Recurrent Neural Networks (RNNs) have been widely used in sequence analysis and modeling. However, when processing high-dimensional data, RNNs typically require very large model sizes, thereby bringing a series of deployment challenges. Although the state-of-the-art tensor decomposition approaches can provide good model compression performance, these existing methods are still suffering some inherent limitations, such as restricted representation capability and insufficient model complexity reduction. To overcome these limitations, in this paper we propose to develop compact RNN models using Hierarchical Tucker (HT) decomposition. HT decomposition brings strong hierarchical structure to the decomposed RNN models, which is very useful and important for enhancing the representation capability. Meanwhile, HT decomposition provides higher storage and computational cost reduction than the existing tensor decomposition approaches for RNN compression. Our experimental results show that, compared with the state-of-the-art compressed RNN models, such as TT-LSTM, TR-LSTM and BT-LSTM, our proposed HT-based LSTM (HT-LSTM), consistently achieves simultaneous and significant increases in both compression ratio and test accuracy on different datasets.
Convolutional Neural Networks (CNN) are the state-of-the-art in the field of visual computing. However, a major problem with CNNs is the large number of floating point operations (FLOPs) required to perform convolutions for large inputs. When considering the application of CNNs to video data, convolutional filters become even more complex due to the extra temporal dimension. This leads to problems when respective applications are to be deployed on mobile devices, such as smart phones, tablets, micro-controllers or similar, indicating less computational power. Kim et al. (2016) proposed using a…
Arizona State University（亚利桑那州立大学）；Samsung Research America（三星美国研究院）
Recurrent neural networks (RNNs) achieve cutting-edge performance on a variety of problems. However, due to their high computational and memory demands, deploying RNNs on resource constrained mobile devices is a challenging task. To guarantee minimum accuracy loss with higher compression rate and driven by the mobile resource requirement, we introduce a novel model compression approach DirNet based on an optimized fast dictionary learning algorithm, which 1) dynamically mines the dictionary atoms of the projection dictionary matrix within layer to adjust the compression rate 2) adaptively chan…
RIKEN, Center for Advanced Intelligence Project AIP（理化学研究所先进智能项目中心）
In the machine learning fields, Recurrent Neural Network (RNN) has become a popular architecture for sequential data modeling. However, behind the impressive performance, RNNs require a large number of parameters for both training and inference. In this paper, we are trying to reduce the number of parameters and maintain the expressive power from RNN simultaneously. We utilize several tensor decompositions method including CANDECOMP/PARAFAC (CP), Tucker decomposition and Tensor Train (TT) to re-parameterize the Gated Recurrent Unit (GRU) RNN. We evaluate all tensor-based RNNs performance on se…
Nara Institute of Science and Technology（奈良先端科学技术大学院大学）
Recurrent Neural Network (RNN) are a popular choice for modeling temporal and sequential tasks and achieve many state-of-the-art performance on various complex problems. However, most of the state-of-the-art RNNs have millions of parameters and require many computational resources for training and predicting new data. This paper proposes an alternative RNN model to reduce the number of parameters significantly by representing the weight parameters based on Tensor Train (TT) format. In this paper, we implement the TT-format representation for several RNN architectures such as simple RNN and Gat…
Principal component analysis, dictionary learning, and auto-encoders are all unsupervised methods for learning representations from a large amount of training data. In all these methods, the higher the dimensions of the input data, the longer it takes to learn. We introduce a class of neural networks, termed RandNet, for learning representations using compressed random measurements of data of interest, such as images. RandNet extends the convolutional recurrent sparse auto-encoder architecture to dense networks and, more importantly, to the case when the input data are compressed random measur…
University of Electronic Science and Technology of China（电子科技大学）；Weill Cornell Medical College, Cornell University（康奈尔大学威尔康奈尔医学院）；Tencent Inc.（腾讯公司）
Recurrent Neural Networks (RNNs) and their variants, such as Long-Short Term Memory (LSTM) networks, and Gated Recurrent Unit (GRU) networks, have achieved promising performance in sequential data modeling. The hidden layers in RNNs can be regarded as the memory units, which are helpful in storing information in sequential contexts. However, when dealing with high dimensional input data, such as video and text, the input-to-hidden linear transformation in RNNs brings high memory usage and huge computational cost. This makes the training of RNNs unscalable and difficult. To address this challen…
Traditional Recurrent Neural Networks assume vectorized data as inputs. However many data from modern science and technology come in certain structures such as tensorial time series data. To apply the recurrent neural networks for this type of data, a vectorisation process is necessary, while such a vectorisation leads to the loss of the precise information of the spatial or longitudinal dimensions. In addition, such a vectorized data is not an optimum solution for learning the representation of the longitudinal data. In this paper, we propose a new variant of tensorial neural networks which d…
Compressing Recurrent Neural Networks for FPGA-accelerated Implementation in Fluorescence Lifetime Imaging
Center for Modeling, Simulation, & Imaging in Medicine（医学建模、仿真与成像中心）；Rensselaer Polytechnic Institute（伦斯勒理工学院）；IBM T.J. Watson Research Center（IBM TJ·沃森研究中心）
The significant computational costs of deploying neural networks in large-scale or resource constrained environments, such as data centers and mobile devices, has spurred interest in model compression, which can achieve a reduction in both arithmetic operations and storage memory. Several techniques have been proposed for reducing or compressing the parameters for feed-forward and convolutional neural networks, but less is understood about the effect of parameter compression on recurrent neural networks (RNN). In particular, the extent to which the recurrent parameters can be compressed and th…
Recurrent Neural Networks (RNN) can be difficult to deploy on resource constrained devices due to their size.As a result, there is a need for compression techniques that can significantly compress RNNs without negatively impacting task accuracy. This paper introduces a method to compress RNNs for resource constrained environments using Kronecker product (KP). KPs can compress RNN layers by 15-38x with minimal accuracy loss. By quantizing the resulting models to 8-bits, we further push the compression factor to 50x. We show that KP can beat the task accuracy achieved by other state-of-the-art c…
We study the problem of compressing recurrent neural networks (RNNs). In particular, we focus on the compression of RNN acoustic models, which are motivated by the goal of building compact and accurate speech recognition systems which can be run efficiently on mobile devices. In this work, we present a technique for general recurrent model compression that jointly compresses both recurrent and non-recurrent inter-layer weight matrices. We find that the proposed technique allows us to reduce the size of our Long Short-Term Memory (LSTM) acoustic model to a third of its original size with neglig…
Skolkovo Institute of Science and Technology（斯科尔科沃科学技术研究所）；Institute of Numerical Mathematics RAS（俄罗斯科学院数值数学研究所）
Deep neural networks are surprisingly efficient at solving practical tasks, but the theory behind this phenomenon is only starting to catch up with the practice. Numerous works show that depth is the key to this efficiency. A certain class of deep convolutional networks -- namely those that correspond to the Hierarchical Tucker (HT) tensor decomposition -- has been proven to have exponentially higher expressive power than shallow networks. I.e. a shallow network of exponential width is required to realize the same score function as computed by the deep architecture. In this paper, we prove the…
Recurrent neural networks (RNNs) such as Long Short Term Memory (LSTM) networks have become popular in a variety of applications such as image processing, data classification, speech recognition, and as controllers in autonomous systems. In practical settings, there is often a need to deploy such RNNs on resource-constrained platforms such as mobile phones or embedded devices. As the memory footprint and energy consumption of such components become a bottleneck, there is interest in compressing and optimizing such networks using a range of heuristic techniques. However, these techniques do not…
University of Illinois Urbana Champaign（伊利诺伊大学厄巴纳-香槟分校）；State University of New York at Buffalo（纽约州立大学布法罗分校）
Recent advances in deep learning motivate the use of deep neutral networks in sensing applications, but their excessive resource needs on constrained embedded devices remain an important impediment. A recently explored solution space lies in compressing (approximating or simplifying) deep neural networks in some manner before use on the device. We propose a new compression solution, called DeepIoT, that makes two key contributions in that space. First, unlike current solutions geared for compressing specific types of neural networks, DeepIoT presents a unified approach that compresses all comm…
National Research University Higher School of Economics（国立研究型大学高等经济学院）；Samsung AI Center（三星人工智能中心）
In natural language processing, a lot of the tasks are successfully solved with recurrent neural networks, but such models have a huge number of parameters. The majority of these parameters are often concentrated in the embedding layer, which size grows proportionally to the vocabulary length. We propose a Bayesian sparsification technique for RNNs which allows compressing the RNN dozens or hundreds of times without time-consuming hyperparameters tuning. We also generalize the model for vocabulary sparsification to filter out unnecessary words and compress the RNN even further. We show that th…
Baidu Silicon Valley Artificial Intelligence Lab（百度硅谷人工智能实验室）
We propose and evaluate new techniques for compressing and speeding up dense matrix multiplications as found in the fully connected and recurrent layers of neural networks for embedded large vocabulary continuous speech recognition (LVCSR). For compression, we introduce and study a trace norm regularization technique for training low rank factored versions of matrix multiplications. Compared to standard low rank training, we show that our method leads to good accuracy versus number of parameter trade-offs and can be used to speed up training of large models. For speedup, we enable faster infer…
Toshiba Corporation（东芝公司）；The University of Tokyo（东京大学）；RIKEN Center for Advanced Intelligence Project（理化学研究所先进智能项目中心）
Compressing DNNs is important for the real-world applications operating on resource-constrained devices. However, we typically observe drastic performance deterioration when changing model size after training is completed. Therefore, retraining is required to resume the performance of the compressed models suitable for different devices. In this paper, we propose Decomposable-Net (the network decomposable in any size), which allows flexible changes to model size without retraining. We decompose weight matrices in the DNNs via singular value decomposition and adjust ranks according to the targe…
Accelerating Neural ODEs Using Model Order Reduction
Tampere University（坦佩雷大学）；Faculty of Medicine and Health Technology, Tampere University（坦佩雷大学医学与健康技术学院）；Faculty of Information Technology and Communication Sciences, Tampere University（坦佩雷大学信息技术与传播科学学院）
Recent achievements in end-to-end deep learning have encouraged the exploration of tasks dealing with highly structured data with unified deep network models. Having such models for compressing audio signals has been challenging since it requires discrete representations that are not easy to train with end-to-end backpropagation. In this paper, we present an end-to-end deep learning approach that combines recurrent neural networks (RNNs) within the training strategy of variational autoencoders (VAEs) with a binary representation of the latent space. We apply a reparametrization trick for the B…
Tensor network compressibility of convolutional models
Multiverse Computing（多元宇宙计算公司）；Donostia International Physics Center（多诺斯蒂亚国际物理中心）；Institute for Advanced Studies in Basic Sciences (IASBS)（基础科学高级研究所）；Ikerbasque Foundation for Science（伊克尔巴斯克科学基金会）
