T-Basis: a Compact Representation for Neural Networks

We introduce T-Basis, a novel concept for a compact representation of a set of tensors, each of an arbitrary shape, which is often seen in Neural Networks. Each of the tensors in the set is modeled using Tensor Rings, though the concept applies to other Tensor Networks. Owing its name to the T-shape of nodes in diagram notation of Tensor Rings, T-Basis is simply a list of equally shaped three-dimensional tensors, used to represent Tensor Ring nodes. Such representation allows us to parameterize the tensor set with a small number of parameters (coefficients of the T-Basis tensors), scaling logarithmically with each tensor's size in the set and linearly with the dimensionality of T-Basis. We evaluate the proposed approach on the task of neural network compression and demonstrate that it reaches high compression rates at acceptable performance drops. Finally, we analyze memory and operation requirements of the compressed networks and conclude that T-Basis networks are equally well suited for training and inference in resource-constrained environments and usage on the edge devices.

[1]  Bo Peng,et al.  Extreme Network Compression via Filter Group Approximation , 2018, ECCV.

[2]  Mathieu Salzmann,et al.  Learning the Number of Neurons in Deep Networks , 2016, NIPS.

[3]  Konstantinos Kamnitsas,et al.  Efficient multi‐scale 3D CNN with fully connected CRF for accurate brain lesion segmentation , 2016, Medical Image Anal..

[4]  Bobby Bhattacharjee,et al.  Tensorial Neural Networks: Generalization of Neural Networks and Application to Model Compression , 2018, 1805.10352.

[5]  V. Aggarwal,et al.  Efficient Low Rank Tensor Ring Completion , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[6]  B. Khoromskij O(dlog N)-Quantics Approximation of N-d Tensors in High-Dimensional Numerical Modeling , 2011 .

[7]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[8]  Alexander Novikov,et al.  Tensorizing Neural Networks , 2015, NIPS.

[9]  Bo Chen,et al.  Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[10]  Reinhold Schneider,et al.  Optimization problems in contracted tensor networks , 2011, Comput. Vis. Sci..

[11]  Deng Cai,et al.  COP: Customized Deep Model Compression via Regularized Correlation-Based Filter-Level Pruning , 2019, IJCAI.

[12]  Alexander Novikov,et al.  Ultimate tensorization: compressing convolutional and FC layers alike , 2016, ArXiv.

[13]  Ross B. Girshick,et al.  Mask R-CNN , 2017, 1703.06870.

[14]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[15]  Michael Carbin,et al.  The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks , 2018, ICLR.

[16]  Ali Farhadi,et al.  XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks , 2016, ECCV.

[17]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[18]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[20]  Qinru Qiu,et al.  CircConv: A Structured Convolution with Low Complexity , 2019, AAAI.

[21]  George Papandreou,et al.  Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation , 2018, ECCV.

[22]  Yiran Chen,et al.  Learning Structured Sparsity in Deep Neural Networks , 2016, NIPS.

[23]  Jian Sun,et al.  Accelerating Very Deep Convolutional Networks for Classification and Detection , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Shuchang Zhou,et al.  DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients , 2016, ArXiv.

[25]  Hao Zhou,et al.  Less Is More: Towards Compact CNNs , 2016, ECCV.

[26]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[27]  Kaiming He,et al.  Rethinking ImageNet Pre-Training , 2018, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[28]  Román Orús,et al.  Tensor networks for complex quantum systems , 2018, Nature Reviews Physics.

[29]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[30]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[31]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[32]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[33]  Philip Heng Wai Leong,et al.  SYQ: Learning Symmetric Quantization for Efficient Deep Neural Networks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[34]  Bo Chen,et al.  NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications , 2018, ECCV.

[35]  Anshumali Shrivastava,et al.  Scalable and Sustainable Deep Learning via Randomized Hashing , 2016, KDD.

[36]  知秀 柴田 5分で分かる!? 有名論文ナナメ読み:Jacob Devlin et al. : BERT : Pre-training of Deep Bidirectional Transformers for Language Understanding , 2020 .

[37]  Zhiqiang Shen,et al.  Learning Efficient Convolutional Networks through Network Slimming , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[38]  Daniel Kressner,et al.  A literature survey of low‐rank tensor approximation techniques , 2013, 1302.7121.

[39]  Ji Liu,et al.  Global Sparse Momentum SGD for Pruning Very Deep Neural Networks , 2019, NeurIPS.

[40]  Song Han,et al.  Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding , 2015, ICLR.

[41]  Jian Cheng,et al.  Quantized Convolutional Neural Networks for Mobile Devices , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[42]  Ran El-Yaniv,et al.  Binarized Neural Networks , 2016, NIPS.

[43]  Frank Verstraete,et al.  Matrix product state representations , 2006, Quantum Inf. Comput..

[44]  Larry S. Davis,et al.  NISP: Pruning Networks Using Neuron Importance Score Propagation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[45]  Elad Eban,et al.  MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[46]  Misha Denil,et al.  Predicting Parameters in Deep Learning , 2014 .

[47]  Song Han,et al.  Trained Ternary Quantization , 2016, ICLR.

[48]  Liqing Zhang,et al.  Tensor Ring Decomposition , 2016, ArXiv.

[49]  Simon Haykin,et al.  GradientBased Learning Applied to Document Recognition , 2001 .

[50]  Alexander M. Rush,et al.  Weightless: Lossy Weight Encoding For Deep Neural Network Compression , 2018, ICML.

[51]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[52]  Joan Bruna,et al.  Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation , 2014, NIPS.

[53]  F. L. Hitchcock The Expression of a Tensor or a Polyadic as a Sum of Products , 1927 .

[54]  Yixin Chen,et al.  Compressing Neural Networks with the Hashing Trick , 2015, ICML.

[55]  Luc Van Gool,et al.  Learning Filter Basis for Convolutional Neural Network Compression , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[56]  Song Han,et al.  Learning both Weights and Connections for Efficient Neural Network , 2015, NIPS.

[57]  Hanan Samet,et al.  Pruning Filters for Efficient ConvNets , 2016, ICLR.

[58]  Ivan Oseledets,et al.  Tensor-Train Decomposition , 2011, SIAM J. Sci. Comput..

[59]  Markus Nagel,et al.  Data-Free Quantization Through Weight Equalization and Bias Correction , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[60]  Xiangyu Zhang,et al.  Channel Pruning for Accelerating Very Deep Neural Networks , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[61]  Baoyuan Wu,et al.  Compressing Convolutional Neural Networks via Factorized Convolutional Filters , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[62]  Subhransu Maji,et al.  Semantic contours from inverse detectors , 2011, 2011 International Conference on Computer Vision.

[63]  Luca Zappella,et al.  Filter Distillation for Network Compression , 2020, 2020 IEEE Winter Conference on Applications of Computer Vision (WACV).

[64]  Andrew Zisserman,et al.  Speeding up Convolutional Neural Networks with Low Rank Expansions , 2014, BMVC.

[65]  Mingjie Sun,et al.  Rethinking the Value of Network Pruning , 2018, ICLR.

[66]  Eunhyeok Park,et al.  Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications , 2015, ICLR.

[67]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[68]  Ivan V. Oseledets,et al.  Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition , 2014, ICLR.

[69]  Rich Caruana,et al.  Do Deep Nets Really Need to be Deep? , 2013, NIPS.

[70]  Nikos Komodakis,et al.  Wide Residual Networks , 2016, BMVC.

[71]  Tamara G. Kolda,et al.  Tensor Decompositions and Applications , 2009, SIAM Rev..

[72]  Yoshua Bengio,et al.  BinaryConnect: Training Deep Neural Networks with binary weights during propagations , 2015, NIPS.

[73]  Elad Eban,et al.  Structured Multi-Hashing for Model Compression , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[74]  Yifan Sun,et al.  Wide Compression: Tensor Ring Nets , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.