A Lite Distributed Semantic Communication System for Internet of Things

The rapid development of deep learning (DL) and widespread applications of Internet-of-Things (IoT) have made the devices smarter than before, and enabled them to perform more intelligent tasks. However, it is challenging for any IoT device to train and run DL models independently due to its limited computing capability. In this paper, we consider an IoT network where the cloud/edge platform performs the DL based semantic communication (DeepSC) model training and updating while IoT devices perform data collection and transmission based on the trained model. To make it affordable for IoT devices, we propose a lite distributed semantic communication system based on DL, named L-DeepSC, for text transmission with low complexity, where the data transmission from the IoT devices to the cloud/edge works at the semantic level to improve transmission efficiency. Particularly, by pruning the model redundancy and lowering the weight resolution, the L-DeepSC becomes affordable for IoT devices and the bandwidth required for model weight transmission between IoT devices and the cloud/edge is reduced significantly. Through analyzing the effects of fading channels in forward-propagation and back-propagation during the training of L-DeepSC, we develop a channel state information (CSI) aided training processing to decrease the effects of fading channels on transmission. Meanwhile, we tailor the semantic constellation to make it implementable on capacity-limited IoT devices. Simulation demonstrates that the proposed L-DeepSC achieves competitive performance compared with traditional methods, especially in the low signal-to-noise (SNR) region. In particular, while it can reach as large as $40\times $ compression ratio without performance degradation.

[1]  F. Moore,et al.  Polynomial Codes Over Certain Finite Fields , 2017 .

[2]  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.

[3]  Jeffrey G. Andrews,et al.  Massive MIMO Channel Estimation With an Untrained Deep Neural Network , 2019, IEEE Transactions on Wireless Communications.

[4]  Lida Xu,et al.  The internet of things: a survey , 2014, Information Systems Frontiers.

[5]  Philipp Koehn,et al.  Europarl: A Parallel Corpus for Statistical Machine Translation , 2005, MTSUMMIT.

[6]  Masoud Nikravesh,et al.  Feature Extraction - Foundations and Applications , 2006, Feature Extraction.

[7]  Jian Song,et al.  Joint Transceiver Optimization for Wireless Communication PHY Using Neural Network , 2019, IEEE Journal on Selected Areas in Communications.

[8]  Geoffrey Ye Li,et al.  Deep Learning Enabled Semantic Communication Systems , 2020, IEEE Transactions on Signal Processing.

[9]  David Tse,et al.  Fundamentals of Wireless Communication , 2005 .

[10]  Viktor K. Prasanna,et al.  Sparse Matrix-Vector multiplication on FPGAs , 2005, FPGA '05.

[11]  Raghuraman Krishnamoorthi,et al.  Quantizing deep convolutional networks for efficient inference: A whitepaper , 2018, ArXiv.

[12]  Lin Xu,et al.  Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights , 2017, ICLR.

[13]  Geoffrey Ye Li,et al.  Compression and Acceleration of Neural Networks for Communications , 2019, IEEE Wireless Communications.

[14]  Rudolf Carnap,et al.  An outline of a theory of semantic information , 1952 .

[15]  Nitin Indurkhya,et al.  Handbook of Natural Language Processing , 2010 .

[16]  Bin Liu,et al.  Ternary Weight Networks , 2016, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[17]  Mianxiong Dong,et al.  Learning IoT in Edge: Deep Learning for the Internet of Things with Edge Computing , 2018, IEEE Network.

[18]  Mohsen Guizani,et al.  Deep Learning for IoT Big Data and Streaming Analytics: A Survey , 2017, IEEE Communications Surveys & Tutorials.

[19]  Yoshua Bengio,et al.  Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation , 2013, ArXiv.

[20]  Deniz Gündüz,et al.  Deep Joint Transmission-Recognition for Power-Constrained IoT Devices , 2020, ArXiv.

[21]  Biing-Hwang Juang,et al.  Deep Learning in Physical Layer Communications , 2018, IEEE Wireless Communications.

[22]  Andrea J. Goldsmith,et al.  Deep Learning for Joint Source-Channel Coding of Text , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[23]  Jakob Hoydis,et al.  An Introduction to Deep Learning for the Physical Layer , 2017, IEEE Transactions on Cognitive Communications and Networking.

[24]  Keqiu Li,et al.  How Can Heterogeneous Internet of Things Build Our Future: A Survey , 2018, IEEE Communications Surveys & Tutorials.

[25]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

[26]  Stephan ten Brink,et al.  Deep Learning Based Communication Over the Air , 2017, IEEE Journal of Selected Topics in Signal Processing.

[27]  Yu-Chieh Chang,et al.  Deep Learning-Constructed Joint Transmission-Recognition for Internet of Things , 2019, IEEE Access.

[28]  Salim Roukos,et al.  Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.

[29]  Deniz Gündüz,et al.  Deep Joint Source-Channel Coding for Wireless Image Transmission , 2019, IEEE Transactions on Cognitive Communications and Networking.

[30]  David Gil,et al.  Internet of Things: A Review of Surveys Based on Context Aware Intelligent Services , 2016, Sensors.

[31]  Wangmeng Zuo,et al.  Attention-guided CNN for image denoising , 2020, Neural Networks.

[32]  Lei Zhang,et al.  Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising , 2016, IEEE Transactions on Image Processing.

[33]  Budhaditya Bhattacharyya,et al.  Deep Learning and Channel Estimation , 2020, 2020 6th International Conference on Advanced Computing and Communication Systems (ICACCS).

[34]  Ming Yang,et al.  Compressing Deep Convolutional Networks using Vector Quantization , 2014, ArXiv.

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

[36]  Jakob Hoydis,et al.  Model-Free Training of End-to-End Communication Systems , 2018, IEEE Journal on Selected Areas in Communications.

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

[38]  Biing-Hwang Juang,et al.  Deep Learning-Based End-to-End Wireless Communication Systems With Conditional GANs as Unknown Channels , 2019, IEEE Transactions on Wireless Communications.

[39]  Richard Szeliski,et al.  Computer Vision - Algorithms and Applications , 2011, Texts in Computer Science.

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

[41]  Deniz Gündüz,et al.  Deep Joint Source-channel Coding for Wireless Image Transmission , 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[42]  Dejan Markovic,et al.  A scalable sparse matrix-vector multiplication kernel for energy-efficient sparse-blas on FPGAs , 2014, FPGA.

[43]  Deniz Gündüz,et al.  Joint Device-Edge Inference over Wireless Links with Pruning , 2020, 2020 IEEE 21st International Workshop on Signal Processing Advances in Wireless Communications (SPAWC).

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