Pruning is one of the most effective model reduction techniques. Deep networks require massive computation and such models need to be compressed to bring them on edge devices. Most existing pruning techniques are focused on vision-based models like convolutional networks, while text-based models are still evolving. The emergence of multi-modal multi-task learning calls for a general method that works on vision and text architectures simultaneously. We introduce a \emph{differentiable mask}, that induces sparsity on various granularity to fill this gap. We apply our method successfully to prune weights, filters, subnetwork of a convolutional architecture, as well as nodes of a recurrent network.
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 …
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…
University of Oxford（牛津大学）；ServiceNow；Google Brain；MILA（MILA（蒙特利尔学习算法研究所））
We study an approach to learning pruning masks by optimizing the expected loss of stochastic pruning masks, i.e., masks which zero out each weight independently with some weight-specific probability. We analyze the training dynamics of the induced stochastic predictor in the setting of linear regression, and observe a data-adaptive L1 regularization term, in contrast to the dataadaptive L2 regularization term known to underlie dropout in linear regression. We also observe a preference to prune weights that are less well-aligned with the data labels. We evaluate probabilistic fine-tuning for op…
Facebook AI Research（脸书人工智能研究院）；Brown University（布朗大学）
We examine how recently documented, fundamental phenomena in deep learning models subject to pruning are affected by changes in the pruning procedure. Specifically, we analyze differences in the connectivity structure and learning dynamics of pruned models found through a set of common iterative pruning techniques, to address questions of uniqueness of trainable, high-sparsity sub-networks, and their dependence on the chosen pruning method. In convolutional layers, we document the emergence of structure induced by magnitude-based unstructured pruning in conjunction with weight rewinding that r…
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…
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 constra…
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…
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…
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…
Ningxia University（宁夏大学）；Collaborative Innovation Center for Ningxia Big Data and Artificial Intelligence co-founded by Ningxia Municipality and Ministry of Education（宁夏大数据与人工智能省部共建协同创新中心）
Existing differentiable channel pruning methods often attach scaling factors or masks behind channels to prune filters with less importance, and implicitly assume uniform contribution of input samples to filter importance. Specifically, the effects of instance complexity on pruning performance are not yet fully investigated in static network pruning. In this paper, we propose a simple yet effective differentiable network pruning method CWP based on instance complexity weighted filter importance scores. We define instance complexity related weight for each instance by giving higher weights to h…
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…
Modern neural network architectures typically have many millions of parameters and can be pruned significantly without substantial loss in effectiveness which demonstrates they are over-parameterized. The contribution of this work is two-fold. The first is a method for approximating a multivariate Bernoulli random variable by means of a deterministic and differentiable transformation of any real-valued multivariate random variable. The second is a method for model selection by element-wise multiplication of parameters with approximate binary gates that may be computed deterministically or stoc…
University of Cambridge（剑桥大学）；Samsung AI Centre Cambridge（三星剑桥人工智能中心）
Embedded and personal IoT devices are powered by microcontroller units (MCUs), whose extreme resource scarcity is a major obstacle for applications relying on on-device deep learning inference. Orders of magnitude less storage, memory and computational capacity, compared to what is typically required to execute neural networks, impose strict structural constraints on the network architecture and call for specialist model compression methodology. In this work, we present a differentiable structured network pruning method for convolutional neural networks, which integrates a model's MCU-specific…
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…
Facebook AI Research（Facebook人工智能研究院）；Brown University（布朗大学）
The observation of sparse trainable sub-networks within over-parametrized networks - also known as Lottery Tickets (LTs) - has prompted inquiries around their trainability, scaling, uniqueness, and generalization properties. Across 28 combinations of image classification tasks and architectures, we discover differences in the connectivity structure of LTs found through different iterative pruning techniques, thus disproving their uniqueness and connecting emergent mask structure to the choice of pruning. In addition, we propose a consensus-based method for generating refined lottery tickets. T…
SparseSwaps: Tractable LLM Pruning Mask Refinement at Scale
Department for AI in Society, Science, and Technology, Zuse Institute Berlin, Germany（人工智能与社会、科学与技术部门，柏林Zuse研究所，德国）；Institute of Mathematics, Technische Universität Berlin, Germany（数学研究所，柏林技术大学，德国）
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…
As deep neural networks are growing in size and being increasingly deployed to more resource-limited devices, there has been a recent surge of interest in network pruning methods, which aim to remove less important weights or activations of a given network. A common limitation of most existing pruning techniques, is that they require pre-training of the network at least once before pruning, and thus we can benefit from reduction in memory and computation only at the inference time. However, reducing the training cost of neural networks with rapid structural pruning may be beneficial either to …
Recent studies assessing the efficacy of pruning neural networks methods uncovered a surprising finding: when conducting ablation studies on existing pruning-at-initialization methods, namely SNIP, GraSP, SynFlow, and magnitude pruning, performances of these methods remain unchanged and sometimes even improve when randomly shuffling the mask positions within each layer (Layerwise Shuffling) or sampling new initial weight values (Reinit), while keeping pruning masks the same. We attempt to understand the reason behind such network immunity towards weight/mask modifications, by studying layer-wi…
The University of Hong Kong（香港大学）；City University of Hong Kong（香港城市大学）
We present a novel network pruning algorithm called Dynamic Sparse Training that can jointly find the optimal network parameters and sparse network structure in a unified optimization process with trainable pruning thresholds. These thresholds can have fine-grained layer-wise adjustments dynamically via backpropagation. We demonstrate that our dynamic sparse training algorithm can easily train very sparse neural network models with little performance loss using the same number of training epochs as dense models. Dynamic Sparse Training achieves the state of the art performance compared with ot…
Modern deep neural networks are often too large to use in many practical scenarios. Neural network pruning is an important technique for reducing the size of such models and accelerating inference. Gibbs pruning is a novel framework for expressing and designing neural network pruning methods. Combining approaches from statistical physics and stochastic regularization methods, it can train and prune a network simultaneously in such a way that the learned weights and pruning mask are well-adapted for each other. It can be used for structured or unstructured pruning and we propose a number of spe…
Dynamic model pruning is a recent direction that allows for the inference of a different sub-network for each input sample during deployment. However, current dynamic methods rely on learning a continuous channel gating through regularization by inducing sparsity loss. This formulation introduces complexity in balancing different losses (e.g task loss, regularization loss). In addition, regularization based methods lack transparent tradeoff hyperparameter selection to realize a computational budget. Our contribution is two-fold: 1) decoupled task and pruning losses. 2) Simple hyperparameter se…
Pruning is an efficient model compression technique to remove redundancy in the connectivity of deep neural networks (DNNs). Computations using sparse matrices obtained by pruning parameters, however, exhibit vastly different parallelism depending on the index representation scheme. As a result, fine-grained pruning has not gained much attention due to its irregular index form leading to large memory footprint and low parallelism for convolutions and matrix multiplications. In this paper, we propose a new network pruning technique that generates a low-rank binary index matrix to compress index…
University of Amsterdam（阿姆斯特丹大学）；University of Edinburgh（爱丁堡大学）
Graph neural networks (GNNs) have become a popular approach to integrating structural inductive biases into NLP models. However, there has been little work on interpreting them, and specifically on understanding which parts of the graphs (e.g. syntactic trees or co-reference structures) contribute to a prediction. In this work, we introduce a post-hoc method for interpreting the predictions of GNNs which identifies unnecessary edges. Given a trained GNN model, we learn a simple classifier that, for every edge in every layer, predicts if that edge can be dropped. We demonstrate that such a clas…
A central goal in deep learning is to learn compact representations of features at every layer of a neural network, which is useful for both unsupervised representation learning and structured network pruning. While there is a growing body of work in structured pruning, current state-of-the-art methods suffer from two key limitations: (i) instability during training, and (ii) need for an additional step of fine-tuning, which is resource-intensive. At the core of these limitations is the lack of a systematic approach that jointly prunes and refines weights during training in a single stage, and…
Sparsity has become one of the promising methods to compress and accelerate Deep Neural Networks (DNNs). Among different categories of sparsity, structured sparsity has gained more attention due to its efficient execution on modern accelerators. Particularly, N:M sparsity is attractive because there are already hardware accelerator architectures that can leverage certain forms of N:M structured sparsity to yield higher compute-efficiency. In this work, we focus on N:M sparsity and extensively study and evaluate various training recipes for N:M sparsity in terms of the trade-off between model a…
Tandon School of Engineering（坦顿工程学院）；New York University（纽约大学）
Deep neural networks are often highly overparameterized, prohibiting their use in compute-limited systems. However, a line of recent works has shown that the size of deep networks can be considerably reduced by identifying a subset of neuron indicators (or mask) that correspond to significant weights prior to training. We demonstrate that an simple iterative mask discovery method can achieve state-of-the-art compression of very deep networks. Our algorithm represents a hybrid approach between single shot network pruning methods (such as SNIP) with Lottery-Ticket type approaches. We validate ou…
Pruning is an effective way to reduce the huge inference cost of Transformer models. However, prior work on pruning Transformers requires retraining the models. This can add high training cost and high complexity to model deployment, making it difficult to use in many practical situations. To address this, we propose a fast post-training pruning framework for Transformers that does not require any retraining. Given a resource constraint and a sample dataset, our framework automatically prunes the Transformer model using structured sparsity methods. To retain high accuracy without retraining, w…
Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient
School of Computer Science, Wuhan University（武汉大学计算机学院）；School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院）；School of Data Science, Fudan University（复旦大学数据科学学院）
LLM-Barber: Block-Aware Rebuilder for Sparsity Mask in One-Shot for Large Language Models
School of Microelectronics, Southern University of Science and Technology（微电子学院，南方科技大学）；Department of Electrical and Electronic Engineering, University of Hong Kong（电气与电子工程系，香港大学）
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…
Neural networks (NNs) whose subnetworks implement reusable functions are expected to offer numerous advantages, including compositionality through efficient recombination of functional building blocks, interpretability, preventing catastrophic interference, etc. Understanding if and how NNs are modular could provide insights into how to improve them. Current inspection methods, however, fail to link modules to their functionality. In this paper, we present a novel method based on learning binary weight masks to identify individual weights and subnets responsible for specific functions. Using t…
Xiamen University（厦门大学）；Southern Illinois University Carbondale（南伊利诺伊大学卡本代尔分校）；Kneron Inc.（耐能智慧股份有限公司）；Yulin Normal University（玉林师范学院）
Since sparse neural networks usually contain many zero weights, these unnecessary network connections can potentially be eliminated without degrading network performance. Therefore, well-designed sparse neural networks have the potential to significantly reduce FLOPs and computational resources. In this work, we propose a new automatic pruning method - Sparse Connectivity Learning (SCL). Specifically, a weight is re-parameterized as an element-wise multiplication of a trainable weight variable and a binary mask. Thus, network connectivity is fully described by the binary mask, which is modulat…
We propose three novel pruning techniques to improve the cost and results of inference-aware Differentiable Neural Architecture Search (DNAS). First, we introduce Prunode, a stochastic bi-path building block for DNAS, which can search over inner hidden dimensions with O(1) memory and compute complexity. Second, we present an algorithm for pruning blocks within a stochastic layer of the SuperNet during the search. Third, we describe a novel technique for pruning unnecessary stochastic layers during the search. The optimized models resulting from the search are called PruNet and establishes a ne…
Convolutional Neural Networks (CNNs) compression is crucial to deploying these models in edge devices with limited resources. Existing channel pruning algorithms for CNNs have achieved plenty of success on complex models. They approach the pruning problem from various perspectives and use different metrics to guide the pruning process. However, these metrics mainly focus on the model's `outputs' or `weights' and neglect its `interpretations' information. To fill in this gap, we propose to address the channel pruning problem from a novel perspective by leveraging the interpretations of a model …
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…
