面向带宽受限场景的高效语义通信方法

doi:10.19665/j.issn1001-2400.20240203

摘要/Abstract

摘要：

语义通信为通信系统优化和性能提升提供了新的研究角度,然而,目前语义通信的研究忽略了通信开销的影响,未考虑语义通信性能和通信开销的关系,导致带宽资源受限时语义通信性能难以提升。为此,针对带宽受限场景,提出一种基于信息瓶颈的语义通信方法。首先,该方法采用Transformer模型进行语义和信道联合编解码,并设计特征选择模块以识别和删除冗余语义信息,构建了端到端语义通信模型;进而考虑语义通信性能与通信开销之间的折衷关系,基于信息瓶颈理论设计损失函数,在保证语义通信性能的同时,降低通信开销,完成语义通信模型的训练和优化。实验结果显示,在欧洲议会平行语料库上,与基线模型相比,所提方法在保证通信性能的同时可降低约20%~30%的通信开销,在相同带宽条件下该方法的BLEU分数可提升约5%。实验结果表明,所提方法可以有效降低语义通信开销,从而提升带宽资源受限场景下的语义通信性能。

关键词: 语义通信, 通信系统, 深度学习, Transformer, 特征选择模块, 信息瓶颈理论

Abstract:

Semantic communication provides a new research perspective for communication system optimization and performance improvement.However,current research on semantic communication ignores the impact of communication overhead and does not consider the relationship between semantic communication performance and communication overhead,resulting in difficulty in improving semantic communication performance when the bandwidth resource is limited.Therefore,an information bottleneck based semantic communication method for text sources is proposed.First,the Transformer model is used for semantic and channel joint encoding and decoding,and a feature selection module is designed to identify and delete redundant information,and then an end-to-end semantic communication model is constructed in the method;Second,considering the tradeoff between semantic communication performance and communication cost,a loss function is designed based on the information bottleneck theory to ensure the semantic communication performance,reduce the communication cost,and complete the training and optimization of the semantic communication model.Experimental results show that on the proceedings of the European Parliament,compared with the baseline model,the proposed method can reduce communication overhead by 20%~30% while ensuring communication performance.Under the same bandwidth conditions,the BLEU score of this method can be increased by 5%.Experimental results prove that the proposed method can effectively reduce the semantic communication overhead,thereby improving semantic communication performance when the bandwidth resource is limited.

Key words: semantic communication, communication systems, deep learning, transformer, feature selection module, information bottleneck theory

中图分类号:

TN911.22

刘伟, 王孟洋, 白宝明. 面向带宽受限场景的高效语义通信方法[J]. 西安电子科技大学学报, 2024, 51(3): 9-18.

LIU Wei, WANG Mengyang, BAI Baoming. Efficient semantic communication method for bandwidth constrained scenarios[J]. Journal of Xidian University, 2024, 51(3): 9-18.

图/表 7

图1

图2

图3

图4

图5

图6

图7

参考文献 25

[1]	STRINATI E C, BARBAROSSA S. 6G Networks:Beyond Shannon Towards Semantic and Goal-Oriented Communications[J]. Computer Networks, 2021, 190:107930-107947.
[2]	张平, 牛凯, 田辉, 等. 6G移动通信技术展望[J]. 通信学报, 2019, 40(1):141-148. doi: 10.11959/j.issn.1000-436x.2019022
	ZHANG Ping, NIU Kai, TIAN Hui, et al. Technology Prospect of 6G Mobile Communications[J]. Journal on Communications, 2019, 40(1):141-148. doi: 10.11959/j.issn.1000-436x.2019022
[3]	牛凯, 戴金晟, 张平, 等. 面向6G的语义通信[J]. 移动通信, 2021, 45(4):85-90.
	NIU Kai, DAI Jincheng, ZHANG Ping, et al. 6G-Oriented Semantic Communications[J]. Mobile Communications, 2021, 45(4):85-90.
[4]	石光明, 肖泳, 高大化. 面向万物智联的语义通信网络[J]. 物联网学报, 2021, 5(2):26-36. doi: 10.11959/j.issn.2096-3750.2021.00209
	SHI Guangming, XIAO Yong, GAO Dahua. SemanticCommunication Networking for the Intelligence of Everything[J]. Chinese Journal on Internet of Things, 2021, 5(2):26-36.
[5]	WEAVER W. Recent Contributions to the Mathematical Theory of Communication[J]. ETC:A Review of General Semantics, 1953, 1:261-281.
[6]	ZHANG P, XU W, GAO H, et al. Toward Wisdom-Evolutionary and Primitive-Concise 6G:A New Paradigm of Semantic Communication Networks[J]. Engineering, 2022, 8:60-73.
[7]	徐文伟, 张弓, 白铂, 等. 后香农时代ICT领域的十大挑战问题[J]. 中国科学:数学, 2021, 51(7):1095-1138.
	XU Wenwei, ZHANG Gong, BAI Bo, et al. Ten Key ICT Challenges in the Post-Shannon Era[J]. Scientia Sinica Mathematica, 2021, 51(7):1095-1138.
[8]	BOURTSOULATZE E, KURKA D B, GÜNDÜZ D. Deep Joint Source-Channel Coding for Wireless Image Transmission[J]. IEEE Transactions on Cognitive Communications and Networking, 2019, 5(3):567-579.
[9]	刘传宏, 郭彩丽, 杨洋, 等. 人工智能物联网中面向智能任务的语义通信方法[J]. 通信学报, 2021, 42(11):97-108. doi: 10.11959/j.issn.1000-436x.2021214
	LIU Chuanhong, GUO Caili, YANG Yang, et al, Intelligent Task-Oriented Semantic Communication Method in Artificial Intelligence of Things[J]. Journal on Communications, 2021, 42(11):97-108. doi: 10.11959/j.issn.1000-436x.2021214
[10]	XU J, AI B, CHEN W, et al. Wireless Image Transmission Using Deep Source Channel Coding with Attention Modules[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2021, 32(4):2315-2328.
[11]	FARSAD N, RAO M, GOLDSMITH A. Deep Learning for Joint Source-Channel Coding of Text[C]//2018 IEEE International Conference on Acoustics,Speech and Signal Processing.Piscataway:IEEE, 2018:2326-2330.
[12]	XIE H, QIN Z, LI G Y, et al. Deep Learning Enabled Semantic Communication Systems[J]. IEEE Transactions on Signal Processing, 2021, 69:2663-2675.
[13]	XIE H, QIN Z. A Lite Distributed Semantic Communication System for Internet of Things[J]. IEEE Journal on Selected Areas in Communications, 2020, 39(1):142-153.
[14]	ZHOU Q, LI R, ZHAO Z, et al. Semantic Communication with Adaptive Universal Transformer[J]. IEEE Wireless Communications Letters, 2021, 11(3):453-457.
[15]	ZHOU F, LI Y, ZHANG X, et al. Cognitive Semantic Communication Systems Driven by Knowledge Graph[C]//ICC 2022 IEEE International Conference on Communications.Piscataway:IEEE, 2022:4860-4865.
[16]	WENG Z, QIN Z. Semantic Communication Systems for Speech Transmission[J]. IEEE Journal on Selected Areas in Communications, 2021, 39(8):2434-2444.
[17]	TISHBY N, PEREIRA F, BIALEK W. The Information Bottleneck Method[C]//Proceedings.of the 37th Allerton Conference on Communication and Computation.Piscataway:IEEE, 1999:368-377.
[18]	SHAO J, MAO Y, ZHANG J. Learning Task-Oriented Communication for Edge Inference:An Information Bottleneck Approach[J]. IEEE Journal on Selected Areas in Communications, 2021, 40(1):197-211.
[19]	SHAO J, ZHANG J. Bottlenet++:An End-To-End Approach for Feature Compression in Device-Edge Co-Inference Systems[C]//2020 IEEE International Conference on Communications Workshops.Piscataway:IEEE, 2020:1-6.
[20]	胡继文, 童胜, 白宝明, 等. 低复杂度LDPC码信息瓶颈量化译码器设计[J]. 西安电子科技大学学报, 2022, 49(5):76-83.
	HU Jiwen, TONG Sheng, BAI Baoming, et al. Design of a Low Complexity Information Bottleneck Quantization Decoder for LDPC Codes[J]. Journal of Xidian University, 2022, 49(5):76-83.
[21]	李源, 王伟. 一种基于字词双通道网络的文本情感分析方法[J]. 西安电子科技大学学报, 2021, 48(6):179-186.
	LI Yuan, WANG Wei. Method for the Analysis of Text Sentiment Based on the Word Dual-Channel Network[J]. Journal of Xidian University, 2021, 48(6):179-186.
[22]	王侃, 王孟洋, 刘鑫, 等. 融合自注意力机制与CNN-BiGRU的事件检测[J]. 西安电子科技大学学报, 2022, 49(5):181-188.
	WANG Kan, WANG Mengyang, LIU Xin, et al. Event Detection by Combining Self-Attention and CNN-BiGRU[J]. Journal of Xidian University, 2022, 49(5):181-188.
[23]	VASWANI A, SHAZEER N, PARMAR N, et al. AttentionIs All You Need[J]. Advances In Neural Information Processing Systems, 2017, 30:1-11.
[24]	LUO X, CHEN H, GUO Q. Semantic Communications:Overview,Open Issues,and Future Research Directions[J]. IEEE Wireless Communications, 2022, 29(1):210-219.
[25]	WANG Z, SCOTT D W. Nonparametric Density Estimation for High Dimensional Data:Algorithms and Applications[J]. Wiley Interdisciplinary Reviews:Computational Statistics, 2019, 11(4):1461-1502.