternating direction method of multipliers (…
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…
Neural network pruning is an important step in design process of efficient neural networks for edge devices with limited computational power. Pruning is a form of knowledge transfer from the weights of the original network to a smaller target subnetwork. We propose a new method for compute-constrained structured channel-wise pruning of convolutional neural networks. The method iteratively fine-tunes the network, while gradually tapering the computation resources available to the pruned network via a holonomic constraint in the method of Lagrangian multipliers framework. An explicit and adaptiv…
In lifelong learning, we wish to maintain and update a model (e.g., a neural network classifier) in the presence of new classification tasks that arrive sequentially. In this paper, we propose a learn-prune-share (LPS) algorithm which addresses the challenges of catastrophic forgetting, parsimony, and knowledge reuse simultaneously. LPS splits the network into task-specific partitions via an ADMM-based pruning strategy. This leads to no forgetting, while maintaining parsimony. Moreover, LPS integrates a novel selective knowledge sharing scheme into this ADMM optimization framework. This enable…
Filter pruning is a common method to achieve model compression and acceleration in deep neural networks (DNNs).Some research regarded filter pruning as a combinatorial optimization problem and thus used evolutionary algorithms (EA) to prune filters of DNNs. However, it is difficult to find a satisfactory compromise solution in a reasonable time due to the complexity of solution space searching. To solve this problem, we first formulate a multi-objective optimization problem based on a sub-network of the full model and propose a Sub-network Multiobjective Evolutionary Algorithm (SMOEA) for filt…
Zhejiang University（浙江大学）；NC State University（北卡罗来纳州立大学）
In this paper, we propose a novel distributed alternating direction method of multipliers (ADMM) algorithm with synergetic communication and computation, called SCCD-ADMM, to reduce the total communication and computation cost of the system. Explicitly, in the proposed algorithm, each node interacts with only part of its neighboring nodes, the number of which is progressively determined according to a heuristic searching procedure, which takes into account both the predicted convergence rate and the communication and computation costs at each iteration, resulting in a trade-off between communi…
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. …
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…
Tsinghua University（清华大学）；University of California, Santa Barbara（加州大学圣塔芭芭拉分校）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
As well known, the huge memory and compute costs of both artificial neural networks (ANNs) and spiking neural networks (SNNs) greatly hinder their deployment on edge devices with high efficiency. Model compression has been proposed as a promising technique to improve the running efficiency via parameter and operation reduction. Whereas, this technique is mainly practiced in ANNs rather than SNNs. It is interesting to answer how much an SNN model can be compressed without compromising its functionality, where two challenges should be addressed: i) the accuracy of SNNs is usually sensitive to mo…
California Institute of Technology（加州理工学院）；Ecole des Ponts ParisTech（巴黎高科路桥学院）
We propose a general and versatile framework that significantly speeds-up graphical model optimization while maintaining an excellent solution accuracy. The proposed approach relies on a multi-scale pruning scheme that is able to progressively reduce the solution space by use of a novel strategy based on a coarse-to-fine cascade of learnt classifiers. We thoroughly experiment with classic computer vision related MRF problems, where our framework constantly yields a significant time speed-up (with respect to the most efficient inference methods) and obtains a more accurate solution than directl…
College of William and Mary（威廉与玛丽学院）；Northeastern University（东北大学）；University of Southern California（南加州大学）
With the emergence of a spectrum of high-end mobile devices, many applications that formerly required desktop-level computation capability are being transferred to these devices. However, executing the inference of Deep Neural Networks (DNNs) is still challenging considering high computation and storage demands, specifically, if real-time performance with high accuracy is needed. Weight pruning of DNNs is proposed, but existing schemes represent two extremes in the design space: non-structured pruning is fine-grained, accurate, but not hardware friendly; structured pruning is coarse-grained, h…
POCKET: Pruning Random Convolution Kernels for Time Series Classification from a Feature Selection Perspective
State Key Laboratory of Radio Frequency Heterogeneous Integration (Shenzhen University)（射频异质集成国家重点实验室（深圳大学））；School of Electrical and Electronic Engineering, University College Dublin（都柏林大学学院电气与电子工程学院）
Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning
School of Computer Science and Engineering, Nanyang Technological University（南洋理工大学计算机科学与工程学院）；HP-NTU Digital Manufacturing Corporate Lab, Nanyang Technological University（惠普-南洋理工大学数字制造联合实验室）；Department of Computer Science, Norwegian University of Science and Technology（挪威科技大学计算机科学系）
Robinson College of Business, Georgia State University（佐治亚州立大学罗宾逊商学院）；School of Electrical and Computer Engineering, Georgia Tech（佐治亚理工学院电气与计算机工程学院）
We develop a fast, tractable technique called Net-Trim for simplifying a trained neural network. The method is a convex post-processing module, which prunes (sparsifies) a trained network layer by layer, while preserving the internal responses. We present a comprehensive analysis of Net-Trim from both the algorithmic and sample complexity standpoints, centered on a fast, scalable convex optimization program. Our analysis includes consistency results between the initial and retrained models before and after Net-Trim application and guarantees on the number of training samples needed to discover…
The high computation and memory storage of large deep neural networks (DNNs) models pose intensive challenges to the conventional Von-Neumann architecture, incurring substantial data movements in the memory hierarchy. The memristor crossbar array has emerged as a promising solution to mitigate the challenges and enable low-power acceleration of DNNs. Memristor-based weight pruning and weight quantization have been seperately investigated and proven effectiveness in reducing area and power consumption compared to the original DNN model. However, there has been no systematic investigation of mem…
Neural Architecture Search (NAS) has attracted growing interest. To reduce the search cost, recent work has explored weight sharing across models and made major progress in One-Shot NAS. However, it has been observed that a model with higher one-shot model accuracy does not necessarily perform better when stand-alone trained. To address this issue, in this paper, we propose Progressive Automatic Design of search space, named PAD-NAS. Unlike previous approaches where the same operation search space is shared by all the layers in the supernet, we formulate a progressive search strategy based on …
This paper presents a novel differentiable method for unstructured weight pruning of deep neural networks. Our learned-threshold pruning (LTP) method learns per-layer thresholds via gradient descent, unlike conventional methods where they are set as input. Making thresholds trainable also makes LTP computationally efficient, hence scalable to deeper networks. For example, it takes $30$ epochs for LTP to prune ResNet50 on ImageNet by a factor of $9.1$. This is in contrast to other methods that search for per-layer thresholds via a computationally intensive iterative pruning and fine-tuning proc…
Which Layer Causes Distribution Deviation? Entropy-Guided Adaptive Pruning for Diffusion and Flow Models
Stanford University（斯坦福大学）；North China Electric Power University（华北电力大学）；University of Technology Sydney（悉尼科技大学）；Harvard University（哈佛大学）；University of Science and Technology of China（中国科学技术大学）
Hong Kong University of Science and Technology（香港科技大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
We propose Joint-DetNAS, a unified NAS framework for object detection, which integrates 3 key components: Neural Architecture Search, pruning, and Knowledge Distillation. Instead of naively pipelining these techniques, our Joint-DetNAS optimizes them jointly. The algorithm consists of two core processes: student morphism optimizes the student's architecture and removes the redundant parameters, while dynamic distillation aims to find the optimal matching teacher. For student morphism, weight inheritance strategy is adopted, allowing the student to flexibly update its architecture while fully u…
Efficient search is a core issue in Neural Architecture Search (NAS). It is difficult for conventional NAS algorithms to directly search the architectures on large-scale tasks like ImageNet. In general, the cost of GPU hours for NAS grows with regard to training dataset size and candidate set size. One common way is searching on a smaller proxy dataset (e.g., CIFAR-10) and then transferring to the target task (e.g., ImageNet). These architectures optimized on proxy data are not guaranteed to be optimal on the target task. Another common way is learning with a smaller candidate set, which may r…
While vision transformers (ViTs) have continuously achieved new milestones in the field of computer vision, their sophisticated network architectures with high computation and memory costs have impeded their deployment on resource-limited edge devices. In this paper, we propose a hardware-efficient image-adaptive token pruning framework called HeatViT for efficient yet accurate ViT acceleration on embedded FPGAs. By analyzing the inherent computational patterns in ViTs, we first design an effective attention-based multi-head token selector, which can be progressively inserted before transforme…
Vehicle tracking in Wide Area Motion Imagery (WAMI) relies on associating vehicle detections across multiple WAMI frames to form tracks corresponding to individual vehicles. The temporal window length, i.e., the number $M$ of sequential frames, over which associations are collectively estimated poses a trade-off between accuracy and computational complexity. A larger $M$ improves performance because the increased temporal context enables the use of motion models and allows occlusions and spurious detections to be handled better. The number of total hypotheses tracks, on the other hand, grows e…
PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancement
USTC（中国科学技术大学）；Max Planck Institute（马克斯·普朗克研究所）；CUHK（香港中文大学）；SJTU（上海交通大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Chang’an University（长安大学）
School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院）；College of Computer Science, Sichuan University（四川大学计算机学院）
