Papers
Topics
Authors
Recent
Search
2000 character limit reached

Digital-SC: Digital Semantic Communication with Adaptive Network Split and Learned Non-Linear Quantization

Published 22 May 2023 in eess.SP | (2305.13553v2)

Abstract: Semantic communication, an intelligent communication paradigm that aims to transmit useful information in the semantic domain, is facilitated by deep learning techniques. Robust semantic features can be learned and transmitted in an analog fashion, but it poses new challenges to hardware, protocol, and encryption. In this paper, we propose a digital semantic communication system, which consists of an encoding network deployed on a resource-limited device and a decoding network deployed at the edge. To acquire better semantic representation for digital transmission, a novel non-linear quantization module is proposed to efficiently quantize semantic features with trainable quantization levels. Additionally, structured pruning is incorporated to reduce the dimension of the transmitted features. We also introduce a semantic learning loss (SLL) function to reduce semantic error. To adapt to various channel conditions and inputs under constraints of communication and computing resources, a policy network is designed to adaptively choose the split point and the dimension of the transmitted semantic features. Experiments using the CIFAR-10 and ImageNet dataset for image classification are employed to evaluate the proposed digital semantic communication network, and ablation studies are conducted to assess the proposed quantization module, structured pruning and SLL.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (40)
  1. J. Xu, T.-Y. Tung, B. Ai, W. Chen, Y. Sun, and D. Gündüz, “Deep joint source-channel coding for semantic communications,” IEEE Communications Magazine, vol. 61, no. 11, pp. 42–48, 2023.
  2. G. Shi, Y. Li, and X. Xie, “Semantic communications: Outcome of the intelligence era,” Moshi Shibie yu Rengong Zhineng/Pattern Recognition and Artificial Intelligence, 2018.
  3. D. Gündüz, Z. Qin, I. E. Aguerri, H. S. Dhillon, Z. Yang, A. Yener, K. K. Wong, and C.-B. Chae, “Beyond transmitting bits: Context, semantics, and task-oriented communications,” IEEE Journal on Selected Areas in Communications, vol. 41, no. 1, pp. 5–41, 2023.
  4. J. Dai, P. Zhang, K. Niu, S. Wang, Z. Si, and X. Qin, “Communication beyond transmitting bits: Semantics-guided source and channel coding,” IEEE Wireless Communications, vol. 30, no. 4, pp. 170–177, 2023.
  5. Y. Zhang, W. Xu, H. Gao, and F. Wang, “Multi-user semantic communications for cooperative object identification,” in 2022 IEEE International Conference on Communications Workshops (ICC Workshops), 2022, pp. 157–162.
  6. H. Xie, Z. Qin, and G. Y. Li, “Task-oriented multi-user semantic communications for vqa,” IEEE Wireless Communications Letters, vol. 11, no. 3, pp. 553–557, 2022.
  7. H. Xie, Z. Qin, X. Tao, and K. B. Letaief, “Task-oriented multi-user semantic communications,” IEEE Journal on Selected Areas in Communications, vol. 40, no. 9, pp. 2584–2597, 2022.
  8. X. Kang, B. Song, J. Guo, Z. Qin, and F. R. Yu, “Task-oriented image transmission for scene classification in unmanned aerial systems,” IEEE Transactions on Communications, vol. 70, no. 8, pp. 5181–5192, 2022.
  9. K. Lu, Q. Zhou, R. Li, Z. Zhao, X. Chen, J. Wu, and H. Zhang, “Rethinking modern communication from semantic coding to semantic communication,” IEEE Wireless Communications, vol. 30, no. 1, pp. 158–164, 2023.
  10. M. Jankowski, D. Gündüz, and K. Mikolajczyk, “Wireless image retrieval at the edge,” IEEE Journal on Selected Areas in Communications, vol. 39, no. 1, pp. 89–100, 2021.
  11. J. Shao and J. Zhang, “Bottlenet++: An end-to-end approach for feature compression in device-edge co-inference systems,” in IEEE International Conference on Communications Workshops (ICC Workshops), 2020, pp. 1–6.
  12. W. Shi, Y. Hou, S. Zhou, Z. Niu, Y. Zhang, and L. Geng, “Improving device-edge cooperative inference of deep learning via 2-step pruning,” in IEEE INFOCOM 2019 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), 2019, pp. 1–6.
  13. H. Xie, Z. Qin, G. Y. Li, and B. H. Juang, “Deep learning enabled semantic communication systems,” IEEE Transactions on Signal Processing, vol. 69, pp. 2663–2675, 2021.
  14. B. Tang, Q. Li, L. Huang, and Y. Yin, “Text semantic communication systems with sentence-level semantic fidelity,” in 2023 IEEE Wireless Communications and Networking Conference (WCNC), 2023, pp. 1–6.
  15. Z. Weng and Z. Qin, “Semantic communication systems for speech transmission,” IEEE Journal on Selected Areas in Communications, vol. 39, no. 8, pp. 2434–2444, 2021.
  16. T. Han, Q. Yang, Z. Shi, S. He, and Z. Zhang, “Semantic-preserved communication system for highly efficient speech transmission,” IEEE Journal on Selected Areas in Communications, vol. 41, no. 1, pp. 245–259, 2023.
  17. J. Xu, B. Ai, W. Chen, A. Yang, P. Sun, and M. Rodrigues, “Wireless image transmission using deep source channel coding with attention modules,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 32, no. 4, pp. 2315–2328, 2022.
  18. H. Li, C. Hu, J. Jiang, W. Zhi, and W. Zhu, “Jalad: Joint accuracy-and latency-aware deep structure decoupling for edge-cloud execution,” in IEEE 24th International Conference on Parallel and Distributed Systems (ICPADS), 2018, pp. 671–678.
  19. A. E. Eshratifar, A. Esmaili, and M. Pedram, “Bottlenet: A deep learning architecture for intelligent mobile cloud computing services,” in IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED), 2019, pp. 1–6.
  20. S. Zhou, Y. Wu, Z. Ni, X. Zhou, H. Wen, and Y. Zou, “Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients,” https://arxiv.org/abs/1606.06160, 2016.
  21. H. Xie and Z. Qin, “A lite distributed semantic communication system for internet of things,” IEEE Journal on Selected Areas in Communications, vol. 39, no. 1, pp. 142–153, 2021.
  22. Q. Zhou, R. Li, Z. Zhao, Y. Xiao, and H. Zhang, “Adaptive bit rate control in semantic communication with incremental knowledge-based harq,” IEEE Open Journal of the Communications Society, vol. 3, pp. 1076–1089, 2022.
  23. J. Fang, A. Shafiee, H. Abdel-Aziz, D. Thorsley, G. Georgiadis, and J. Hassoun, “Post-training piecewise linear quantization for deep neural networks,” in European Conference on Computer Vision (ECCV), 2020.
  24. E. Park, S. Yoo, and P. Vajda, “Value-aware quantization for training and inference ofneural networks.” in European Conference on Computer Vision (ECCV), 2018.
  25. S. Jain, S. Venkataramani, V. Srinivasan, J. Choi, K. Gopalakrishnan, and L. Chang, “Biscaled-dnn: Quantizing long-tailed datastructures with two scale factors for deep neural networks,” in ACM/IEEE Design Automation Conference (DAC), 2019, pp. 1–6.
  26. Y. Sun, W. Shi, X. Huang, S. Zhou, and Z. Niu, “Edge learning with timeliness constraints: Challenges and solutions,” IEEE Communications Magazine, vol. 58, no. 12, pp. 27–33, 2020.
  27. J. Ballé, V. Laparra, and E. P. Simoncelli, “Density modeling of images using a generalized normalization transformation,” in The International Conference on Learning Representations (ICLR), 2016.
  28. M. Jankowski, D. Gunduz, and K. Mikolajczyk, “Joint device-edge inference over wireless links with pruning,” in IEEE 21st International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), 2020, pp. 1–5.
  29. K. He, X. Zhang, S. Ren, and J. Sun, “Identity mappings in deep residual networks.” in European Conference on Computer Vision (ECCV), 2016.
  30. Z. Liu, Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, S. Lin, and B. Guo, “Swin transformer: Hierarchical vision transformer using shifted windows,” in IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 9992–10 002.
  31. T.-Y. Tung, D. B. Kurka, M. Jankowski, and D. Gündüz, “Deepjscc-q: Constellation constrained deep joint source-channel coding,” IEEE Journal on Selected Areas in Information Theory, vol. 3, no. 4, pp. 720–731, 2022.
  32. L. Guo, W. Chen, Y. Sun, and B. Ai, “Device-edge digital semantic communication with trained non-linear quantization,” in 2023 IEEE 97th Vehicular Technology Conference (VTC2023-Spring), 2023, pp. 1–5.
  33. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770–778.
  34. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, “Attention is all you need,” in Neural Information Processing Systems (NIPS), 2017.
  35. J. Yang, X. Shen, J. Xing, X. Tian, H. Li, B. Deng, J. Huang, and X. S. Hua, “Quantization networks,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 7300–7308.
  36. H. Song, H. Mao, and W. J. Dally, “Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding,” in The International Conference on Learning Representations (ICLR), 2016.
  37. G. Hinton, O. Vinyals, and J. Dean, “Distilling the knowledge in a neural network,” Computer Science, 2015.
  38. X. Liu, X. Wang, and S. Matwin, “Improving the interpretability of deep neural networks with knowledge distillation,” IEEE International Conference on Data Mining Workshops (ICDMW), pp. 905–912, 2018.
  39. A. Krizhevsky and I. Sutskever, “Convolutional deep belief networks on cifar-10,” https://www.cs.toronto.edu/ kriz/cifar.html, 2012.
  40. J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, “Imagenet: A large-scale hierarchical image database,” in 2009 IEEE Conference on Computer Vision and Pattern Recognition, 2009, pp. 248–255.
Citations (5)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Authors (4)

  1. Lei Guo 
  2. Wei Chen 
  3. Yuxuan Sun 
  4. Bo Ai 

Collections

Sign up for free to add this paper to one or more collections.

Sign Up