ClickTrain: Efficient and Accurate End-to-End Deep Learning Training via Fine-Grained Architecture-Preserving Pruning
Washington State University（华盛顿州立大学）；Northeastern University（东北大学）；College of William and Mary（威廉与玛丽学院）；University of Sydney（悉尼大学）；University of Alabama（阿拉巴马大学）
Chengming Zhang, Geng Yuan, Wei Niu, Jiannan Tian, Sian Jin, Donglin Zhuang, Zhe Jiang, Yanzhi Wang, Bin Ren, Shuaiwen Leon Song, Dingwen Tao
备注：
12 pages, 15 figures, 2 tables, published by ICS'21
Convolutional neural networks (CNNs) are becoming increasingly deeper, wider, and non-linear because of the growing demand on prediction accuracy and analysis quality. The wide and deep CNNs, however, require a large amount of computing resources and processing time. Many previous works have studied model pruning to improve inference performance, but little work has been done for effectively reducing training cost. In this paper, we propose ClickTrain: an efficient and accurate end-to-end training and pruning framework for CNNs. Different from the existing pruning-during-training work, ClickTrain provides higher model accuracy and compression ratio via fine-grained architecture-preserving pruning. By leveraging pattern-based pruning with our proposed novel accurate weight importance estimation, dynamic pattern generation and selection, and compiler-assisted computation optimizations, ClickTrain generates highly accurate and fast pruned CNN models for direct deployment without any extra time overhead, compared with the baseline training. ClickTrain also reduces the end-to-end time cost of the pruning-after-training method by up to 2.3X with comparable accuracy and compression ratio. Moreover, compared with the state-of-the-art pruning-during-training approach, ClickTrain provides significant improvements both accuracy and compression ratio on the tested CNN models and datasets, under similar limited training time.
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…
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…
The recent trend toward increasingly deep convolutional neural networks (CNNs) leads to a higher demand of computational power and memory storage. Consequently, the deployment of CNNs in hardware has become more challenging. In this paper, we propose an Intra-Kernel Regular (IKR) pruning scheme to reduce the size and computational complexity of the CNNs by removing redundant weights at a fine-grained level. Unlike other pruning methods such as Fine-Grained pruning, IKR pruning maintains regular kernel structures that are exploitable in a hardware accelerator. Experimental results demonstrate u…
We introduce hybrid pruning which combines both coarse-grained channel and fine-grained weight pruning to reduce model size, computation and power demands with no to little loss in accuracy for enabling modern networks deployment on resource-constrained devices, such as always-on security cameras and drones. Additionally, to effectively perform channel pruning, we propose a fast sensitivity test that helps us quickly identify the sensitivity of within and across layers of a network to the output accuracy for target multiplier accumulators (MACs) or accuracy tolerance. Our experiment shows sign…
Pruning is a popular technique for reducing the model size and computational cost of convolutional neural networks (CNNs). However, a slow retraining or fine-tuning procedure is often required to recover the accuracy loss caused by pruning. Recently, a new research direction on weight pruning, pruning-at-initialization (PAI), is proposed to directly prune CNNs before training so that fine-tuning or retraining can be avoided. While PAI has shown promising results in reducing the model size, existing approaches rely on fine-grained weight pruning which requires unstructured sparse matrix computa…
Northeastern University（东北大学）；College of William and Mary（威廉与玛丽学院）；Michigan State University（密歇根州立大学）；University of Pittsburgh（匹兹堡大学）
Weight pruning is an effective model compression technique to tackle the challenges of achieving real-time deep neural network (DNN) inference on mobile devices. However, prior pruning schemes have limited application scenarios due to accuracy degradation, difficulty in leveraging hardware acceleration, and/or restriction on certain types of DNN layers. In this paper, we propose a general, fine-grained structured pruning scheme and corresponding compiler optimizations that are applicable to any type of DNN layer while achieving high accuracy and hardware inference performance. With the flexibi…
Network pruning can significantly reduce the computation and memory footprint of large neural networks. To achieve a good trade-off between model size and performance, popular pruning techniques usually rely on hand-crafted heuristics and require manually setting the compression ratio for each layer. This process is typically time-consuming and requires expert knowledge to achieve good results. In this paper, we propose NAP, a unified and automatic pruning framework for both fine-grained and structured pruning. It can find out unimportant components of a network and automatically decide approp…
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 …
Unstructured neural network pruning algorithms have achieved impressive compression rates. However, the resulting - typically irregular - sparse matrices hamper efficient hardware implementations, leading to additional memory usage and complex control logic that diminishes the benefits of unstructured pruning. This has spurred structured coarse-grained pruning solutions that prune entire filters or even layers, enabling efficient implementation at the expense of reduced flexibility. Here we propose a flexible new pruning mechanism that facilitates pruning at different granularities (weights, k…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
This paper presents a method for adding multiple tasks to a single deep neural network while avoiding catastrophic forgetting. Inspired by network pruning techniques, we exploit redundancies in large deep networks to free up parameters that can then be employed to learn new tasks. By performing iterative pruning and network re-training, we are able to sequentially "pack" multiple tasks into a single network while ensuring minimal drop in performance and minimal storage overhead. Unlike prior work that uses proxy losses to maintain accuracy on older tasks, we always optimize for the task at han…
Technical University of Munich, Germany（慕尼黑工业大学，德国）；University of Oxford, UK（牛津大学，英国）；Johns Hopkins University, USA（约翰斯·霍普金斯大学，美国）
Attributing the output of a neural network to the contribution of given input elements is a way of shedding light on the black-box nature of neural networks. Due to the complexity of current network architectures, current gradient-based attribution methods provide very noisy or coarse results. We propose to prune a neural network for a given single input to keep only neurons that highly contribute to the prediction. We show that by input-specific pruning, network gradients change from reflecting local (noisy) importance information to global importance. Our proposed method is efficient and gen…
We present an elegant framework of fine-grained neural architecture search (FGNAS), which allows to employ multiple heterogeneous operations within a single layer and can even generate compositional feature maps using several different base operations. FGNAS runs efficiently in spite of significantly large search space compared to other methods because it trains networks end-to-end by a stochastic gradient descent method. Moreover, the proposed framework allows to optimize the network under predefined resource constraints in terms of number of parameters, FLOPs and latency. FGNAS has been appl…
RS-Prune: Training-Free Data Pruning at High Ratios for Efficient Remote Sensing Diffusion Foundation Models
Department of Earth System Science, Tsinghua University（清华大学地球系统科学系）；School of Artificial Intelligence, Sun Yat-sen University（中山大学人工智能学院）；National Supercomputing Center in Shenzhen（深圳国家超算中心）；Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生学院）；Department of Geography, The University of Hong Kong（香港大学地理系）；Wangxuan Institute of Computer Technology, Peking University（北京大学王轩计算机技术研究所）
Northeastern University（东北大学）；College of William and Mary（威廉与玛丽学院）；Rice University（莱斯大学）；Michigan State University（密歇根州立大学）
With the increasing demand to efficiently deploy DNNs on mobile edge devices, it becomes much more important to reduce unnecessary computation and increase the execution speed. Prior methods towards this goal, including model compression and network architecture search (NAS), are largely performed independently and do not fully consider compiler-level optimizations which is a must-do for mobile acceleration. In this work, we first propose (i) a general category of fine-grained structured pruning applicable to various DNN layers, and (ii) a comprehensive, compiler automatic code generation fram…
TAP-ViTs: Task-Adaptive Pruning for On-Device Deployment of Vision Transformers
State Key Laboratory of Blockchain and Data Security（区块链与数据安全国家重点实验室）；College of Computer Science and Technology（计算机科学与技术学院）；College of Computer Science and Electronic Engineering（计算机科学与电子工程学院）
In this paper, we propose the differentiable channel sparsity search (DCSS) for convolutional neural networks. Unlike traditional channel pruning algorithms which require users to manually set prune ratios for each convolutional layer, DCSS automatically searches the optimal combination of sparsities. Inspired by the differentiable architecture search (DARTS), we draw lessons from the continuous relaxation and leverage the gradient information to balance the computational cost and metrics. Since directly applying the scheme of DARTS causes shape mismatching and excessive memory consumption, we…
School of Computer Science and Information Engineering, Hefei University of Technology（合肥工业大学计算机与信息工程学院）
The existing convolutional neural network pruning algorithms can be divided into two categories: coarse-grained clipping and fine-grained clipping. This paper proposes a coarse and fine-grained automatic pruning algorithm, which can achieve more efficient and accurate compression acceleration for convolutional neural networks. First, cluster the intermediate feature maps of the convolutional neural network to obtain the network structure after coarse-grained clipping, and then use the particle swarm optimization algorithm to iteratively search and optimize the structure. Finally, the optimal n…
Multi-Grained Feature Pruning for Video-Based Human Pose Estimation
College of Computer Science and Technology, Zhejiang Gongshang University（浙江工商大学计算机科学与技术学院）；School of Computing, National University of Singapore（新加坡国立大学计算机学院）；Zhejiang University（浙江大学）；Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security（杭州高新区（滨江）区块链与数据安全研究院）；College of Computer Science and Technology, Jilin University（吉林大学计算机科学与技术学院）；College of Computer Science and Technology, Zhejiang University of Technology（浙江工业大学计算机科学与技术学院）
This paper introduces channel gating, a dynamic, fine-grained, and hardware-efficient pruning scheme to reduce the computation cost for convolutional neural networks (CNNs). Channel gating identifies regions in the features that contribute less to the classification result, and skips the computation on a subset of the input channels for these ineffective regions. Unlike static network pruning, channel gating optimizes CNN inference at run-time by exploiting input-specific characteristics, which allows substantially reducing the compute cost with almost no accuracy loss. We experimentally show …
Pattern matching of streaming time series with lower latency under limited computing resource comes to a critical problem, especially as the growth of Industry 4.0 and Industry Internet of Things. However, against traditional single pattern matching problem, a pattern may contain multiple segments representing different statistical properties or physical meanings for more precise and expressive matching in real world. Hence, we formulate a new problem, called "fine-grained pattern matching", which allows users to specify varied granularities of matching deviation to different segments of a giv…
Image restoration tasks have achieved tremendous performance improvements with the rapid advancement of deep neural networks. However, most prevalent deep learning models perform inference statically, ignoring that different images have varying restoration difficulties and lightly degraded images can be well restored by slimmer subnetworks. To this end, we propose a new solution pipeline dubbed ClassPruning that utilizes networks with different capabilities to process images with varying restoration difficulties. In particular, we use a lightweight classifier to identify the image restoration …
Changsha University of Science and Technology（长沙理工大学）；Xidian University（西安电子科技大学）
Pruning on neural networks before training not only compresses the original models, but also accelerates the network training phase, which has substantial application value. The current work focuses on fine-grained pruning, which uses metrics to calculate weight scores for weight screening, and extends from the initial single-order pruning to iterative pruning. Through these works, we argue that network pruning can be summarized as an expressive force transfer process of weights, where the reserved weights will take on the expressive force from the removed ones for the purpose of maintaining t…
University of Twente（特文特大学）；University of Duisburg-Essen（杜伊斯堡-埃森大学）
Prototype-based methods use interpretable representations to address the black-box nature of deep learning models, in contrast to post-hoc explanation methods that only approximate such models. We propose the Neural Prototype Tree (ProtoTree), an intrinsically interpretable deep learning method for fine-grained image recognition. ProtoTree combines prototype learning with decision trees, and thus results in a globally interpretable model by design. Additionally, ProtoTree can locally explain a single prediction by outlining a decision path through the tree. Each node in our binary tree contain…
Despite the remarkable performance, modern deep neural networks are inevitably accompanied by a significant amount of computational cost for learning and deployment, which may be incompatible with their usage on edge devices. Recent efforts to reduce these overheads involve pruning and decomposing the parameters of various layers without performance deterioration. Inspired by several decomposition studies, in this paper, we propose a novel energy-aware pruning method that quantifies the importance of each filter in the network using nuclear-norm (NN). Proposed energy-aware pruning leads to sta…
Tsinghua University（清华大学）；Harbin Institute of Technology（哈尔滨工业大学）；Beihang University（北京航空航天大学）；Microsoft Research Asia（微软亚洲研究院）
In trained deep neural networks, unstructured pruning can reduce redundant weights to lower storage cost. However, it requires the customization of hardwares to speed up practical inference. Another trend accelerates sparse model inference on general-purpose hardwares by adopting coarse-grained sparsity to prune or regularize consecutive weights for efficient computation. But this method often sacrifices model accuracy. In this paper, we propose a novel fine-grained sparsity approach, balanced sparsity, to achieve high model accuracy with commercial hardwares efficiently. Our approach adapts t…
Bifocal: Training-Free Mixed Granularity Visual Token Pruning for Multimodal LLMs
Eastern Institute of Technology（东方理工大学）；Shanghai Jiao Tong University（上海交通大学）；Uppsala University（乌普萨拉大学）；University of Science and Technology of China（中国科学技术大学）
Layer as Puzzle Pieces: Compressing Large Language Models through Layer Concatenation
South China University of Technology（华南理工大学）；JD Explore Academy（JD探索学院）；Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区）；University of Sydney（悉尼大学）；Pazhou Lab（琶洲实验室）
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…
