Deploying deep learning models, comprising of non-linear combination of millions, even billions, of parameters is challenging given the memory, power and compute constraints of the real world. This situation has led to research into model compression techniques most of which rely on suboptimal heuristics and do not consider the parameter redundancies due to linear dependence between neuron activations in overparametrized networks. In this paper, we propose a novel model compression approach based on exploitation of linear dependence, that compresses networks by elimination of entire neurons and redistribution of their activations over other neurons in a manner that is provably lossless while training. We combine this approach with an annealing algorithm that may be applied during training, or even on a trained model, and demonstrate, using popular datasets, that our method results in a reduction of up to 99\% in overall network size with small loss in performance. Furthermore, we provide theoretical results showing that in overparametrized, locally linear (ReLU) neural networks where redundant features exist, and with correct hyperparameter selection, our method is indeed able to capture and suppress those dependencies.
Pruning and quantization are proven methods for improving the performance and storage efficiency of convolutional neural networks (CNNs). Pruning removes near-zero weights in tensors and masks weak connections between neurons in neighbouring layers. Quantization reduces the precision of weights by replacing them with numerically similar values that require less storage. In this paper, we identify another form of redundancy in CNN weight tensors, in the form of repeated patterns of similar values. We observe that pruning and quantization both tend to drastically increase the number of repeated …
North Carolina State University（北卡罗来纳州立大学）；William & Mary（威廉与玛丽学院）；Northeastern University（东北大学）
Data redundancy is ubiquitous in the inputs and intermediate results of Deep Neural Networks (DNN). It offers many significant opportunities for improving DNN performance and efficiency and has been explored in a large body of work. These studies have scattered in many venues across several years. The targets they focus on range from images to videos and texts, and the techniques they use to detect and exploit data redundancy also vary in many aspects. There is not yet a systematic examination and summary of the many efforts, making it difficult for researchers to get a comprehensive view of t…
Model compression and acceleration are attracting increasing attentions due to the demand for embedded devices and mobile applications. Research on efficient convolutional neural networks (CNNs) aims at removing feature redundancy by decomposing or optimizing the convolutional calculation. In this work, feature redundancy is assumed to exist among channels in CNN architectures, which provides some leeway to boost calculation efficiency. Aiming at channel compression, a novel convolutional construction named compact convolution is proposed to embrace the progress in spatial convolution, channel…
Locality-Aware Redundancy Pruning for LLM Depth Compression
University of Southern California（美国南加州大学）；Neural Superintelligence Lab, MODULABS（MODULABS神经超级智能实验室）；Seoul National University（首尔国立大学）；Inha University（釜山大学）
In video compression, coding efficiency is improved by reusing pixels from previously decoded frames via motion and residual compensation. We define two levels of hierarchical redundancy in video frames: 1) first-order: redundancy in pixel space, i.e., similarities in pixel values across neighboring frames, which is effectively captured using motion and residual compensation, 2) second-order: redundancy in motion and residual maps due to smooth motion in natural videos. While most of the existing neural video coding literature addresses first-order redundancy, we tackle the problem of capturin…
Massachusetts Institute of Technology（麻省理工学院）；University of California, San Diego（加州大学圣地亚哥分校）
The Poisson-sampling technique eliminates dependencies among symbol appearances in a random sequence. It has been used to simplify the analysis and strengthen the performance guarantees of randomized algorithms. Applying this method to universal compression, we relate the redundancies of fixed-length and Poisson-sampled sequences, use the relation to derive a simple single-letter formula that approximates the redundancy of any envelope class to within an additive logarithmic term. As a first application, we consider i.i.d. distributions over a small alphabet as a step-envelope class, and provi…
Smart Scissor: Coupling Spatial Redundancy Reduction and CNN Compression for Embedded Hardware
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）；HP Inc.（惠普公司）
University of Liège（列日大学）；Aristotle University of Thessaloniki（塞萨洛尼基亚里士多德大学）；Katholieke Universiteit Leuven（鲁汶天主教大学）
Within machine learning, the supervised learning field aims at modeling the input-output relationship of a system, from past observations of its behavior. Decision trees characterize the input-output relationship through a series of nested $if-then-else$ questions, the testing nodes, leading to a set of predictions, the leaf nodes. Several of such trees are often combined together for state-of-the-art performance: random forest ensembles average the predictions of randomized decision trees trained independently in parallel, while tree boosting ensembles train decision trees sequentially to ref…
Image compression with upsampling encodes information to succeedingly increase image resolution, for example by encoding differences in FUIF and JPEG XL. It is useful for progressive decoding, also often can improve compression ratio - both for lossless compression and e.g. DC coefficients of lossy. However, the currently used solutions rather do not exploit context dependence for encoding of such upscaling information. This article discusses simple inexpensive general techniques for this purpose, which allowed to save on average $0.645$ bits/difference (between $0.138$ and $1.489$) for the la…
Effective MoE-based LLM Compression by Exploiting Heterogeneous Inter-Group Experts Routing Frequency and Information Density
Department of Computer Science, Stevens Institute of Technology, Hoboken, NJ, USA（计算机科学系，史蒂文斯理工学院，新泽西州霍博肯）；Northeastern University, Boston, MA, USA（东北大学，波士顿，马萨诸塞州）
The University of Tennessee Knoxville（田纳西大学诺克斯维尔分校）；Sun Yat-sen University（中山大学）
Convolutional neural network (CNN) pruning has become one of the most successful network compression approaches in recent years. Existing works on network pruning usually focus on removing the least important filters in the network to achieve compact architectures. In this study, we claim that identifying structural redundancy plays a more essential role than finding unimportant filters, theoretically and empirically. We first statistically model the network pruning problem in a redundancy reduction perspective and find that pruning in the layer(s) with the most structural redundancy outperfor…
Trinity College Dublin（都柏林圣三一学院）；Dublin City University（都柏林城市大学）
We show how parameter redundancy in Convolutional Neural Network (CNN) filters can be effectively reduced by pruning in spectral domain. Specifically, the representation extracted via Discrete Cosine Transform (DCT) is more conducive for pruning than the original space. By relying on a combination of weight tensor reshaping and reordering we achieve high levels of layer compression with just minor accuracy loss. Our approach is applied to compress pretrained CNNs and we show that minor additional fine-tuning allows our method to recover the original model performance after a significant parame…
PACC: Protocol-Aware Cross-Layer Compression for Compact Network Traffic Representation
University of Electronic Science and Technology of China（电子科技大学）；University of Hong Kong（香港大学）；Renmin University of China（中国人民大学）；Hong Kong Polytechnic University（香港理工大学）
SparseST: Exploiting Data Sparsity in Spatiotemporal Modeling and Prediction
Department of Industrial and Systems Engineering, Rensselaer Polytechnic Institute（工业与系统工程系，罗切斯特理工学院）；Department of Electrical, Computer, and Systems Engineering and the Department of Computer Science, Rensselaer Polytechnic Institute（电气、计算机与系统工程系和计算机科学系，罗切斯特理工学院）；IBM Research（IBM研究院）
Training deep neural networks on large datasets containing high-dimensional data requires a large amount of computation. A solution to this problem is data-parallel distributed training, where a model is replicated into several computational nodes that have access to different chunks of the data. This approach, however, entails high communication rates and latency because of the computed gradients that need to be shared among nodes at every iteration. The problem becomes more pronounced in the case that there is wireless communication between the nodes (i.e. due to the limited network bandwidt…
The application of the context-adaptive entropy model significantly improves the rate-distortion (R-D) performance, in which hyperpriors and autoregressive models are jointly utilized to effectively capture the spatial redundancy of the latent representations. However, the latent representations still contain some spatial correlations. In addition, these methods based on the context-adaptive entropy model cannot be accelerated in the decoding process by parallel computing devices, e.g. FPGA or GPU. To alleviate these limitations, we propose a learned multi-resolution image compression framewor…
University of Maryland（马里兰大学）；Shandong University（山东大学）
Network compression is crucial to making the deep networks to be more efficient, faster, and generalizable to low-end hardware. Current network compression methods have two open problems: first, there lacks a theoretical framework to estimate the maximum compression rate; second, some layers may get over-prunned, resulting in significant network performance drop. To solve these two problems, this study propose a gradient-matrix singularity analysis-based method to estimate the maximum network redundancy. Guided by that maximum rate, a novel and efficient hierarchical network pruning algorithm …
Exploiting Correlations in Federated Learning: Opportunities and Practical Limitations
Department of Electrical Engineering (ISY), Linköping University（_linköping大学电气工程系）；CentraleSupélec, CNRS, L2S, Université Paris-Saclay（_centralesupelec, CNRS, L2S, 巴黎萨克雷大学）；Division of Decision and Control Systems, School of EECS, KTH Royal Institute of Technology（_决策与控制系统系，皇家理工学院）
