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
Items 101–200 of 585
Knowledge-enhanced semantic communication system with OFDM transmissions
Xu, X., Xiong, H., Wang, Y., Che, Y., Han, S., Wang, B., & Zhang, P. (2023) · Science China Information Sciences · doi:10.1007/s11432-022-3624-4 · Cited by 54
“To reduce the size and computation of the deep learning-based semantic communication system (DeepSC) model, the methods of pruning and quantization are applied [10].”
BackgroundMethodInfluentialBlockchain-Based Efficient and Trustworthy AIGC Services in Metaverse
Lin, Y., Gao, Z., Du, H., Niyato, D. T., Kang, J., Xiong, Z., & Zheng, Z. (2024) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2024.3382958 · Cited by 53
“According to [30], the original semantic communication can be extracted by the Cross-Entropy (CE) loss function denoted as (1) where q ( x ) and p ( x ) are the probability distributions for real and expected outputs, respectively.”
MethodResource Management, Security, and Privacy Issues in Semantic Communications: A Survey
Won, D., Woraphonbenjakul, G., Wondmagegn, A. B., Tran, A.-T., Lee, D., Lakew, D. S., & Cho, S. (2024) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2024.3471685 · Cited by 51
“Conventional text-based SC systems [40], [42], [43], [55] primarily rely on fixed-length codes for sentences, which are unsuitable for sentences of varying lengths and result in inefficiencies under varying meanings and SNR conditions.”
InfluentialToward Natively Intelligent Semantic Communications and Networking
Trevlakis, S. E., Παππάς, Ν., & Boulogeorgos, A. A. (2024) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2024.3371871 · Cited by 50
“However, SemCom has introduced the semantic noise, which resides in errors generated during the interpretation of the semantic information of the transmitted messages [19], [20].”
BackgroundMultiple Access in the Era of Distributed Computing and Edge Intelligence
Evgenidis, N. G., Mitsiou, N. A., Koutsioumpa, V. I., Tegos, S. A., Diamantoulakis, P. D., & Karagiannidis, G. K. (2024) · Proceedings of the IEEE · doi:10.1109/jproc.2024.3417528 · Cited by 50
“Tomake DeepSC more suitable for practical applications, in [95], a quantization technique on the constructed unstructured constellation resulting from DeepSC was proposed.”
MethodScalable Extraction Based Semantic Communication for 6G Wireless Networks
Fu, Y., Cheng, W., Zhang, W., & Wang, J. (2023) · IEEE Communications Magazine · doi:10.1109/mcom.021.2300269 · Cited by 48
Communication-Efficient Framework for Distributed Image Semantic Wireless Transmission
Xie, B., Wu, Y., Shi, Y., Ng, D. W. K., & Zhang, W. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3304650 · Cited by 47
“Also, some existing works view the data transmission of each user as totally isolated procedure, e.g. [18], thus not fully improving the semantic extraction and task performance through the correlation among users.”
BackgroundA GAN-Based Semantic Communication for Text Without CSI
Mao, J., Xiong, K., Liu, M., Qin, Z., Chen, W., Fan, P., & Letaief, K. B. (2024) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2024.3415363 · Cited by 47
“It is noticed that, compared with AWGN channel, the ANN training for SC in fading channels is more challenging [28].”
BackgroundResultSelf-citationSecure Semantic Communications: From Perspective of Physical Layer Security
Li, Y., Shi, Z., Hu, H., Fu, Y., Wang, H., & Lei, H. (2024) · IEEE Communications Letters · doi:10.1109/lcomm.2024.3452715 · Cited by 47
“The semantic decoder contains multiple Transformer decoding layers with each having three sublayers, namely, the self-attention sublayer, encoder-decoder attention sublayer, and feed-forward sublayer.”
MDVSC—Efficient Wireless Model Division Video Semantic Communication
Bao, Z., Liang, H., Dong, C., Li, C., Xu, X., & Zhang, P. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3464614 · Cited by 47
“Works in [14], [15], [16], and [17] are the pioneer in implementing the semantic communication system.”
Rethinking Generative Semantic Communication for Multi-User Systems with Large Language Models
Yang, W., Xiong, Z., Mao, S., Quek, T. Q. S., Zhang, P., Debbah, M. A., & Tafazolli, R. (2025) · IEEE Wireless Communications · doi:10.1109/mwc.002.2400332 · Cited by 47
“To address the computational limitations of large-scale model training, preliminary works have integrated edge computing into SemCom frameworks to offload training tasks [3], [4].”
Aloudat, M. Z., Aboumadi, A., Soliman, A., Al-Mohammed, H. A., Al-Ali, M. S., Mahgoub, A., Barhamgi, M., & Yaacoub, E. E. (2025) · IEEE Access · doi:10.1109/access.2025.3555753 · Cited by 46
“In [163],”
Reasoning Over the Air: A Reasoning- Based Implicit Semantic-Aware Communication Framework
Xiao, Y. L., Liao, Y., Li, Y., Shi, G., Poor, H. V., Saad, W., Debbah, M. A., & Bennis, M. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3312115 · Cited by 45
“…on transporting the explicit semantic information, e.g., human-labeled objects or signal features that can be directly identified from the source signals (e.g, image, voice, and text signals) by adopting machine learning algorithms, especially the deep learning (DL)-based algorithms [8], [9].”
BackgroundGuo, L., Chen, W., Sun, Y., & Ai, B. (2024) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2024.3510586 · Cited by 45
“Restrictions apply. where I j ( z ideal ; T se ) and I j (ˆ z ; T se ) are the semantic information of the ideal network of the j -th class and the predicted semantic information of the j -th class, respectively.”
Zhang, M., Abdi, M., Dasari, V. R., & Restuccia, F. (2025) · Computer Networks · doi:10.1016/j.comnet.2025.111531 · Cited by 45
Context-Based Semantic Communication via Dynamic Programming
Zhang, Y., Zhao, H., Wei, J., Zhang, J., Flanagan, M. F., & Xiong, J. (2022) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2022.3173056 · Cited by 45
“The DeepSC Network [14], [35] is a state-of-the-art joint source-channel coding policy, which adopts a deep-learning (DL) enabled architecture for semantic communication.”
BackgroundGoal-Oriented Quantization: Analysis, Design, and Application to Resource Allocation
Zou, H., Zhang, C., Lasaulce, S., Saludjian, L., & Poor, H. V. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2022.3221976 · Cited by 44
“Similar models [32], [33] are extended to audio transmission and Internet-of-things (IoT) applications.”
Advances and Challenges in Semantic Communications: A Systematic Review
Zhang, P., Liu, Y., Song, Y., & Zhang, J. (2023) · National Science Open · doi:10.1360/nso/20230029 · Cited by 43
“[45] proposed a lightweight distributed semantic communication system designed for low-computing-capability devices by leveraging a model compression algorithm.”
BackgroundMethodComputing Networks Enabled Semantic Communications
Qin, Z., Ying, J., Yang, D., Wang, H., & Tao, X. (2024) · IEEE Network · doi:10.1109/mnet.2024.3352031 · Cited by 42
“In [10], DeepSC was deployed in an Internet-of-Things (IoT) network where the cloud/edge platforms equipped with high computing capabilities are used to train and update DL models while distributed IoT devices are used to extract and upload semantic features.”
BackgroundMethodSelf-citationA Comprehensive Survey on Self-Supervised Learning for Specific Emitter Identification
Liu, C., Gui, G., Wang, Y., Ohtsuki, T. O., Niyato, D. T., & Shen, X. (2025) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2025.3588171 · Cited by 41
“Compressing large models through pruning [146], quantization [147], knowledge distillation [148], and lottery ticket hypothesis [149] is an important research direction in the future, which can create efficient, general lightweight models suitable for a wide range of devices.”
Txt2Vid: Ultra-Low Bitrate Compression of Talking-Head Videos via Text
Tandon, P., Chandak, S., Pataranutaporn, P., Liu, Y., Mapuranga, A. M., Maes, P., Weissman, T., & Sra, M. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2022.3221953 · Cited by 41
“In fact, “semantic communication” [10], has seen a recent surge in research for various data modalities such as text [11], speech [12], Internet of Things (IoT) [13], and videos [14], to name a few (see Ref.”
BackgroundA Survey on Integrated Sensing, Communication, and Computing Networks for Smart Oceans
Dai, M., Li, Y., Li, P., Wu, Y., Qian, L., Lin, B., & Su, Z. (2022) · Journal of Sensor and Actuator Networks · doi:10.3390/jsan11040070 · Cited by 41
“Moreover, computation-efficient management methods and lightweight deep learning models should be investigated to enhance the resource utilization for the on-device semantic extraction [175].”
MethodCooperative Semantic Communication With On-Demand Semantic Forwarding
Tang, B., Huang, L., Li, Q., Pandharipande, A., & Ge, X. (2023) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2023.3344882 · Cited by 40
“It is worth noting that the proposed semantic encoding/decoding relies on deep neural network training, which usually consumes a considerable power that may not be feasible or affordable on wireless mobile devices [43].”
BackgroundMethodxURLLC-Aware Service Provisioning in Vehicular Networks: A Semantic Communication Perspective
Xia, L., Sun, Y., Niyato, D. T., Feng, D., Feng, L., & Imran, M. A. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3319442 · Cited by 39
“Xie et al. [6] devised a Transformer-based end-to-end Sem-Com system to realize link-level text transmission, and then improved this system to be lightweight in [14].”
BackgroundKnowledge Distillation-Based Semantic Communications for Multiple Users
Liu, C., Zhou, Y., Chen, Y., & Yang, S. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3336941 · Cited by 38
“We adopt the same structure as the L-DeepSC [8] for Teacher and Student 1, which has 4 layers of Transformer with 8 attention heads and 128 units as the semantic encoder and decoder.”
BackgroundMethodInfluentialCommon Language for Goal-Oriented Semantic Communications: A Curriculum Learning Framework
Karimzadeh‐Farshbafan, M., Saad, W., & Debbah, M. A. (2022) · International Conference on Communications · doi:10.1109/icc45855.2022.9838724 · Cited by 38
“In [2] and [3], the authors proposed a semantic communication frameworks for text transmission using deep learning.”
BackgroundSemantic Communication with Probability Graph: A Joint Communication and Computation Design
Zhao, Z., Yang, Z., Pham, Q., Yang, Q., & Zhang, Z. (2023) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2023-fall60731.2023.10333452 · Cited by 37
“With the rapid increase in demand for intelligent applications of wireless communication, the future communication network will change from a traditional architecture that simply pursues high transmission rate to a new architecture that is oriented to complete tasks efficiently [3].”
BackgroundLightweight Joint Source-Channel Coding for Semantic Communications
Jia, Y., Huang, Z., Luo, K., & Wen, W. (2023) · IEEE Communications Letters · doi:10.1109/lcomm.2023.3329533 · Cited by 36
“In [10], the authors proposed training and updating the DNN model at the network edge, compressing the trained DNN model using pruning quantization, and distributing them downstream, aiming to achieve a lightweight deployment of the JSCC scheme.”
MethodPragmatic Communication in Multi-Agent Collaborative Perception
Hu, Y., Pang, X., Qin, X., Eldar, Y. C., Chen, S., Zhang, P., & Zhang, W. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3680062 · Cited by 36
“Semantic communication: Semantic communication [42], [43], [44], [45], [46], [47], [47], [48], [49] aims at effective semantic information exchange rather than accurate symbol transmission regardless of its meaning.”
Cognitive Semantic Communication: A New Communication Paradigm for 6G
Li, Y., Zhou, F., Yuan, L., Wu, Q., & Al‐Dhahir, N. (2025) · IEEE Communications Magazine · doi:10.1109/mcom.005.2400366 · Cited by 36
“Framework for the Cognitive SemCom System”
Raha, A. D., Kim, K. T., Adhikary, A., Gain, M., Han, Z., & Hong, C. S. (2025) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2025.3573711 · Cited by 36
“Motivated by the visionary objectives of 6G technology and the advancements in artificial intelligence (AI), a new paradigm in communication, known as semantic communication (Sem-Com) [20], [21], [24], [25], [26], [27], [28], has recently been introduced.”
Reasoning on the Air: An Implicit Semantic Communication Architecture
Xiao, Y., Li, Y., Shi, G., & Poor, H. V. (2022) · IEEE International Conference on Communications workshops · doi:10.1109/iccworkshops53468.2022.9814604 · Cited by 36
Economics of Semantic Communication System in Wireless Powered Internet of Things
Liew, Z. Q., Cheng, Y., Lim, W. Y. B., Niyato, D. T., Miao, C., & Sun, S. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746463 · Cited by 35
Zhao, Z., Yang, Z., Gan, X., Pham, Q., Huang, C., Xu, W., & Zhang, Z. (2024) · Journal of the Franklin Institute · doi:10.1016/j.jfranklin.2024.107055 · Cited by 35
“Moreover, work [19] presented a lite distributed semantic communication system named L-DeepSC, designed for text transmission with low complexity.”
BackgroundRIS-Enhanced Semantic Communications Adaptive to User Requirements
Jiang, P., Wen, C.-K., Jin, S., & Li, G. Y. (2024) · IEEE Transactions on Communications · doi:10.1109/tcomm.2024.3369697 · Cited by 34
“Specifically, by employing deep learning (DL)- based joint source-channel coding architectures together with end-to-end training, the transmission process is optimized from the transmitter to the receiver, leading to accurate and efficient communication [5]–[8].”
BackgroundResource-Efficient Ubiquitous Sensor Networks for Smart Agriculture: A Survey
Arif, M., Maya, J. A., Anandan, N., Pérez, D. A., Tonello, A. M., Zangl, H., & Rinner, B. (2024) · IEEE Access · doi:10.1109/access.2024.3516814 · Cited by 34
“Recently, several frameworks for semantic communication have been proposed for the transmission of multimodal data [219], [220], [221].”
Adaptive Semantic-Bit Communication for Extended Reality Interactions
Wang, C., Li, Y., Gao, F., Deng, D., Xu, J., Liu, Y., & Wang, W. (2023) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2023.3310654 · Cited by 34
“We assume the semantic communication is based on the DeepSC framework [34], and thus the achievable semantic rate in suts/s/Hz at the k - th XR user can be expressed as: where I is the expected number of words per sentence, M is the average number of semantic symbols for each word, L denotes the…”
BackgroundMethodSemantic Communication Meets Edge Intelligence: Semantic-Relay-Aided Text Transmissions
Hu, Z., You, C., Liu, T., Wen, D., Hu, Y., Cui, Y., Gong, Y., & Huang, K. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3433431 · Cited by 33
Semantic Compression with Side Information: A Rate-Distortion PerspectivePreprint
Guo, T., Wang, Y., Han, J., Wu, H., Bai, B. B., & Han, W. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2208.06094 · Cited by 33
Speech Semantic Communication Based on Swin Transformer
Zhou, Z., Zheng, S., Chen, J., Zhao, Z., & Yang, X. (2023) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2023.3345858 · Cited by 31
“Xie and Qin [9] quantized the encoded signals before transmitting them through the physical channel, reducing the impact of noise while improving training efficiency.”
BackgroundSemantic Transfer Between Different Tasks in the Semantic Communication System
Wu, Q., Liu, F., Xia, H., & Zhang, T. (2022) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc51071.2022.9771768 · Cited by 31
Xu, W., Yang, Z., Ng, D. W. K., Schober, R., Poor, H. V., Zhang, Z., & You, X. (2026) · IEEE Transactions on Communications · doi:10.1109/tcomm.2026.3662396 · Cited by 35
“As edge hardware improves and techniques such as model compression, pruning, quantization, and knowledge distillation advance, lightweight sub-models are increasingly feasible on mobile and IoT nodes [127], [128].”
Semantic-aware Speech to Text Transmission with Redundancy Removal
Han, T., Yang, Q., Shi, Z., He, S., & Zhang, Z. (2022) · IEEE International Conference on Communications workshops · doi:10.1109/iccworkshops53468.2022.9814492 · Cited by 30
Constellation Design for Deep Joint Source-Channel Coding
Wang, M., Li, J., Ma, M., & Fan, X. (2022) · IEEE Signal Processing Letters · doi:10.1109/lsp.2022.3184251 · Cited by 30
“Apart from the constellation design of the physical layer, [17] proposed a semantic communication system, and the constellation of coded information is mapped to a finite set by uniform quantization.”
BackgroundDeep Learning Enabled Semantic Communication Systems for Video Transmission
Zhang, Z., Yang, Q., He, S., & Chen, J. (2023) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2023-fall60731.2023.10333553 · Cited by 30
“In [6], the authors proposed a text semantic communication system for Internet-of-Things devices, utilizing channel state information (CSI) aided scheme to achieve remarkable performance on different physical channels.”
BackgroundGenerative AI-Enabled Semantic Communication: State-of-the-Art, Applications, and the Way Ahead
Liang, C., & Li, D. (2025) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2025.3649707 · Cited by 29
“T HE exponential increase in mobile data traffic, coupled with the widespread adoption of Internet of Things (IoT) devices, has imposed significant demands on contemporary communication systems [1], [2].”
Energy-Efficient Task Offloading for Semantic-Aware Networks
Ji, Z., & Qin, Z. (2023) · International Conference on Communications · doi:10.1109/icc45041.2023.10279646 · Cited by 29
Self-citationA Theory for Semantic Channel Coding With Many-to-One Source
Ma, S., Chuanhui, Z., Qi, H., Li, H., Bi, Y., Shi, G., & Al‐Dhahir, N. (2025) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2025.3544275 · Cited by 29
“Recently, with the great progress of artificial intelligence (AI), neural networks can extract semantic information, such as images, text, and speech, which makes semantic communications feasible [22], [23], [24], [25].”
sDMCM—A Semantic Digital Modulation Constellation Mapping Scheme for Semantic Communication
Teng, L., An, W., Dong, C., & Xu, X. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3545667 · Cited by 28
LLM-Enabled Data Transmission in End-to-End Semantic Communication
Salehi, S., Erol‐Kantarci, M., & Niyato, D. T. (2025) · IEEE Symposium on Computers and Communications (ISCC) · doi:10.1109/iscc65549.2025.11326061 · Cited by 28
“This step reduces redundancy by concentrating on key information, resulting in a compressed representation, which is Authorized licensed use limited to the terms of the applicable license agreement with IEEE.”
Importance-aware image segmentation-based semantic communication for autonomous driving
Lyu, J., Haonan, T., Qiang, P., Zhilong, Z., Xinxin, H., Luo, T., & Yin, C. (2026) · China Communications · doi:10.23919/jcc.fa.2023-0771.202602 · Cited by 28
Dong, P., Wu, Q., Zhang, X., & Ding, G. (2022) · China Communications · doi:10.23919/jcc.2022.08.001 · Cited by 28
“As pointed in [22], dedicated channel estimation, especially DL-based approaches [31– 33], can help equalize the impact of channel fading, which stabilizes the model training and thus improves the system performance.”
BackgroundMethodInfluentialDeep Joint Source-Channel Coding for Wireless Image Transmission with Semantic Importance
Sun, Q., Guo, C., Yang, Y., Chen, J., Tang, R., & Liu, C. (2022) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2022-fall57202.2022.10012892 · Cited by 28
“Note the quantizer is designed to reduce the transmitter’s cost [17], and can map each element ei,j of the encoder output e to 0 or 1, which can be expressed as:”
BackgroundExplainable Semantic Communication for Text Tasks
Liu, C., Guo, C., Yang, Y., Ni, W., Zhou, Y., Li, L., & Quek, T. Q. S. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3450902 · Cited by 28
“Based on [9], the authors in [10] further proposed a lite distributed semantic communication system, making the model easier to deploy on the Internet of Things (IoT) devices.”
Attention-Aware Semantic Communications for Collaborative Inference
Im, J., Kwon, N., Park, T., Woo, J., Lee, J., & Kim, Y. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3440313 · Cited by 27
“Notably, collaborative inference is closely connected to semantic communications [8], [9], [10], [11], [12], [13], [14], considering that the extracted features are essentially semantic information tailored for the inference task.”
BackgroundContent-Aware Semantic Communication for Goal-Oriented Wireless Communications
Fu, Y., Cheng, W., & Zhang, W. (2023) · IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) · doi:10.1109/infocomwkshps57453.2023.10226153 · Cited by 27
“Moreover, the authors of [6] proposed the lite distributed semantic communication framework, which transmits data at the semantic level to improve transmission efficiency of Internet-of-Things (IoT) networks.”
BackgroundHybrid Semantic-Shannon Communications
Evgenidis, N. G., Mitsiou, N. A., Tegos, S. A., Diamantoulakis, P. D., Sarigiannidis, P. G., Krikidis, I., & Karagiannidis, G. K. (2024) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2024.3376998 · Cited by 27
“In [24], the authors considered a more practical scenario for the constellation arising from DeepSC, by using quantization on the constructed unstructured constellation.”
BackgroundMethodInfluentialNetworked Metaverse Systems: Foundations, Gaps, Research Directions
Zhang, Y., Kutscher, D., & Cui, Y. (2024) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2024.3426098 · Cited by 27
Multimodal Virtual Semantic Communication for Tiny-Machine-Learning-Based UAV Task Execution
Ren, C., He, Z., Long, Y., Zhao, C. Z., Sun, L., & Xu, K. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3416253 · Cited by 26
“However, [16] demonstrates that weight pruning and quantization can mitigate these issues by reducing the model size and complexity.”
BackgroundMethodWireless Resource Optimization in Hybrid Semantic/Bit Communication Networks
Xia, L., Sun, Y., Niyato, D. T., Zhang, L., & Imran, M. A. (2024) · IEEE Transactions on Communications · doi:10.1109/tcomm.2024.3485582 · Cited by 26
“As for the semantic transceiver design, Xie et al. [4] devised a Transformer-enabled end-to-end SemCom system for reliable text transmission, and then upgraded this system to be lightweight in [14].”
Semantic-Aware Resource Management for C-V2X Platooning via Multi-Agent Reinforcement LearningPreprint
Zhang, W., Wu, Q., Fan, P., Wang, K., Cheng, N., Chen, W., & Letaief, K. B. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2411.04672 · Cited by 26
Itahara, S., Nishio, T., Koda, Y., & Yamamoto, K. (2022) · IEEE Access · doi:10.1109/access.2022.3149336 · Cited by 25
“[10], [11] used analog communication to reduce the cost of channel encoding in digital communication, where multiple nodes transmit signals in the same time slot by leveraging superimposition [12].”
MethodToward Intelligent and Efficient 6G Networks: JCSC Enabled On-Purpose Machine Communications
Zhang, P., Yang, H., Feng, Z., Cui, Y., Dai, J., Qin, X., Li, J., & Zhang, Q. (2022) · IEEE Wireless Communications · doi:10.1109/mwc.014.2100641 · Cited by 25
“The irrelevant and redundant information sensing data leads to low system efficiency [7 information can be extracted from raw data to realize realize concise and efficient information exchange.”
BackgroundSignal Shaping for Semantic Communication Systems with A Few Message Candidates
Guo, S., Wang, Y., & Zhangz, P. (2022) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2022-fall57202.2022.10012981 · Cited by 25
“[7] proposed a lite distributed semantic communication system based on previous work [6], for Internet-of-Things devices with limited computing capability.”
Task-Oriented Semantic Communication Based on Semantic Triplets
Liu, C., Guo, C., Wang, S., Li, Y., & Hu, D. (2023) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc55385.2023.10118916 · Cited by 25
“Based on [9], the authors in [10] further proposed a lite distributed semantic communication system, making the model easier to deploy on the Internet of things (IoT) devices.”
BackgroundZheng, Y., Zhang, T., & Loo, J. (2023) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2023.3290546 · Cited by 25
“[14]consideredasemanticcommu-nicationsystemwhichwasconstructedbetweenedgeandIoT deviceswhereMECserverstrainedandupdatedthesemantic communicationmodelbasedondeeplearning,andtheIoTde-vicescollectedandtransmitteddatabasedonthetrainingmodel.”
BackgroundA survey on security issues in IoT operating systems
Sun, P. J., Wan, Y., Wu, Z., & Fang, Z. (2024) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2024.103976 · Cited by 25
Image Generation With Supervised Selection Based on Multimodal Features for Semantic Communications
Liang, C., & Li, D. (2025) · IEEE Transactions on Communications · doi:10.1109/tcomm.2025.3615798 · Cited by 24
“These applications not only necessitate high data rates but also demand low latency, high reliability, and context-aware communication [2], [3].”
Edge Learning for Large-Scale Internet of Things With Task-Oriented Efficient Communication
Xie, H., Xia, M., Wu, P., Wang, S., & Poor, H. V. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3271665 · Cited by 24
“Furthermore, concurrent transmissions of massive IoTs will inevitably yield severe CCI, thus degrading the performance of task-oriented communications [18].”
BackgroundSelf-citationBo, Y., Shao, S., & Tao, M. (2024) · IEEE Transactions on Communications · doi:10.1109/tcomm.2024.3447870 · Cited by 24
Integrated Object Detection and Communication for Synthetic Aperture Radar Images
Xu, Z., Xu, D., Lin, L., Song, L., Song, D., Sun, Y., & Chen, Q. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3495023 · Cited by 24
“Basedonthiswork,tomeetthe performanceconstraintsoftheInternetofThings(IoT)devices, alightweightdistributedsemanticcommunicationsystemis developedbypruningmodelredundancyandreducingweight resolution,andoptimizingthesemanticconstellation[51].”
Task-Driven Semantic-Aware Green Cooperative Transmission Strategy for Vehicular Networks
Yang, W., Chi, X., Zhao, L., Xiong, Z., & Jiang, W. (2023) · IEEE Transactions on Communications · doi:10.1109/tcomm.2023.3300869 · Cited by 23
“The employed semantic encoder and decoder are two separate learnable neural networks, and linked through a layer for modeling random channels [17].”
MethodLi, P., & Aijaz, A. (2023) · IEEE Conference on Standards for Communications and Networking · doi:10.1109/cscn60443.2023.10453123 · Cited by 23
“…a federated edge intelligence for resource-efficient semantic-aware networking [5]; the authors in [6] studied task-oriented communication for edge inference, and further, investigated the multi-device cooperative inference in [7]; the authors proposed a distributed SemCom system for IoT in [8].”
BackgroundComputational Offloading in Semantic-Aware Cloud-Edge-End Collaborative Networks
Ji, Z., & Qin, Z. (2024) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2024.3433387 · Cited by 22
“However, it is hard to find the closed-form derivative for the transmit power p tx , E i as it is provided by the pre-trained DeepSC model [22] as a black box.”
Self-citationControlled Quantum Semantic Communication for Industrial CPS Networks
Rizvi, S. M. A., Khalid, U., Chatzinotas, S., Duong, T. Q., & Shin, H. (2025) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3589296 · Cited by 22
“By transmitting the meaning of data rather than just raw bits, SC enhances the efficiency and effectiveness of information exchange in industrial environments [10], [11], [12], [13].”
Cross-modal communication technology: A survey
Wei, X., Wu, D., Zhou, L., & Guizani, M. (2023) · Fundamental Research · doi:10.1016/j.fmre.2023.08.002 · Cited by 22
“Specifically, Xie and Qin [68] develops a lightweight distributed semantic communication system for text transmission.”
Dynamic Malware Mitigation Strategies for IoT Networks: A Mathematical Epidemiology Approach
Vara, R. C., Severt, M., Díaz-Longueira, A., del Rey, A. M., & ROLLE, J. L. C. (2024) · Mathematics · doi:10.3390/math12020250 · Cited by 22
Peng, J., Xing, H., Li, Y., Li, F., Xu, L., & Lei, X. (2024) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2024.3417028 · Cited by 22
“For example, Xie and Qin [9] proposed L-DeepSC, a lightweight SC system with reduced model size.”
BackgroundDistortion Resilience for Goal-Oriented Semantic Communication
Nguyen, M.-D., Vinh, Q., Yang, Z., Pham, Q., & Hwang, W. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3456856 · Cited by 22
“The studies in [15], [16], [17] utilize Mean Square Error (MSE) and KL divergence between the original and reconstructed images as learning metrics to enhance the performance of semantic encoders.”
Wireless Network Optimization for Federated Learning with Model Compression in Hybrid VLC/RF Systems
Huang, W., Yang, Y., Chen, M., Liu, C., Feng, C., & Poor, H. V. (2021) · Entropy · doi:10.3390/e23111413 · Cited by 22
“The change of weights in a model can be used to evaluate their importance [22].”
BackgroundBlind Training for Channel-Adaptive Digital Semantic Communications
Oh, Y., Park, J., Choi, J., Park, J., & Jeon, Y. (2025) · IEEE Transactions on Communications · doi:10.1109/tcomm.2025.3585587 · Cited by 21
“This approach was further extended by incorporating non-orthogonal multiple access to enhance bandwidth effi-ciency [14], and lightweight DNN structures were developed to accommodate the limited computational power of edge devices [15].”
SemAudio: Semantic-Aware Streaming Communications for Real-Time Audio Transmission
Wei, H., Xu, W., Wang, F., Du, X., Zhang, T., & Zhang, P. (2022) · Globecom · doi:10.1109/globecom48099.2022.10001043 · Cited by 21
“In addition, to address the challenges associated with IoT devices, a lite distributed semantic communication system [5] was developed.”
BackgroundDRL-based intelligent resource allocation for physical layer semantic communication with IRS
Hu, B., Ma, J., Sun, Z., Liu, J., Li, R., & Wang, L. (2023) · Physical Communication · doi:10.1016/j.phycom.2023.102270 · Cited by 21
Optimized Support Vector Machine Based Fused IoT Network Security Management
Kumar, D., Pawar, P. P., Ananthan, B., Rajasekaran, S., & Prabhakaran, T. V. (2024) · International Conference on Artificial Intelligence for Internet of Things (AIIoT) · doi:10.1109/aiiot58432.2024.10574673 · Cited by 21
“IoT gadgets [2] are vulnerable to hacking attempts due to the shortage of trustworthy defensive mechanisms, as they provide a sizable assault space that is constantly leveraged.”
BackgroundAdversarial Attacks Against Shared Knowledge Interpretation in Semantic Communications
Hoang, V.-T., Nguyen, V.-L., Chang, R., Lin, P., Hwang, R., & Duong, T. Q. (2025) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2025.3528891 · Cited by 21
“S EMANTIC communications is one of the emerging technologies for addressing extremely high bandwidth demands from ultra high-definition (UHD) or 4K/8K resolution video services and holographic content providers in the sixth-generation (6G) networks [1], [2], [3], [4].”
Semantic communication for intelligent devices: architectures and a paradigm
张, 亦., Zhang, P., 魏, 急., 赵, 海., 熊, 俊., & 张, 姣. (2022) · Scientia Sinica Informationis · doi:10.1360/ssi-2020-0379 · Cited by 21
Semantic Communication for Cooperative Multi-Task Processing Over Wireless Networks
Razlighi, A. H., Bockelmann, C., & Dekorsy, A. (2024) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2024.3451139 · Cited by 20
“Data reconstruction is generally done by extracting semantic information on the transmitter side and recovering data using the received semantic information on the receiver side [5], [6], [7], [8].”
MethodDigital Semantic Device-Edge Co-Inference With Task-Oriented ARQ
Li, X., Bi, S., Wang, S., Li, X., & Zhang, Y. A. (2024) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2024.3390213 · Cited by 20
“Ifsuchdistortionisneglectedlikein[4],[5],[6],theactualinference resultindigitalcommunicationsystemscansignificantlydeviatefrom thetrainingprediction.”
MethodYin, J., Guo, L., Jiang, W., Hong, S., & Yang, J. (2021) · Computer Communications · doi:10.1016/j.comcom.2021.05.005 · Cited by 20
Large Generative Model Assisted 3D Semantic CommunicationPreprint
Jiang, F., Peng, Y., Li, D., Wang, K., Yang, K., Pan, C., & You, X. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2403.05783 · Cited by 20
“(17) - (19) can optimize ASCM to some extent, the fading channel still contaminates gradients during back-propagation and constrains semantic representation during forward-propagation [33].”
BackgroundTranGDeepSC: Leveraging ViT knowledge in CNN-based semantic communication system
Do, T. S., Truong, T. P., Do, Q. T., & Cho, S. (2025) · ICT Express · doi:10.1016/j.icte.2025.02.010 · Cited by 19
“Building on this foundation, Lite-DeepSC [6] proposed a more lightweight approach to address resource constraints in Internet of Things devices.”
Classification-Oriented Distributed Semantic Communication for Multivariate Time Series
Zhao, B., Xing, H., Wang, X., Xiao, Z., & Xu, L. (2023) · IEEE Signal Processing Letters · doi:10.1109/lsp.2023.3265330 · Cited by 19
“Traditional encoder and decoder networks [6], [7], [8], like convolutional neural networks (CNNs) [11], [12] or Transformers [13], [14], [15], may not be able to capture multi-scale features by an identical neural architecture, possibly leading to imbalanced attention to different variables.”
BackgroundDevice-Edge Digital Semantic Communication with Trained Non-Linear Quantization
Guo, L., Chen, W., Sun, Y., & Ai, B. (2023) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2023-spring57618.2023.10200355 · Cited by 19
“In addition, many researches [6], [7] focus on the joint device-edge semantic communication, in which devices with limited memory and computing capabilities process simple DL models to extract features and the powerful of DL models are usually deployed on the edge with abundant computational resources.”
BackgroundMethodInfluentialEconomics of Semantic Communication System: An Auction Approach
Liew, Z. Q., Du, H., Lim, W. Y. B., Xiong, Z., Niyato, D. T., Miao, C., & Kim, D. I. (2023) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2023.3278467 · Cited by 19
“To solve this dilemma, semantic communication technologies are proposed [1], which aims to transmit the extracted semantic information relevant to the communications goal.”
BackgroundAn Investigation on Intelligent Relay assisted Semantic Communication Networks
Ma, S., Liang, W., Zhang, B., & Wang, D. (2023) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc55385.2023.10118657 · Cited by 18
“Then, L-deepSC was proposed for context transmission in IoT devices [11].”
Computing Offloading and Semantic Compression for Intelligent Computing Tasks in MEC Systems
Zheng, Y., Zhang, T., Huang, R. Y., & Wang, Y. (2023) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc55385.2023.10118995 · Cited by 18
“[2] investigated the deployment of semantic communication system based on edge and IoT devices where MEC servers computing the semantic model and IoT devices collect and transmit data based on semantic task model where semantic compression exists on transmission side.”
BackgroundSemantic Information Extraction for Text Data with Probability Graph
Zhao, Z., Yang, Z., Hu, Y., Lin, L., & Zhang, Z. (2023) · IEEE/CIC International Conference on Communications in China (ICCC) · doi:10.1109/icccworkshops57813.2023.10233741 · Cited by 18
“The authors in [12] proposed a lite distributed semantic communication system based on deep learning, named LDeepSC, 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.”
BackgroundA Semantic-Oriented Federated Learning for Hybrid Ground–Aqua Computing Systems
Picano, B., & Fantacci, R. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3325289 · Cited by 18
“Before transmission, the picture s is mapped into symbols x m in order to be sent over the physical channel, experiencing transmission impairments due to sea environment, which implies that the symbol received at the receiver y m , b is subjected to wireless channel impairments [15], [16].”
BackgroundMethodLiu, J., Lu, Y., Wu, H., & Dai, Y. (2023) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2023-fall60731.2023.10333738 · Cited by 18
“A lightweight semantic communication system was developed in [10].”
Attention-Based UNet Enabled Lightweight Image Semantic Communication System over Internet of Things
Ma, G., Tong, H., Yang, N., & Yin, C. (2024) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc57260.2024.10570506 · Cited by 18
“The prior arts [7], [8] have studied lightweight image semantic communication along with the development of image segmentation techniques.”
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.