A Lite Distributed Semantic Communication System for Internet of Things
Open accessThe DOI matches its Crossref record; 45 of the 45 references it cites were found in a registry or an index.
Abstract
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“For instance, edge DL approach has been developed in [58] to deliver low-latency semantic tasks (e.g., text messages) by learning the communication strategies in an end-to-end fashion based on JSCC.”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [58]
Experimental — accuracy not yet measuredIn the citing paper
“Edge AI can also help design AI-native communication strategies for the physical layer (e.g., task-oriented semantic communication [58]) and medium access control layer (e.g., random access protocol [59]).”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [58]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
A Mathematical Theory of Communication
Shannon, C. E. (1948) · Bell System Technical Journal · doi:10.1002/j.1538-7305.1948.tb00917.x · Cited by 48,949
BLEU: a method for automatic evaluation of machine translation
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073135 · Cited by 21,344 · cited 1×
“The bilingual evaluation understudy (BLEU) score is used to measure the performance [36].”
MethodThe Internet of Things: A survey
Atzori, L., Iera, A., & Morabito, G. (2010) · Computer Networks · doi:10.1016/j.comnet.2010.05.010 · Cited by 15,613
Fundamentals of Wireless Communication
Tse, D., & Viswanath, P. (2005) · doi:10.1017/cbo9780511807213 · Cited by 13,162 · cited 1×
“To make a decision from the received information, there are usually three steps, i) the traditional communication receiver to recover the raw data [7], ii) the feature extractor to obtain and interpret the meanings of the raw data for the decision [8], and iii) the effects due to decisions…”
BackgroundBeyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
Zhang, K., Zuo, W., Chen, Y., Meng, D., & Zhang, L. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2662206 · Cited by 8,983 · cited 1×
“Then, we adopt the deep de-noise network to increase the resolution of LS estimator as in [31] shown in Fig.”
MethodQuantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
Jacob, B., Kligys, S., Chen, B., Zhu, M., Tang, M., Howard, A., Adam, H., & Kalenichenko, D. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00286 · Cited by 4,114
Computer vision: algorithms and applications
(2011) · Choice Reviews Online · doi:10.5860/choice.48-5140 · Cited by 3,911
Bleu: a method for automatic evaluation of machine translation
Papineni, K. (2024) · doi:10.57702/ljteqmrb · Cited by 3,672
Polynomial Codes Over Certain Finite Fields
Reed, I. S., & Solomon, G. (1960) · Journal of the Society for Industrial and Applied Mathematics · doi:10.1137/0108018 · Cited by 3,662 · cited 1×
“Turbo coding and Reed-Solomon (RS) coding [44] for channel coding, where turbo decoding method is log-MAP algorithm with 5 iterations, and quadrature amplitude modulation (QAM).”
Method(2005) · Cited by 3,125
Research works printed but not linked: 2
- goodfellow, 2016, Deep Learning
- 10.1017/cbo9780511807213 · DOI · Paper page
Cited by
On the Road to 6G: Visions, Requirements, Key Technologies, and Testbeds
Wang, C.-X., You, X., Gao, X., Zhu, X., Li, Z., Zhang, C., Wang, H., Huang, Y., Chen, Y., Haas, H., et al. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3249835 · Cited by 2,336
Deep Learning Enabled Semantic Communication Systems
Xie, H., Qin, Z., Li, G. Y., & Juang, B.-H. (2021) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2021.3071210 · Cited by 1,602
“Following the concept of semantic communications proposed in this paper, we have developed L-DeepSC [36] and DeepSCS [37] for text and speech transmission.”
MethodSelf-citationEdge artificial intelligence for 6g: vision, enabling technologies, and applications
Letaief, K. B., Shi, Y., Lu, J., & Lu, J. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3126076 · Cited by 829
“For instance, edge DL approach has been developed in [58] to deliver low-latency semantic tasks (e.g., text messages) by learning the communication strategies in an end-to-end fashion based on JSCC.”
BackgroundMethodInfluentialSemantic Communications: Overview, Open Issues, and Future Research Directions
Luo, X., Chen, H.-H., & Guo, Q. (2022) · IEEE Wireless Communications · doi:10.1109/mwc.101.2100269 · Cited by 690
Semantic Communications for Future Internet: Fundamentals, Applications, and Challenges
Yang, W., Du, H., Liew, Z. Q., Lim, W. Y. B., Xiong, Z., Niyato, D., Chi, X., Shen, X., & Miao, C. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2022.3223224 · Cited by 670
“system, named L-DeepSC [74], can be used.”
InfluentialSemantic Communication Systems for Speech Transmission
Weng, Z., & Qin, Z. (2021) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3087240 · Cited by 663
“Inspired by this, a lite distributed semantic communication system for text transmission, named L-DeepSC, has been proposed in [26] to address the challenge of IoT to perform the intelligent tasks by pruning parameters to reduce the size of the trained models as well as to reduce the communication cost between IoT dev…”
MethodSelf-citationXu, W., Yang, Z., Ng, D. W. K., Levorato, M., Eldar, Y. C., & Debbah, M. (2023) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2023.3239189 · Cited by 660
“In a distributed IoE network, a lightweight DL-based semantic communication system was proposed in [228] by training semantic feature extraction and”
Xu, M., Ng, W. C., Lim, W. Y. B., Kang, J., Xiong, Z., Niyato, D., Yang, Q., Shen, X., & Miao, C. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2022.3221119 · Cited by 564
“Therefore, in [144], the authors propose a lightweight semantic communication system for low-complexity text transmission in IoT.”
BackgroundTask-Oriented Multi-User Semantic Communications
Xie, H., Qin, Z., Tao, X., & Letaief, K. B. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2022.3191326 · Cited by 458
“Moreover, Xie et al. [11] also proposed an environment-friendly semantic communication system, named L-DeepSC, for the capacity-limited devices.”
BackgroundSelf-citationFederated Learning for 6G: Applications, Challenges, and Opportunities
Yang, Z., Chen, M., Wong, K.-K., Poor, H. V., & Cui, S. (2022) · Engineering · doi:10.1016/j.eng.2021.12.002 · Cited by 374
Wang, Y., Su, Z., Guo, S., Dai, M., Luan, T. H., & Liu, Y. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3263909 · Cited by 357
“Semantic communication [27], [28], as the breakthrough beyond the Shannon paradigm, provides a promising solution by offering ultralow latency semantic transmissions for both intra-twin and inter-twin communications, where only the meaningful data essential for the task are transmitted.”
BackgroundMethodToward Semantic Communications: Deep Learning-Based Image Semantic Coding
Huang, D., Gao, F., Tao, X., Du, Q., & Lu, J. (2023) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2022.3221999 · Cited by 331
“Recent works mainly focus on semantic communications for text/speech modalities [2], [3], [4], [5], and therefore can be categorize as text semantic communications(TSC).”
BackgroundZhang, P., Xu, W., Gao, H., Niu, K., Xu, X., Qin, X., Yuan, C., Qin, Z., Zhao, H., Wei, J., et al. (2022) · Engineering · doi:10.1016/j.eng.2021.11.003 · Cited by 311
Self-citationWang, Y., Gui, G., Gacanin, H., Ohtsuki, T., Dobre, O. A., & Poor, H. V. (2021) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3087243 · Cited by 304
“A lightweight semantic communication system is designed by weight-sum-based neuron pruning and quantization in [44].”
MethodWhat is Semantic Communication? A View on Conveying Meaning in the Era of Machine Intelligence
Lan, Q., Wen, D., Zhang, Z., Zeng, Q., Chen, X., Popovski, P., & Huang, K. (2021) · Journal of Communications and Information Networks · doi:10.23919/jcin.2021.9663101 · Cited by 255
Wireless Semantic Communications for Video Conferencing
Jiang, P., Wen, C.-K., Jin, S., & Li, G. Y. (2023) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2022.3221968 · Cited by 255
“DL-based semantic communication systems are usually designed using joint source and channel coding methods, and trained for a specific transmission content, including image [10], [11], [12], [13], video [14], speech [15], and text [16], [17], [18].”
BackgroundChen, J., Yi, C., Okegbile, S. D., Cai, J., & Shen, X. (2024) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3308717 · Cited by 254
“To achieve this, HDT requires accurate massive data and intensive computation power, which can hardly be met by resource-constrained mobile and IoT devices.”
BackgroundInfluentialSemantic Communications: Principles and Challenges
Qin, Z., Tao, X., Lü, J., Tong, W., & Li, G. Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2201.01389 · Cited by 254
“The bilingual evaluation understudy (BLEU) score is a commonly used metric to measure the quality of text after machine translation [36], which has been exploited to measure semantic communication systems for text transmission [12], [14].”
MethodSelf-citationDeep Learning-Enabled Semantic Communication Systems With Task-Unaware Transmitter and Dynamic Data
Zhang, H., Shao, S., Tao, M., Bi, X., & Letaief, K. B. (2023) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2022.3221991 · Cited by 252
“In the Internet of Things (IoT), where the computing power of each device is limited, a semantic communication system based on ADNet [27] is proposed to transmit text in [28].”
BackgroundGenerative AI-Driven Semantic Communication Networks: Architecture, Technologies, and Applications
Liang, C., Du, H., Sun, Y., Niyato, D. T., Kang, J., Zhao, D., & Imran, M. A. (2024) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2024.3435524 · Cited by 245
“In order to adapt the trained model for Internet-of-Things (IoT) devices with limited capability, the authors in [123] come up with a lite version of DeepSC (L-DeepSC) through pruning and quantizing the fully trained DeepSC models to achieve as large as 40 × compression ratio without performance…”
Task-Oriented Multi-User Semantic Communications for VQA
Xie, H., Qin, Z., & Li, G. Y. (2022) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2021.3136045 · Cited by 243
“Inspired by the emerging deep learning (DL) technologies, some initial works on DL-enabled semantic communications focus on semantic recovery at the receiver for text [3]–[5], image [6], and speech [7].”
BackgroundSelf-citationWang, Y., Chen, M., Luo, T., Saad, W., Niyato, D., Poor, H. V., & Cui, S. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2022.3191112 · Cited by 225
“The authors in [6] designed a distributed semantic communication system for capacity-limited networks.”
BackgroundSemantic-Preserved Communication System for Highly Efficient Speech Transmission
Han, T., Yang, Q., Shi, Z., He, S., & Zhang, Z. (2023) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2022.3221952 · Cited by 217
“The authors in [2] have also proposed an efficient and robust semantic-oriented transmission scheme, the deep learning model of which was then further compressed to be able to work on IoT devices [13] using the model quantization and pruning.”
Semantics-Empowered Communications: A Tutorial-Cum-Survey
Lu, Z., Li, R., Lu, K., Chen, X., Hossain, E., Zhao, Z., & Zhang, H. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3333342 · Cited by 213
“For example, in [154], a lite version “L-DeepSC” is studied, in which the authors consider an affordable structure for context transmission in IoT devices by pruning the model redundancy and decreasing the resolution of DNN weights.”
BackgroundMethodDeep Joint Source-Channel Coding for Semantic Communications
Xu, J., Tung, T.-Y., Ai, B., Chen, W., Sun, Y., & Gündüz, D. (2023) · IEEE Communications Magazine · doi:10.1109/mcom.004.2200819 · Cited by 207
“Recent works have demonstrated the superiority of Deep-JSCC over separate source and channel coding for various information sources, e.g., image [2], video [4], text [5] and speech [6].”
BackgroundMachine Learning for Large-Scale Optimization in 6G Wireless Networks
Shi, Y., Lian, L., Shi, Y., Wang, Z., Zhou, Y., Fu, L., Bai, L., Zhang, J., & Zhang, W. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3300664 · Cited by 205
“[34], [149], [150], image [151], [152], speech signals [153], [154] and general signals [155], [156]), from the perspective of performance metrics, semantic quantity module, semantic error module, loss function, KBs as well as the adaptation to dynamic environment for task-specific applications.”
BackgroundInfluentialDeep Source-Channel Coding for Sentence Semantic Transmission With HARQ
Jiang, P., Wen, C.-K., Jin, S., & Li, G. Y. (2022) · IEEE Transactions on Communications · doi:10.1109/tcomm.2022.3180997 · Cited by 199
“DeepSC is extended to the Internet of Things in [33], where more practical issues, such as channel impact, quantization, and network compression, are considered.”
BackgroundLarge AI Model Empowered Multimodal Semantic Communications
Jiang, F., Li, D., Peng, Y., Wang, K., Yang, K., Pan, C., & You, X. (2024) · IEEE Communications Magazine · doi:10.1109/mcom.001.2300575 · Cited by 193
“This change can be easily handled by neural networkbased channel decoders [11].”
BackgroundAdaptable Semantic Compression and Resource Allocation for Task-Oriented Communications
Liu, C., Guo, C., Yang, Y., & Jiang, N. (2023) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2023.3346481 · Cited by 192
“Recently, deep learning (DL) has emerged as a popular solution for signal processing tasks and semantic communications due to its powerful feature extraction capability [13], [14], [15], [16], [17], [18], [19], [20], [21], [22].”
BackgroundKang, J., Du, H., Li, Z., Xiong, Z., Ma, S., Niyato, D., & Li, Y. (2023) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2022.3221990 · Cited by 186
“The UTSC is particularly suitable for emerging intelligent scenarios in daily life [6], [9] and industry [17] (e.g., smart agriculture [18]).”
DRL-Driven Dynamic Resource Allocation for Task-Oriented Semantic Communication
Zhang, H., Wang, H., Li, Y., Long, K., & Nallanathan, A. (2023) · IEEE Transactions on Communications · doi:10.1109/tcomm.2023.3274145 · Cited by 184
“the authors in [9] further investigated an affordable semantic”
BackgroundTask-Oriented Image Transmission for Scene Classification in Unmanned Aerial Systems
Kang, X., Song, B., Guo, J., Qin, Z., & Yu, F. R. (2022) · IEEE Transactions on Communications · doi:10.1109/tcomm.2022.3182325 · Cited by 182
Self-citationDeep Learning-Based Image Semantic Coding for Semantic Communications
Huang, D., Tao, X., Gao, F., & Lu, J. (2021) · 2021 IEEE Global Communications Conference (GLOBECOM) · doi:10.1109/globecom46510.2021.9685667 · Cited by 177
“The semantic communication systems for text transmission is proposed in [5], [7], which enables intelligent communications for human-to-machine and machine-to-machine.”
BackgroundFederated Learning and Wireless Communications
Qin, Z., Li, G. Y., & Ye, H. (2021) · IEEE Wireless Communications · doi:10.1109/mwc.011.2000501 · Cited by 177
Self-citationJoint Coding-Modulation for Digital Semantic Communications via Variational Autoencoder
Bo, Y., Duan, Y., Shao, S., & Tao, M. (2024) · IEEE Transactions on Communications · doi:10.1109/tcomm.2024.3386577 · Cited by 175
“For example, in [24], the continuous outputs of the NN encoder are first uniformly quantized into discrete number sequences, then modulated into constellation symbol sequences.”
BackgroundInfluentialLifelo, Z., Ding, J., Ning, H., Ain, Q. U., & Dhelim, S. (2024) · Electronics · doi:10.3390/electronics13244874 · Cited by 173
Robust Information Bottleneck for Task-Oriented Communication With Digital Modulation
Xie, S., Ma, S., Ding, M., Shi, Y., Tang, M., & Wu, Y. (2023) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2023.3288252 · Cited by 170
“communication [33], [34], [35], the continuous-valued representation transmission exhibit weak compatibility with digital modulation based wireless systems, which greatly limits the deployment in the current and future communication systems.”
BackgroundSemantic Communication System Based on Semantic Slice Models Propagation
Chen, D., Liang, H., Xu, X., Han, S., Wang, B., & Zhang, P. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2022.3221948 · Cited by 166
“We embed the AI models into the transmitter and receiver of the physical layer to perform effective semantic communication, inspired by the existing semantic communication architecture proposed in [16], [17], and [18].”
BackgroundMethodInfluentialSemantic Communication Meets Edge Intelligence
Yang, W., Liew, Z. Q., Lim, W. Y. B., Xiong, Z., Niyato, D. T., Chi, X., Cao, X., & Letaief, K. B. (2022) · IEEE Wireless Communications · doi:10.1109/mwc.004.2200050 · Cited by 163
“Such a system can follow the semantic encoder/decoder structure in [9] where the input parameters are first encoded by the transmitter using a semantic encoder and a channel encoder, before sending the encoded information to the receiver.”
BackgroundMethodInfluentialSemantic Communication With Adaptive Universal Transformer
Zhou, Q., Li, R., Zhao, Z., Peng, C., & Zhang, H. (2021) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2021.3132067 · Cited by 161
AI Empowered Wireless Communications: From Bits to Semantics
Qin, Z., Liang, L., Wang, Z., Jin, S., Tao, X., Tong, W., & Li, G. Y. (2024) · Proceedings of the IEEE · doi:10.1109/jproc.2024.3437730 · Cited by 155
“The fast development of NLP forms the basic ground-work for analyzing and understanding the SoI and facilitates the implementation of joint semantic-channel coding for text [138], [139], [140], [141].”
BackgroundMethodSelf-citationZhang, P., Xu, W., Liu, Y., Qin, X., Niu, K., Cui, S. R., Shi, G., Qin, Z., Xu, X., Wang, F., et al. (2024) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2024.3443193 · Cited by 155
“There have been promising developments in the integration of SemCom with the industrial Internet, such as the task-oriented multi-user SemCom systems and lite distributed SemCom systems designed for low-computing-capacity devices [121].”
Self-citationDistributed Machine Learning for UAV Swarms: Computing, Sensing, and Semantics
Ding, Y., Yang, Z., Pham, Q., Hu, Y., Zhang, Z., & Shikh‐Bahaei, M. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3341307 · Cited by 146
“DNN model compression techniques (quantification and network sparsification) and DL are effective ways to address the above issue [127], [130].”
MethodA Comprehensive Exploration of 6G Wireless Communication Technologies
Siddiky, M. N. A., Rahman, M. E., Uzzal, M. S., & Kabir, H. M. D. (2025) · Computers · doi:10.3390/computers14010015 · Cited by 146
Federated Learning based Audio Semantic Communication over Wireless Networks
Tong, H., Yang, Z., Wang, S., Hu, Y., Saad, W., & Yin, C. (2021) · Globecom · doi:10.1109/globecom46510.2021.9685654 · Cited by 139
“However, most of these existing works [3]–[9] that focused on the use of semantic communication technique for text data processing did not consider how to extract the meaning out of the audio data.”
BackgroundA Robust Deep Learning Enabled Semantic Communication System for Text
Peng, X., Qin, Z., Huang, D., Tao, X., Lü, J., Liu, G., & Pan, C. (2022) · Globecom · doi:10.1109/globecom48099.2022.10000901 · Cited by 130
“DeepSC [2] is a pioneer work on semantic communications that presents a novel and effective architecture for text semantic transmission.”
BackgroundMethodSelf-citationBlockchain-Aided Secure Semantic Communication for AI-Generated Content in Metaverse
Lin, Y., Du, H., Niyato, D. T., Nie, J., Zhang, J., Cheng, Y., & Yang, Z. (2023) · IEEE Open Journal of the Computer Society · doi:10.1109/ojcs.2023.3260732 · Cited by 130
“To enable edge devices to perform DL-based semantic communication tasks, H. Xie et al. [11] proposed a lite-distributed semantic communication framework for edge devices to transmit low-complexity texts by optimizing training processes.”
Das, S. K., Benkhelifa, F., Sun, Y., Abumarshoud, H., Abbasi, Q. H., Imran, M. A., & Mohjazi, L. (2023) · Computer Networks · doi:10.1016/j.comnet.2023.109581 · Cited by 125
“Depending on the sender categories, recovering the transmitted data at receiver end is the primary intention of joint source-channel coding for images and texts [222].”
BackgroundA survey on semantic communications: Technologies, solutions, applications and challenges
Liu, Y., Wang, X., Ning, Z., Zhou, M., Guo, L., & Jedari, B. (2023) · Digital Communications and Networks · doi:10.1016/j.dcan.2023.05.010 · Cited by 122
Engineering Semantic Communication: A Survey
Wheeler, D., & Natarajan, B. (2023) · IEEE Access · doi:10.1109/access.2023.3243065 · Cited by 121
“Finally, L-DeepSC [32] reduces traffic in another way, by drastically reduce the parameters of a ML model which is to be broadcast to IoT devices.”
BackgroundInfluentialSemantics-Native Communication via Contextual Reasoning
Seo, H., Park, J., Bennis, M., & Debbah, M. A. (2023) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2023.3250206 · Cited by 121
“This includes the image-to-text embedding via Transformer [17], [18] and the conversion from system states into the state evolution law using the Koopman operator [19], [20].”
Applications of Distributed Machine Learning for the Internet-of-Things: A Comprehensive Survey
Le, M., Huynh‐The, T., Do‐Duy, T., Vu, T.-H., Hwang, W., & Pham, Q. (2024) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2024.3427324 · Cited by 120
“For text data, [92] shows the superiority of FL-SemCom over the conventional SemCom method, e.g., the model size is reduced from 12 .”
Toward Ubiquitous Semantic Metaverse: Challenges, Approaches, and Opportunities
Li, K., Lau, B. P. L., Yuan, X., Ni, W., Guizani, M., & Yuen, C. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3302159 · Cited by 115
“For example, AR/VR devices can use an information exchange process that enables entities, not using a standard syntax or protocol, to accomplish tasks [95], [96].”
BackgroundPhysical-Layer Adversarial Robustness for Deep Learning-Based Semantic Communications
Nan, G., Li, Z., Zhai, J., Cui, Q., Chen, G., Du, X., Zhang, X., Tao, X., Han, Z., & Quek, T. Q. S. (2023) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2023.3288249 · Cited by 114
“Towards this direction, many deep learning-based semantic communication systems have been proposed, including DeepSC [11], [19] for textual data, UDSem [37] for texts and images, DVST for video transmission [38], SCS [39], [40] for speech signals, MU-DeepSC [41] for question answering applications, and L-DeepSC [42] f…”
BackgroundSemantic Communication: A Survey on Research Landscape, Challenges, and Future Directions
Getu, T. M., Kaddoum, G., & Bennis, M. (2024) · Proceedings of the IEEE · doi:10.1109/jproc.2024.3520707 · Cited by 110
Task-Oriented Explainable Semantic Communications
Ma, S., Qiao, W., Wu, Y., Li, H., Shi, G., Gao, D., Shi, Y., Li, S., & Al‐Dhahir, N. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3269444 · Cited by 110
“Specifically, for text semantic transmission, the JSCC schemes have been designed by exploiting architectures like the recurrent neural network (RNN) [18], Transformer [19], [29], autoencoder (AE) [30], adaptive Universal Transformer [31], and deep neural network (DNN) [32].”
MethodMeng, S., Wu, S., Zhang, J., Cheng, J., Zhou, H., & Zhang, Q. (2024) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2024.3416309 · Cited by 110
“…Joint semantic-noise coding [102] Literal semantic noise and adversarial semantic noise [150] Capturing and utilizing CSI Channel ModNet [151], [152] Response network [153] Attention feature module [154] Encoding and modulation match with CSI [155] Training with CSI [156] Rate-control-related METs”
MethodNon-Orthogonal Multiple Access Enhanced Multi-User Semantic Communication
Li, W., Liang, H., Dong, C., Xu, X., Zhang, P., & Liu, K. (2023) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2023.3306852 · Cited by 107
“Recently, researchers have developed digital semantic communication systems which maps the full resolution feature into limited constellations [13]–[17].”
BackgroundMethodYang, Y., Guo, C., Liu, F., Sun, L., Liu, C., & Sun, Q. (2022) · IEEE Industrial Electronics Magazine · doi:10.1109/mie.2022.3174331 · Cited by 106
“Based on [8], the authors of [9] introduced a light distributed SC system for Internet of Things (IoT) applications.”
BackgroundMethodAdaptive Bit Rate Control in Semantic Communication With Incremental Knowledge-Based HARQ
Zhou, Q., Li, R., Zhao, Z., Xiao, Y. L., & Zhang, H. (2022) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2022.3189023 · Cited by 104
Reliable Semantic Communication System Enabled by Knowledge Graph
Jiang, S., Liu, Y., Zhang, Y., Luo, P., Cao, K., Xiong, J., Zhao, H., & Wei, J. (2022) · Entropy · doi:10.3390/e24060846 · Cited by 102
A Unified Blockchain-Semantic Framework for Wireless Edge Intelligence Enabled Web 3.0
Lin, Y., Gao, Z., Du, H., Niyato, D. T., Kang, J., Deng, R., & Shen, X. (2023) · IEEE Wireless Communications · doi:10.1109/mwc.018.2200568 · Cited by 102
“The data of wireless edge devices can be reduced to 2.5 percent exchange [3].”
BackgroundInfluentialSemantic Communications for Speech Signals
Weng, Z., Qin, Z., & Li, G. Y. (2021) · ICC 2021 - IEEE International Conference on Communications · doi:10.1109/icc42927.2021.9500590 · Cited by 96
Self-citationSemantic Communication With Memory
Xie, H., Qin, Z., & Li, G. Y. (2023) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2023.3288236 · Cited by 96
“Zhijin Qin is with the Department of Electronic Engineering, Tsinghua University, Beijing 100084, China (e-mail: qinzhijin@tsinghua.edu.cn).”
BackgroundInfluentialSelf-citationNguyen, L. X., Raha, A. D., Aung, P. S., Niyato, D. T., Han, Z., & Hong, C. S. (2025) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2025.3616973 · Cited by 96
“To overcome this, the authors of [147] introduce a CSI-aided training process that leverages CSI to mitigate the effects of fading during model training, thereby enhancing the robustness and accuracy of data transmission.”
Towards goal-oriented semantic signal processing: Applications and future challenges
Kalfa, M., Gok, M., Atalık, A., Tegin, B., Duman, T. M., & Arıkan, O. (2021) · Digital Signal Processing · doi:10.1016/j.dsp.2021.103134 · Cited by 94
“In [51], a lite version of this distributed semantic communication system for text transmission is studied, where the authors consider an affordable IoT network by pruning the model redundancies and reducing the model size.”
BackgroundMultimodal semantic communication accelerated bidirectional caching for 6G MEC
Wang, C., Yu, X., Xu, L., Wang, Z., & Wang, W. (2022) · Future Generation Computer Systems · doi:10.1016/j.future.2022.10.036 · Cited by 94
Deep Learning-Empowered Semantic Communication Systems With a Shared Knowledge Base
Yi, P., Cao, Y., Kang, X., & Liang, Y. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3330744 · Cited by 93
“To be specific, at the transmitter side, the channel state information [24] and the semantic importance distribution [25] were investigated to tackle varying channel conditions and perform resource allocation, respectively.”
BackgroundSemantic segmentation-based semantic communication system for image transmission
Wu, J., Wu, C., Lin, Y., Yoshinaga, T., Zhong, L., Chen, X., & Ji, Y. (2023) · Digital Communications and Networks · doi:10.1016/j.dcan.2023.02.006 · Cited by 92
Semantic Communication in Satellite-Borne Edge Cloud Network for Computation Offloading
Zheng, G., Ni, Q., Navaie, K., & Pervaiz, H. (2024) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2024.3365879 · Cited by 92
“For instance, Xie and Qin [14] introduced a pruned lite ML model tailored for distributed semantic coders.”
Making Sense of Meaning: A Survey on Metrics for Semantic and Goal-Oriented Communication
Getu, T. M., Kaddoum, G., & Bennis, M. (2023) · IEEE Access · doi:10.1109/access.2023.3269848 · Cited by 91
“To evaluate the quality of a machine translated text, the BLEU score [171] is a metric that is commonly used to assess the effectiveness of text SemCom systems [46], [48], [93]– [95], [98].”
MethodReinforcement Learning-powered Semantic Communication via Semantic SimilarityPreprint
Lu, K., Li, R., Chen, X., Zhao, Z., & Zhang, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.12121 · Cited by 89
“As [23] has done, we provide the cosine similarity of BERT embeddings in Fig.”
MethodA new communication paradigm: from bit accuracy to semantic fidelityPreprint
Shi, G., Gao, D., Song, X., Chai, J., Yang, M., Xie, X., Li, L., & Li, X. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.12649 · Cited by 88
“[4], [5] proposes that SC is an important part of the next generation 6G. [6] and [7] focuses on the problems of SC in natural language processing (NLP) and distributed neural network training and shows large saving on bandwidth, which show the promising future of SC.”
BackgroundSemantic Communication-Based Dynamic Resource Allocation in D2D Vehicular Networks
Su, J., Liu, Z., Xie, Y.-A., Ma, K., Du, H., Kang, J., & Niyato, D. T. (2023) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2023.3257770 · Cited by 85
“A novel communication mode, semantic communication mechanism, has been widely studied [4].”
BackgroundLaMoSC: Large Language Model-Driven Semantic Communication System for Visual Transmission
Zhao, Y., Yue, Y., Hou, S., Cheng, B. H., & Huang, Y. (2024) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2024.3401712 · Cited by 84
Zhou, F., Li, Y., Xu, M. Q., Yuan, L., Wu, Q., Hu, R. Q., & Al‐Dhahir, N. (2023) · IEEE Transactions on Communications · doi:10.1109/tcomm.2023.3318605 · Cited by 82
“Based on the works in [10] and [11], the authors in [12] proposed an environment-friendly SemCom system, namely L-DeepSC, for the capacity-limited Internet-of-Things (IoT) devices while the authors in [13] and [14] proposed multi-user SemCom systems, namely MU-DeepSC, for the multiple-user…”
BackgroundXiao, Y. L., Sun, Z., Shi, G., & Niyato, D. T. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2022.3229419 · Cited by 80
“Most existing works consider the semantics of messages as the explicit semantics such as object labels and signal features that can be directly identified from the source signals [13]–[15].”
BackgroundFeature Importance-Aware Task-Oriented Semantic Transmission and Optimization
Wang, Y., Han, S., Xu, X., Liang, H., Meng, R., Dong, C., & Zhang, P. (2024) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2024.3375496 · Cited by 73
“Further, to reduce the size and computation of DeepSC model, pruning and quantization methods were applied in [8], which made it affordable for resource-limited Internet of Things (IoT) devices.”
BackgroundMethodSemantic-Aware Spectrum Sharing in Internet of Vehicles Based on Deep Reinforcement Learning
Shao, Z., Wu, Q., Fan, P., Cheng, N., Chen, W., Wang, J., & Letaief, K. B. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3448538 · Cited by 73
“The existing semantic communication system was then lightweighted in [36], incorporating a channel estimation scheme based on the least squares method and a neural network solution for image denoising (ADNET).”
Quantum Semantic Communications for Metaverse: Principles and Challenges
Khalid, U., Ulum, M. S., Farooq, A., Duong, T. Q., Dobre, O. A., & Shin, H. (2023) · IEEE Wireless Communications · doi:10.1109/mwc.002.2200613 · Cited by 72
“Semantic communication is instrumental for accurate and real-time transmission in IoT networks owing to less consumption of communication resources as well as tolerance to channel noise [4].”
BackgroundPerformance Optimization for Semantic Communications: An Attention-based Learning Approach
Wang, Y., Chen, M., Saad, W., Luo, T., Cui, S. R., & Poor, H. V. (2021) · Globecom · doi:10.1109/globecom46510.2021.9685056 · Cited by 71
“In [4], the authors developed a distributed semantic communication system for capacity-limited Internet of Things devices.”
BackgroundSemantic Communication Empowered 6G Networks: Techniques, Applications, and Challenges
Wang, Y., Han, H., Feng, Y., Zheng, J., & Zhang, B. (2025) · IEEE Access · doi:10.1109/access.2025.3532797 · Cited by 71
Wireless Resource Management in Intelligent Semantic Communication Networks
Xia, L., Sun, Y., Li, X., Feng, G., & Imran, M. A. (2022) · IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) · doi:10.1109/infocomwkshps54753.2022.9797984 · Cited by 70
“For instance, as studied in [2] and [3], text-based ISC becomes promising by leveraging a natural language processing (NLP) model called Transformer.”
Islam, N., & Shin, S. (2024) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2024.3425314 · Cited by 64
“Drawing inspiration from [59], [60] the authors in [61] unveiled a novel SemCom tailored for text transmission based on a universal transformer (UT).”
BackgroundSemantic Importance-Aware Communications With Semantic Correction Using Large Language Models
Guo, S., Wang, Y., Ye, J., Zhang, A., Zhang, P., & Xu, K. (2025) · IEEE Transactions on Machine Learning in Communications and Networking · doi:10.1109/tmlcn.2025.3530875 · Cited by 64
“Xie et al. [19] developed quantization-based feasible constellations for existing systems.”
A survey of secure semantic communications
Meng, R., Gao, S., Fan, D., Gao, H., Wang, Y., Xu, X., Wang, B., Lv, S., Zhang, Z., Sun, M., et al. (2025) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2025.104181 · Cited by 64
On the Role of ViT and CNN in Semantic Communications: Analysis and Prototype Validation
Yoo, H., Dai, L., Kim, S., & Chae, C. (2023) · IEEE Access · doi:10.1109/access.2023.3291405 · Cited by 63
“One of the main research focuses is selecting building blocks for the neural network, such as convolutional [4], [7], self-attention [6], [8], or recurrent neural network blocks [5], or finding optimal network architecture.”
BackgroundRate-Adaptive Coding Mechanism for Semantic Communications With Multi-Modal Data
He, Y., Yu, G., & Cai, Y. (2023) · IEEE Transactions on Communications · doi:10.1109/tcomm.2023.3335977 · Cited by 63
“The authors in [16] quantized the full resolution constellation, which is the output tensor of the NN, to 64 -QAM during the inference phase.”
BackgroundSemantic Communications for Speech Recognition
Weng, Z., Qin, Z., & Li, G. Y. (2021) · Globecom · doi:10.1109/globecom46510.2021.9685250 · Cited by 60
“Moreover, a lite distributed semantic communication system for text transmission, named L-DeepSC, has been proposed in [13] to address the challenge of IoT to perform the intelligent tasks.”
Self-citationWireless large AI model: shaping the AI-empowered future of 6G and beyondPreprint
Zhu, F., Wang, X., Jiang, S., Li, X., Zhang, M., Chen, Y., Huang, C., Yang, Z., Chen, X., Zhang, Z., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.14653 · Cited by 59
Huang, Y., Bai, B., Zhu, Y., Qiao, X., Su, X. J., Yang, L., & Zhang, P. (2023) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2023.3345430 · Cited by 58
“For inference on mobile devices, the quantization method can be used to further accelerate the decoder’s inference performance [33].”
MethodLet RFF do the talking: large language model enabled lightweight RFFI for 6G edge intelligence
Gao, N., Liu, Y., Zhang, Q., Li, X., & Jin, S. (2025) · Science China Information Sciences · doi:10.1007/s11432-024-4463-0 · Cited by 58
Wireless Transmission of Images with the Assistance of Multi-level Semantic Information
Zhang, Z., Yang, Q., He, S., Sun, M., & Chen, J. (2022) · International Symposium on Wireless Communication Systems · doi:10.1109/iswcs56560.2022.9940401 · Cited by 58
Joint User Association and Bandwidth Allocation in Semantic Communication Networks
Xia, L., Sun, Y., Niyato, D. T., Li, X., & Imran, M. A. (2023) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2023.3318510 · Cited by 57
“Powered by advanced natural language processing (NLP) algorithms, the authors in [8] and [9] developed a Transformerbased text sentence similarity metric to measure the semantic performance in end-to-end SemCom systems.”
Mobility-Aware Split-Federated With Transfer Learning for Vehicular Semantic Communication Networks
Zheng, G., Ni, Q., Navaie, K., Pervaiz, H., Min, G., Kaushik, A., & Zarakovitis, C. C. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3360230 · Cited by 57
“Xie and Qin [23] proposed a lite distributed semantic communication system under power and latency constraints.”
BackgroundArtificial Intelligence for Wireless Physical-Layer Technologies (AI4PHY): A Comprehensive Survey
Ye, N., Miao, S., Pan, J., Ouyang, Q., Li, X., & Hou, X. (2024) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2024.3382973 · Cited by 57
“The authors of [106] considered an IoT network where the edge platform performs the DL-based semantic communication model training and updating while IoT devices perform data collection and transmission.”
MethodUnderstand-Before-Talk (UBT): A Semantic Communication Approach to 6G Networks
Pokhrel, S. R., & Choi, J. (2023) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2022.3219363 · Cited by 55
“Xie and Qin [15] applied deep learning to develop distributed SC system for text transmission.”
BackgroundMethodInfluentialZeng, C., Wang, J.-B., Xiao, M., Ding, C., Chen, Y., Yu, H., & Wang, J. (2023) · IEEE Transactions on Communications · doi:10.1109/tcomm.2023.3325901 · Cited by 55
“Thus, task-oriented semantic communications hold promises as a critical technique to fulfill URLLC requirements of WCSs in next-generation wireless networks [10], [11].”
BackgroundResource Optimization for Semantic-Aware Networks With Task Offloading
Ji, Z., Qin, Z., Tao, X., & Han, Z. (2024) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2024.3390407 · Cited by 55
“To reduce the transmission cost of the offloading tasks from local users to the edge server, we adopt the DeepSC model proposed by Xie et al. [11].”
BackgroundMethodSelf-citationFederated Learning for Audio Semantic Communication
Tong, H., Yang, Z., Wang, S., Hu, Y., Semiari, O., Saad, W., & Yin, C. (2021) · Frontiers in Communications and Networks · doi:10.3389/frcmn.2021.734402 · Cited by 55
“Meanwhile, in Xie and Qin (2021), the authors developed a new distributed text semantic communication system for IoT devices and they showed that nearly 20 times compression ratio can be achieved without any performance degradation.”
Background
Metadata
- Authors
- Xie, H., & Qin, Z.
- Affiliations
- Queen Mary University of London (GB)
- Venue
- IEEE Journal on Selected Areas in Communications
- Published
- 2021-01
- Volume
- 39
- Issue
- 1
- Pages
- 142-153
- ISSN
- 0733-8716 (ISSN-L)
- 1558-0008
- OpenAlex
- W3113050802
- Cited by
- 497
- References
- 44
- Citations by year
- 2026: 73 · 2025: 129 · 2024: 114 · 2023: 101 · 2022: 53 · 2021: 27
- FWCI
- 21.27
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Journal on Selected Areas in Communications (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Queen Mary Research Online (Queen Mary University of London) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Wireless Communication Technologies
- Physical Sciences › Engineering › Electrical and Electronic Engineering › IoT Networks and Protocols
- Keywords
- semantic communication, Internet of Things, deep learning, model compression, weight quantization, model pruning, channel state information, fading channels, textual transmission, edge computing, cloud computing, spectral efficiency
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.