Deep neural networks (DNNs) have been extremely successful in solving many challenging AI tasks in natural language processing, speech recognition, and computer vision nowadays. However, DNNs are typically computation intensive, memory demanding, and power hungry, which significantly limits their usage on platforms with constrained resources. Therefore, a variety of compression techniques (e.g. quantization, pruning, and knowledge distillation) have been proposed to reduce the size and power consumption of DNNs. Blockwise knowledge distillation is one of the compression techniques that can effectively reduce the size of a highly complex DNN. However, it is not widely adopted due to its long training time. In this paper, we propose a novel parallel blockwise distillation algorithm to accelerate the distillation process of sophisticated DNNs. Our algorithm leverages local information to conduct independent blockwise distillation, utilizes depthwise separable layers as the efficient replacement block architecture, and properly addresses limiting factors (e.g. dependency, synchronization, and load balancing) that affect parallelism. The experimental results running on an AMD server with four Geforce RTX 2080Ti GPUs show that our algorithm can achieve 3x speedup plus 19% energy savings on VGG distillation, and 3.5x speedup plus 29% energy savings on ResNet distillation, both with negligible accuracy loss. The speedup of ResNet distillation can be further improved to 3.87 when using four RTX6000 GPUs in a distributed cluster.
Qualcomm Technologies, Inc.（高通技术公司）；Qualcomm AI Research（高通人工智能研究院）
As edge devices become prevalent, deploying Deep Neural Networks (DNN) on edge devices has become a critical issue. However, DNN requires a high computational resource which is rarely available for edge devices. To handle this, we propose a novel model compression method for the devices with limited computational resources, called PQK consisting of pruning, quantization, and knowledge distillation (KD) processes. Unlike traditional pruning and KD, PQK makes use of unimportant weights pruned in the pruning process to make a teacher network for training a better student network without pre-train…
Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression
Department of Computer Science, University of West Florida（计算机科学系，西佛罗里达大学）；Department of Mathematics and Statistics, University of West Florida（数学与统计学系，西佛罗里达大学）；Department of Intelligent Systems and Robotics, University of West Florida（智能系统与机器人系，西佛罗里达大学）；Institute of Human and Machine Cognition（人机认知研究所）；DEVCOM Army Research Laboratory（陆军研究实验室）
Seoul National University（首尔国立大学）；Yonsei University（延世大学）；NAVER（NAVER（韩国NAVER公司））
Training large deep neural network models is highly challenging due to their tremendous computational and memory requirements. Blockwise distillation provides one promising method towards faster convergence by splitting a large model into multiple smaller models. In state-of-the-art blockwise distillation methods, training is performed block-by-block in a data-parallel manner using multiple GPUs. To produce inputs for the student blocks, the teacher model is executed from the beginning until the current block under training. However, this results in a high overhead of redundant teacher executi…
Microsoft Dynamics 365 AI Research（微软Dynamics 365人工智能研究院）
Existing language model compression methods mostly use a simple L2 loss to distill knowledge in the intermediate representations of a large BERT model to a smaller one. Although widely used, this objective by design assumes that all the dimensions of hidden representations are independent, failing to capture important structural knowledge in the intermediate layers of the teacher network. To achieve better distillation efficacy, we propose Contrastive Distillation on Intermediate Representations (CoDIR), a principled knowledge distillation framework where the student is trained to distill know…
University of Liverpool（利物浦大学）；Huawei Ireland Research Center（华为爱尔兰研究中心）
Pruning aims to reduce the number of parameters while maintaining performance close to the original network. This work proposes a novel \emph{self-distillation} based pruning strategy, whereby the representational similarity between the pruned and unpruned versions of the same network is maximized. Unlike previous approaches that treat distillation and pruning separately, we use distillation to inform the pruning criteria, without requiring a separate student network as in knowledge distillation. We show that the proposed {\em cross-correlation objective for self-distilled pruning} implicitly …
Adaptive Heterogeneous Compression for Resource-Efficient Federated Knowledge Distillation
School of Information Engineering, Guangdong University of Technology（广东工业大学信息工程学院）；School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications（重庆邮电大学通信与信息工程学院）
Microsoft Dynamics 365 AI Research（微软Dynamics 365人工智能研究院）
Pre-trained language models such as BERT have proven to be highly effective for natural language processing (NLP) tasks. However, the high demand for computing resources in training such models hinders their application in practice. In order to alleviate this resource hunger in large-scale model training, we propose a Patient Knowledge Distillation approach to compress an original large model (teacher) into an equally-effective lightweight shallow network (student). Different from previous knowledge distillation methods, which only use the output from the last layer of the teacher network for …
The Chinese University of Hong Kong（香港中文大学）；Tencent AI Lab（腾讯人工智能实验室）
Model compression has been widely adopted to obtain light-weighted deep neural networks. Most prevalent methods, however, require fine-tuning with sufficient training data to ensure accuracy, which could be challenged by privacy and security issues. As a compromise between privacy and performance, in this paper we investigate few shot network compression: given few samples per class, how can we effectively compress the network with negligible performance drop? The core challenge of few shot network compression lies in high estimation errors from the original network during inference, since the…
Acoustic Event Detection (AED), aiming at detecting categories of events based on audio signals, has found application in many intelligent systems. Recently deep neural network significantly advances this field and reduces detection errors to a large scale. However how to efficiently execute deep models in AED has received much less attention. Meanwhile state-of-the-art AED models are based on large deep models, which are computational demanding and challenging to deploy on devices with constrained computational resources. In this paper, we present a simple yet effective compression approach w…
Deep neural network compression techniques such as pruning and weight tensor decomposition usually require fine-tuning to recover the prediction accuracy when the compression ratio is high. However, conventional fine-tuning suffers from the requirement of a large training set and the time-consuming training procedure. This paper proposes a novel solution for knowledge distillation from label-free few samples to realize both data efficiency and training/processing efficiency. We treat the original network as "teacher-net" and the compressed network as "student-net". A 1x1 convolution layer is a…
Vast requirement of computation power of Deep Neural Networks is a major hurdle to their real world applications. Many recent Application Specific Integrated Circuit (ASIC) chips feature dedicated hardware support for Neural Network Acceleration. However, as ASICs take multiple years to develop, they are inevitably out-paced by the latest development in Neural Architecture Research. For example, Transformer Networks do not have native support on many popular chips, and hence are difficult to deploy. In this paper, we propose Arch-Net, a family of Neural Networks made up of only operators effic…
Knowledge distillation is the procedure of transferring "knowledge" from a large model (the teacher) to a more compact one (the student), often being used in the context of model compression. When both models have the same architecture, this procedure is called self-distillation. Several works have anecdotally shown that a self-distilled student can outperform the teacher on held-out data. In this work, we systematically study self-distillation in a number of settings. We first show that even with a highly accurate teacher, self-distillation allows a student to surpass the teacher in all cases…
National University of Defense Technology（国防科技大学）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；Facebook Inc.（脸书公司）；Tsinghua University（清华大学）
The soaring demand for intelligent mobile applications calls for deploying powerful deep neural networks (DNNs) on mobile devices. However, the outstanding performance of DNNs notoriously relies on increasingly complex models, which in turn is associated with an increase in computational expense far surpassing mobile devices' capacity. What is worse, app service providers need to collect and utilize a large volume of users' data, which contain sensitive information, to build the sophisticated DNN models. Directly deploying these models on public mobile devices presents prohibitive privacy risk…
LIB-KD: Teaching Inductive Bias for Efficient Vision Transformer Distillation and Compression
Department of Electrical Engineering Indian Institute of Technology Delhi（电子工程系印度理工学院德里）；Yogananda School of AI, Computers and Data Sciences（Yoganananda人工智能、计算机与数据科学学院）
Network pruning is one of the most dominant methods for reducing the heavy inference cost of deep neural networks. Existing methods often iteratively prune networks to attain high compression ratio without incurring significant loss in performance. However, we argue that conventional methods for retraining pruned networks (i.e., using small, fixed learning rate) are inadequate as they completely ignore the benefits from snapshots of iterative pruning. In this work, we show that strong ensembles can be constructed from snapshots of iterative pruning, which achieve competitive performance and va…
Sun Yat-sen University（中山大学）；Alibaba Group（阿里巴巴集团）
On many natural language processing tasks, large pre-trained language models (PLMs) have shown overwhelming performances compared with traditional neural network methods. Nevertheless, their huge model size and low inference speed have hindered the deployment on resource-limited devices in practice. In this paper, we target to compress PLMs with knowledge distillation, and propose a hierarchical relational knowledge distillation (HRKD) method to capture both hierarchical and domain relational information. Specifically, to enhance the model capability and transferability, we leverage the idea o…
Extreme compression, particularly ultra-low bit precision (binary/ternary) quantization, has been proposed to fit large NLP models on resource-constraint devices. However, to preserve the accuracy for such aggressive compression schemes, cutting-edge methods usually introduce complicated compression pipelines, e.g., multi-stage expensive knowledge distillation with extensive hyperparameter tuning. Also, they oftentimes focus less on smaller transformer models that have already been heavily compressed via knowledge distillation and lack a systematic study to show the effectiveness of their meth…
Istanbul Technical University（伊斯坦布尔理工大学）；University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）；Arcelik Research and Development（阿奇立克研发中心）
One of the most efficient methods for model compression is hint distillation, where the student model is injected with information (hints) from several different layers of the teacher model. Although the selection of hint points can drastically alter the compression performance, conventional distillation approaches overlook this fact and use the same hint points as in the early studies. Therefore, we propose a clustering based hint selection methodology, where the layers of teacher model are clustered with respect to several metrics and the cluster centers are used as the hint points. Our meth…
Knowledge distillation (KD) is commonly deemed as an effective model compression technique in which a compact model (student) is trained under the supervision of a larger pretrained model or an ensemble of models (teacher). Various techniques have been proposed since the original formulation, which mimic different aspects of the teacher such as the representation space, decision boundary, or intra-data relationship. Some methods replace the one-way knowledge distillation from a static teacher with collaborative learning between a cohort of students. Despite the recent advances, a clear underst…
Exploring the Limits of Model Compression in LLMs: A Knowledge Distillation Study on QA Tasks
Fraunhofer Institute for Intelligent Analysis and Information Systems（弗劳恩霍夫智能分析与信息系统研究所）；University of Southern Denmark（南丹麦大学）；Fraunhofer Institute for Applied Information Technology（弗劳恩霍夫应用信息科技研究所）；University Hospital of Cologne（科隆大学医院）
New Jersey Institute of Technology（新泽西理工学院）；Microsoft Research（微软研究院）；Rice University（莱斯大学）
Recent work has focused on compressing pre-trained language models (PLMs) like BERT where the major focus has been to improve the in-distribution performance for downstream tasks. However, very few of these studies have analyzed the impact of compression on the generalizability and robustness of compressed models for out-of-distribution (OOD) data. Towards this end, we study two popular model compression techniques including knowledge distillation and pruning and show that the compressed models are significantly less robust than their PLM counterparts on OOD test sets although they obtain simi…
Network pruning and knowledge distillation are two widely-known model compression methods that efficiently reduce computation cost and model size. A common problem in both pruning and distillation is to determine compressed architecture, i.e., the exact number of filters per layer and layer configuration, in order to preserve most of the original model capacity. In spite of the great advances in existing works, the determination of an excellent architecture still requires human interference or tremendous experimentations. In this paper, we propose an architecture slimming method that automates…
Several methods of knowledge distillation have been developed for neural network compression. While they all use the KL divergence loss to align the soft outputs of the student model more closely with that of the teacher, the various methods differ in how the intermediate features of the student are encouraged to match those of the teacher. In this paper, we propose a simple-to-implement method using auxiliary classifiers at intermediate layers for matching features, which we refer to as multi-head knowledge distillation (MHKD). We add loss terms for training the student that measure the dissi…
When Smaller Wins: Dual-Stage Distillation and Pareto-Guided Compression of Liquid Neural Networks for Edge Battery Prognostics
Singapore Institute of Technology（新加坡科技学院）；Institute of Materials Research and Engineering（材料研究与工程研究所）；Agency for Science, Technology and Research（科技研究局）；Institute of High Performance Computing（高性能计算研究所）
Despite the success of Deep Learning (DL), the deployment of modern DL models requiring large computational power poses a significant problem for resource-constrained systems. This necessitates building compact networks that reduce computations while preserving performance. Traditional Knowledge Distillation (KD) methods that transfer knowledge from teacher to student (a) use a single-stage and (b) require the whole data set while distilling the knowledge to the student. In this work, we propose a new method called Stagewise Knowledge Distillation (SKD) which builds on traditional KD methods b…
The University of Sydney（悉尼大学）；Birkbeck College, University of London（伦敦大学伯贝克学院）；UBTECH（优必选）
In recent years, deep neural networks have been successful in both industry and academia, especially for computer vision tasks. The great success of deep learning is mainly due to its scalability to encode large-scale data and to maneuver billions of model parameters. However, it is a challenge to deploy these cumbersome deep models on devices with limited resources, e.g., mobile phones and embedded devices, not only because of the high computational complexity but also the large storage requirements. To this end, a variety of model compression and acceleration techniques have been developed. …
Paul G. Allen School of Computer Science & Engineering, University of Washington（华盛顿大学保罗·G·艾伦计算机科学与工程学院）；Language Technologies Institute, Carnegie Mellon University（卡内基梅隆大学语言技术研究所）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
We present Referee, a novel framework for sentence summarization that can be trained reference-free (i.e., requiring no gold summaries for supervision), while allowing direct control for compression ratio. Our work is the first to demonstrate that reference-free, controlled sentence summarization is feasible via the conceptual framework of Symbolic Knowledge Distillation (West et al., 2022), where latent knowledge in pre-trained language models is distilled via explicit examples sampled from the teacher models, further purified with three types of filters: length, fidelity, and Information Bot…
Graduate School at Shenzhen, Tsinghua University（清华大学深圳研究生院）；Tsinghua-Berkeley Shenzhen Institute, Tsinghua University（清华大学清华-伯克利深圳学院）
How to obtain a model with good interpretability and performance has always been an important research topic. In this paper, we propose rectified decision trees (ReDT), a knowledge distillation based decision trees rectification with high interpretability, small model size, and empirical soundness. Specifically, we extend the impurity calculation and the pure ending condition of the classical decision tree to propose a decision tree extension that allows the use of soft labels generated by a well-trained teacher model in training and prediction process. It is worth noting that for the acquisit…
Pixel Distillation: A New Knowledge Distillation Scheme for Low-Resolution Image Recognition
Northwestern Polytechnical University（西北工业大学）；Xijing Hospital, The Fourth Military Medical University（第四军医大学西京医院）；Beijing Technology And Business University（北京工商大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Nankai University（南开大学）；Hefei Comprehensive National Science Center（合肥综合性国家科学中心）
University of British Columbia（不列颠哥伦比亚大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
Word-embeddings are vital components of Natural Language Processing (NLP) models and have been extensively explored. However, they consume a lot of memory which poses a challenge for edge deployment. Embedding matrices, typically, contain most of the parameters for language models and about a third for machine translation systems. In this paper, we propose Distilled Embedding, an (input/output) embedding compression method based on low-rank matrix decomposition and knowledge distillation. First, we initialize the weights of our decomposed matrices by learning to reconstruct the full pre-traine…
Institute for Infocomm Research, A*STAR（新加坡科技研究局资讯通信研究院）；School of Computing, National University of Singapore（新加坡国立大学计算机学院）
With the increasing popularity of deep learning on edge devices, compressing large neural networks to meet the hardware requirements of resource-constrained devices became a significant research direction. Numerous compression methodologies are currently being used to reduce the memory sizes and energy consumption of neural networks. Knowledge distillation (KD) is among such methodologies and it functions by using data samples to transfer the knowledge captured by a large model (teacher) to a smaller one(student). However, due to various reasons, the original training data might not be accessi…
University of Texas at Austin（德克萨斯大学奥斯汀分校）；Texas A&M University（德州农工大学）；Kwai Inc.（快手公司）
Vision transformers (ViTs) have gained popularity recently. Even without customized image operators such as convolutions, ViTs can yield competitive performance when properly trained on massive data. However, the computational overhead of ViTs remains prohibitive, due to stacking multi-head self-attention modules and else. Compared to the vast literature and prevailing success in compressing convolutional neural networks, the study of Vision Transformer compression has also just emerged, and existing works focused on one or two aspects of compression. This paper proposes a unified ViT compress…
Ajou University（亚洲大学）；Hyundai Motor Company（现代汽车公司）；Naver AI Lab（Naver人工智能实验室）
Point-cloud based 3D object detectors recently have achieved remarkable progress. However, most studies are limited to the development of network architectures for improving only their accuracy without consideration of the computational efficiency. In this paper, we first propose an autoencoder-style framework comprising channel-wise compression and decompression via interchange transfer-based knowledge distillation. To learn the map-view feature of a teacher network, the features from teacher and student networks are independently passed through the shared autoencoder; here, we use a compress…
University of California, San Diego（加州大学圣地亚哥分校）；Beihang University（北京航空航天大学）；Microsoft Research Asia（微软亚洲研究院）
In this paper, we propose a novel model compression approach to effectively compress BERT by progressive module replacing. Our approach first divides the original BERT into several modules and builds their compact substitutes. Then, we randomly replace the original modules with their substitutes to train the compact modules to mimic the behavior of the original modules. We progressively increase the probability of replacement through the training. In this way, our approach brings a deeper level of interaction between the original and compact models. Compared to the previous knowledge distillat…
Zhejiang University（浙江大学）；Stevens Institute of Technology（史蒂文斯理工学院）；Alibaba-Zhejiang University Joint Research Institute of Frontier Technologies（阿里巴巴-浙江大学前沿技术联合研究院）
Knowledge distillation has demonstrated encouraging performances in deep model compression. Most existing approaches, however, require massive labeled data to accomplish the knowledge transfer, making the model compression a cumbersome and costly process. In this paper, we investigate the practical few-shot knowledge distillation scenario, where we assume only a few samples without human annotations are available for each category. To this end, we introduce a principled dual-stage distillation scheme tailored for few-shot data. In the first step, we graft the student blocks one by one onto the…
Indian Institute of Technology, Kharagpur（印度理工学院卡拉格普尔分校）
Singing Voice Detection (SVD) has been an active area of research in music information retrieval (MIR). Currently, two deep neural network-based methods, one based on CNN and the other on RNN, exist in literature that learn optimized features for the voice detection (VD) task and achieve state-of-the-art performance on common datasets. Both these models have a huge number of parameters (1.4M for CNN and 65.7K for RNN) and hence not suitable for deployment on devices like smartphones or embedded sensors with limited capacity in terms of memory and computation power. The most popular method to a…
Amazon Web Services（亚马逊云科技）；Hong Kong University of Science and Technology（香港科技大学）
Communication overhead is a major bottleneck hampering the scalability of distributed machine learning systems. Recently, there has been a surge of interest in using gradient compression to improve the communication efficiency of distributed neural network training. Using 1-bit quantization, signSGD with majority vote achieves a 32x reduction on communication cost. However, its convergence is based on unrealistic assumptions and can diverge in practice. In this paper, we propose a general distributed compressed SGD with Nesterov's momentum. We consider two-way compression, which compresses the…
