Recent works imply that the channel pruning can be regarded as searching optimal sub-structure from unpruned networks. However, existing works based on this observation require training and evaluating a large number of structures, which limits their application. In this paper, we propose a novel differentiable method for channel pruning, named Differentiable Markov Channel Pruning (DMCP), to efficiently search the optimal sub-structure. Our method is differentiable and can be directly optimized by gradient descent with respect to standard task loss and budget regularization (e.g. FLOPs constraint). In DMCP, we model the channel pruning as a Markov process, in which each state represents for retaining the corresponding channel during pruning, and transitions between states denote the pruning process. In the end, our method is able to implicitly select the proper number of channels in each layer by the Markov process with optimized transitions. To validate the effectiveness of our method, we perform extensive experiments on Imagenet with ResNet and MobilenetV2. Results show our method can achieve consistent improvement than state-of-the-art pruning methods in various FLOPs settings. The code is available at https://github.com/zx55/dmcp
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…
The convolutional neural network has achieved great success in fulfilling computer vision tasks despite large computation overhead against efficient deployment. Structured (channel) pruning is usually applied to reduce the model redundancy while preserving the network structure, such that the pruned network can be easily deployed in practice. However, existing structured pruning methods require hand-crafted rules which may lead to tremendous pruning space. In this paper, we introduce Differentiable Annealing Indicator Search (DAIS) that leverages the strength of neural architecture search in t…
We propose a simple but effective data-driven channel pruning algorithm, which compresses deep neural networks in a differentiable way by exploiting the characteristics of operations. The proposed approach makes a joint consideration of batch normalization (BN) and rectified linear unit (ReLU) for channel pruning; it estimates how likely the two successive operations deactivate each feature map and prunes the channels with high probabilities. To this end, we learn differentiable masks for individual channels and make soft decisions throughout the optimization procedure, which facilitates to ex…
ETH Zürich（苏黎世联邦理工学院）；The University of Sydney（悉尼大学）；KU Leuven（鲁汶大学）
Network pruning has been the driving force for the acceleration of neural networks and the alleviation of model storage/transmission burden. With the advent of AutoML and neural architecture search (NAS), pruning has become topical with automatic mechanism and searching based architecture optimization. Yet, current automatic designs rely on either reinforcement learning or evolutionary algorithm. Due to the non-differentiability of those algorithms, the pruning algorithm needs a long searching stage before reaching the convergence. To circumvent this problem, this paper introduces a differenti…
We propose a new gradient-based approach for extracting sub-architectures from a given large model. Contrarily to existing pruning methods, which are unable to disentangle the network architecture and the corresponding weights, our architecture-pruning scheme produces transferable new structures that can be successfully retrained to solve different tasks. We focus on a transfer-learning setup where architectures can be trained on a large data set but very few data points are available for fine-tuning them on new tasks. We define a new gradient-based algorithm that trains architectures of arbit…
Kuaishou Technology（快手科技）；University of Texas at Austin（德克萨斯大学奥斯汀分校）
Model compression techniques are recently gaining explosive attention for obtaining efficient AI models for various real-time applications. Channel pruning is one important compression strategy and is widely used in slimming various DNNs. Previous gate-based or importance-based pruning methods aim to remove channels whose importance is smallest. However, it remains unclear what criteria the channel importance should be measured on, leading to various channel selection heuristics. Some other sampling-based pruning methods deploy sampling strategies to train sub-nets, which often causes the trai…
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…
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…
The Better You Learn, The Smarter You Prune: Towards Efficient Vision-language-action Models via Differentiable Token Pruning
LiAuto Inc.（LiAuto公司）；School of Vehicle and Mobility, Tsinghua University（清华大学车辆与移动学院）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
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…
S2HPruner: Soft-to-Hard Distillation Bridges the Discretization Gap in Pruning
School of Information Science and Technology, Fudan University（复旦大学信息科学与技术学院）；Academy for Engineering and Technology, Fudan University（复旦大学工程技术研究院）；Shanghai AI Laboratory（上海人工智能实验室）
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…
Structure pruning is an effective method to compress and accelerate neural networks. While filter and channel pruning are preferable to other structure pruning methods in terms of realistic acceleration and hardware compatibility, pruning methods with a finer granularity, such as intra-channel pruning, are expected to be capable of yielding more compact and computationally efficient networks. Typical intra-channel pruning methods utilize a static and hand-crafted pruning granularity due to a large search space, which leaves room for improvement in their pruning performance. In this work, we in…
LUMS School of Science and Engineering（拉合尔管理科学大学科学与工程学院）
Network pruning reduces the size of neural networks by removing (pruning) neurons such that the performance drop is minimal. Traditional pruning approaches focus on designing metrics to quantify the usefulness of a neuron which is often quite tedious and sub-optimal. More recent approaches have instead focused on training auxiliary networks to automatically learn how useful each neuron is however, they often do not take computational limitations into account. In this work, we propose a general methodology for pruning neural networks. Our proposed methodology can prune neural networks to respec…
Strategic Analytics — lastminute.com group（战略分析——lastminute.com集团）；DISCo — Università degli Studi di Milano Bicocca（米兰比可卡大学数据信息系统与通信系）
In this work we present a method to improve the pruning step of the current state-of-the-art methodology to compress neural networks. The novelty of the proposed pruning technique is in its differentiability, which allows pruning to be performed during the backpropagation phase of the network training. This enables an end-to-end learning and strongly reduces the training time. The technique is based on a family of differentiable pruning functions and a new regularizer specifically designed to enforce pruning. The experimental results show that the joint optimization of both the thresholds and …
Beijing National Research Center for Information Science and Technology (BNRist)（北京信息科学与技术国家研究中心（BNRist））；School of Software, Tsinghua University（清华大学软件学院）；Department of Electronic Engineering, Tsinghua University（清华大学电子工程系）；Department of Automation, Tsinghua University（清华大学自动化系）；Institute for Brain and Cognitive Sciences, Tsinghua University（清华大学脑与认知科学研究院）；WMG Data Science, University of Warwick（华威大学制造工程学院数据科学系）；Kwai Seattle AI Lab, Kwai FeDA Lab, Kwai AI platform（快手西雅图人工智能实验室、快手联邦与分布式人工智能实验室、快手人工智能平台）
Deep Neural Network (DNN) is powerful but computationally expensive and memory intensive, thus impeding its practical usage on resource-constrained front-end devices. DNN pruning is an approach for deep model compression, which aims at eliminating some parameters with tolerable performance degradation. In this paper, we propose a novel momentum-SGD-based optimization method to reduce the network complexity by on-the-fly pruning. Concretely, given a global compression ratio, we categorize all the parameters into two parts at each training iteration which are updated using different rules. In th…
In seeking for sparse and efficient neural network models, many previous works investigated on enforcing L1 or L0 regularizers to encourage weight sparsity during training. The L0 regularizer measures the parameter sparsity directly and is invariant to the scaling of parameter values, but it cannot provide useful gradients, and therefore requires complex optimization techniques. The L1 regularizer is almost everywhere differentiable and can be easily optimized with gradient descent. Yet it is not scale-invariant, causing the same shrinking rate to all parameters, which is inefficient in increa…
Recently, differentiable neural architecture search methods significantly reduce the search cost by constructing a super network and relax the architecture representation by assigning architecture weights to the candidate operations. All the existing methods determine the importance of each operation directly by architecture weights. However, architecture weights cannot accurately reflect the importance of each operation; that is, the operation with the highest weight might not related to the best performance. To alleviate this deficiency, we propose a simple yet effective solution to neural a…
Transferrable neural architecture search can be viewed as a binary optimization problem where a single optimal path should be selected among candidate paths in each edge within the repeated cell block of the directed a cyclic graph form. Recently, the field of differentiable architecture search attempts to relax the search problem continuously using a one-shot network that combines all the candidate paths in search space. However, when the one-shot network is pruned to the model in the discrete architecture space by the derivation algorithm, performance is significantly degraded to an almost r…
Recently, deep learning has become a de facto standard in machine learning with convolutional neural networks (CNNs) demonstrating spectacular success on a wide variety of tasks. However, CNNs are typically very demanding computationally at inference time. One of the ways to alleviate this burden on certain hardware platforms is quantization relying on the use of low-precision arithmetic representation for the weights and the activations. Another popular method is the pruning of the number of filters in each layer. While mainstream deep learning methods train the neural networks weights while …
Evolutionary Negative Module Pruning for Better LoRA Merging
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；School of Software Technology, Zhejiang University（浙江大学软件学院）；State Key Laboratory of Blockchain and Security, Zhejiang University（浙江大学区块链与安全国家重点实验室）；Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security（杭州高新技术区（滨江）区块链与数据安全研究院）
Energy-Regularized Spatial Masking: A Novel Approach to Enhancing Robustness and Interpretability in Vision Models
DAVID Lab, UVSQ, Paris-Saclay University（DAVID实验室，UVSQ，巴黎-萨克雷大学）；LIPN, UMR CNRS 7030, Sorbonne Paris Nord University（LIPN，UMR CNRS 7030，索邦巴黎北大学）；LISN, Paris-Saclay University（LISN，巴黎-萨克雷大学）
University of New South Wales（新南威尔士大学）；Jiangnan University（江南大学）；University of Technology Sydney（悉尼科技大学）；University of California San Diego（加州大学圣地亚哥分校）；CSIRO’s Data61（澳大利亚联邦科学与工业研究组织Data61）
Zero-Shot Learning (ZSL) aims to transfer classification capability from seen to unseen classes. Recent methods have proved that generalization and specialization are two essential abilities to achieve good performance in ZSL. However, focusing on only one of the abilities may result in models that are either too general with degraded classification ability or too specialized to generalize to unseen classes. In this paper, we propose an end-to-end network, termed as BGSNet, which equips and balances generalization and specialization abilities at the instance and dataset level. Specifically, BG…
We propose a practical method for $L_0$ norm regularization for neural networks: pruning the network during training by encouraging weights to become exactly zero. Such regularization is interesting since (1) it can greatly speed up training and inference, and (2) it can improve generalization. AIC and BIC, well-known model selection criteria, are special cases of $L_0$ regularization. However, since the $L_0$ norm of weights is non-differentiable, we cannot incorporate it directly as a regularization term in the objective function. We propose a solution through the inclusion of a collection o…
We formulate the entropy of a quantized artificial neural network as a differentiable function that can be plugged as a regularization term into the cost function minimized by gradient descent. Our formulation scales efficiently beyond the first order and is agnostic of the quantization scheme. The network can then be trained to minimize the entropy of the quantized parameters, so that they can be optimally compressed via entropy coding. We experiment with our entropy formulation at quantizing and compressing well-known network architectures over multiple datasets. Our approach compares favora…
Xiamen University（厦门大学）；National Institute for Data Science in Health and Medicine, Xiamen University（厦门大学健康医疗大数据国家研究院）；Peng Cheng Laboratory（鹏城实验室）；University of Chinese Academy of Sciences（中国科学院大学）；Noah’s Ark Lab, Huawei Technologies（华为技术有限公司诺亚方舟实验室）；Peking University（北京大学）
Neural architecture search (NAS) remains a challenging problem, which is attributed to the indispensable and time-consuming component of performance estimation (PE). In this paper, we provide a novel yet systematic rethinking of PE in a resource constrained regime, termed budgeted PE (BPE), which precisely and effectively estimates the performance of an architecture sampled from an architecture space. Since searching an optimal BPE is extremely time-consuming as it requires to train a large number of networks for evaluation, we propose a Minimum Importance Pruning (MIP) approach. Given a datas…
Arizona State University（亚利桑那州立大学）；ByteDance（字节跳动）
Feature selection has been an essential step in developing industry-scale deep Click-Through Rate (CTR) prediction systems. The goal of neural feature selection (NFS) is to choose a relatively small subset of features with the best explanatory power as a means to remove redundant features and reduce computational cost. Inspired by gradient-based neural architecture search (NAS) and network pruning methods, people have tackled the NFS problem with Gating approach that inserts a set of differentiable binary gates to drop less informative features. The binary gates are optimized along with the ne…
Differentiable architecture search (DARTS) is an effective method for data-driven neural network design based on solving a bilevel optimization problem. Despite its success in many architecture search tasks, there are still some concerns about the accuracy of first-order DARTS and the efficiency of the second-order DARTS. In this paper, we formulate a single level alternative and a relaxed architecture search (RARTS) method that utilizes the whole dataset in architecture learning via both data and network splitting, without involving mixed second derivatives of the corresponding loss functions…
The University of Hong Kong（香港大学）；MPI Informatics Saarland Informatics Campus（马克斯·普朗克信息学研究所萨尔信息学园区）；Wuhan University（武汉大学）
Motion coherence is an important clue for distinguishing true correspondences from false ones. Modeling motion coherence on sparse putative correspondences is challenging due to their sparsity and uneven distributions. Existing works on motion coherence are sensitive to parameter settings and have difficulty in dealing with complex motion patterns. In this paper, we introduce a network called Laplacian Motion Coherence Network (LMCNet) to learn motion coherence property for correspondence pruning. We propose a novel formulation of fitting coherent motions with a smooth function on a graph of c…
Efficient and Flexible Neural Network Training through Layer-wise Feedback Propagation
Fraunhofer Heinrich Hertz Institute（弗劳恩霍夫海因里希·赫兹研究所）；Otto-von-Guericke University（奥托·冯·古里克大学）；Singapore Institute of Technology（新加坡理工大学）；Technische Universität Berlin（柏林工业大学）；BIFOLD – Berlin Institute for the Foundations of Learning and Data（柏林学习与数据基础研究所）；Technological University Dublin（都柏林理工大学）
Lipschitz Constant Meets Condition Number: Learning Robust and Compact Deep Neural Networks
Software Engineering Institute, East China Normal University（华东师范大学软件工程学院）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Tianjin University（天津大学）
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
This work presents a method for adapting a single, fixed deep neural network to multiple tasks without affecting performance on already learned tasks. By building upon ideas from network quantization and pruning, we learn binary masks that piggyback on an existing network, or are applied to unmodified weights of that network to provide good performance on a new task. These masks are learned in an end-to-end differentiable fashion, and incur a low overhead of 1 bit per network parameter, per task. Even though the underlying network is fixed, the ability to mask individual weights allows for the…
