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 301–400 of 585
Zhang, T., Xu, D., Ma, J., Bashir, A. K., Dabel, M. M. A., & Feng, H. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3501387 · Cited by 6
“To address this issue, using an empirical moving average (EMA) can effectively manage these out-liers, ensuring more stable quantization outcomes [63].”
Zheng, G., Ni, Q., Navaie, K., & Zarakovitis, C. C. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3546315 · Cited by 6
“This allows the aggregation of an efficient new SC codec model for all vehicles in the VN. Qin et al. [9] explored the potential of FL for SC codec updating, while Xie and Qin [10] proposed a lite federated SC system.”
Large Language Model Enabled Lightweight RFFI for 6G Edge Intelligence
Liu, Y., Gao, N., Li, X., & Jin, S. (2025) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc61545.2025.10978469 · Cited by 6
“Although the model compression and the RFF filters have been studied in several works to reduce the model size and eliminate the channel effect for RFFI, the existing methods still has a large number of parameters or is affected by the channel effect [9]–[14].”
Lee, H., Ahn, H., & Park, Y. D. (2022) · ICT Express · doi:10.1016/j.icte.2022.04.001 · Cited by 6
Machine Learning for Wireless Communication: An Overview
Cao, Z., Zhang, H., Liang, L., & Li, G. Y. (2022) · APSIPA Transactions on Signal and Information Processing · doi:10.1561/116.00000029 · Cited by 6
Alternate Learning based Sparse Semantic Communications for Visual Transmission
Tong, S., Yu, X., Li, R., Lu, K., Zhao, Z., & Zhang, H. (2023) · IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) · doi:10.1109/pimrc56721.2023.10293971 · Cited by 6
Liu, W., Zeng, Q., Lu, L., & Abdul, W. (2024) · Electronics · doi:10.3390/electronics13204076 · Cited by 6
Deep Image Semantic Communication Model for Artificial Intelligent Internet of ThingsPreprint
Qian, L., Zhang, Y., Lyu, S., Zhu, H., Wu, Y., Shen, X., & Yang, X. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2311.02926 · Cited by 6
“In text semantic communication, Xie et al. [11] proposed a deep learning-based distributed semantic communication system, which realizes the semantic transmission of data from the IoT terminal to the cloud/edge as well as the improvement of efficiency.”
BackgroundDo, T. S., Truong, T. P., Do, T., Van, H. P., & Cho, S. (2024) · doi:10.22541/au.172479430.09168922/v1 · Cited by 6
Unequal Error Protection Coding Scheme in Semantic Communication
Xu, Z., Liu, H., & Zhang, L. (2023) · IEEE International Conference on Anti-counterfeiting, Security, and Identification (ASID) · doi:10.1109/asid60355.2023.10426244 · Cited by 5
“On this basis, researchers proposed a lightweight distributed semantic communication system for IoT applications, which improves the text transmission performance [9] .”
BackgroundStochastic Geometry-Based Semantic Performance Analysis for Text Semantic Communication
Zhu, H., Zhu, K., Zhang, Y., & Niyato, D. T. (2025) · IEEE Transactions on Communications · doi:10.1109/tcomm.2025.3534574 · Cited by 5
“The key distinction between semantic communication and traditional communication lies in the nature of the transmitted Researchers [7], [11], [17], [18], [19] utilized deep neural networks to establish end-to-end frameworks for text semantic communication.”
Sleeping Multi-Armed Bandit-Based Path Selection in Space-Ground Semantic Communication Networks
Wu, H., Yang, X., Cao, S., Liu, J., Takakura, H., & Shiratori, N. (2025) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc61545.2025.10978165 · Cited by 5
“Existing research on semantic communication mostly focuses on semantic compression [3], semantic noise suppression [4], and multimodal semantic fusion [5].”
Shuffling for Semantic Secrecy
Chen, F., Xiang, L., Sun, H., Cheng, H. V., & Shen, K. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3573192 · Cited by 5
“The work of Xie and Qin [19] proposes a lightweight semantic communication system supporting IoT devices by pruning the model and adjusting the number of bits assigned to each model weight.”
Fully Learnable Multi-Rate Quantization for Digital Semantic Communication Systems
Kim, M., & Ji, D. J. (2025) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2025.3581374 · Cited by 5
“For instance, [7] utilized uniform quantization to digitize the output from the semantic encoder.”
Chen, C., & Huang, L. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111439 · Cited by 5
A cognitive agriculture framework for crop temperature prediction with semantic communication
Liu, H., Pan, X., Long, W., Wu, Y., Liu, L., Panneerselvam, J., & Zhu, R. (2025) · Digital Communications and Networks · doi:10.1016/j.dcan.2025.07.013 · Cited by 5
Razlighi, A. H., Bockelmann, C., & Dekorsy, A. (2025) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2025.3617156 · Cited by 5
“Initial investigations into data recovery were led by [14] and [15], which utilized the ML approach to reconstruct diverse data sources such as text, speech, and images.”
Deep Reinforcement Learning- and Information Bottleneck-Enabled Task-Oriented Semantic Communication
Zhao, T., Li, F., Du, H., & Sun, L. (2025) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2025.3623199 · Cited by 5
“For text semantic communication, Xie et al. proposed a Transformer-based DL-enabled semantic communication (DeepSC) method [3] and a lightweight version L-DeepSC [4] to address interference from channel noise and mitigate semantic degradation.”
Jiang, G., Han, S., Xu, X., Zhang, W., & Zhang, P. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3622076 · Cited by 5
“The first is data restoration, where the goal is to recover the essential meaning of the source, such as restoring an image or a piece of text [11], [12], [13], [14], [15], [16], [17], [18], [21], [22].”
Efficient Semantic Codec for Real-time Vibrotactile Transmission
Wang, R., Chen, K., Li, S. Q., Chen, M., & Zhao, T. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755630 · Cited by 5
“Additionally, Xie et al. [40] improved compression efficiency by reducing model size and decreasing weight resolution, while Zhou et al. [46] employed a recurrent design with adaptive features to further strengthen the semantic layer.”
Adaptive Source-Channel Coding for Semantic Communications
Li, D., Yuan, K., Huang, J., Huang, C. Z., Qin, X., Cui, S. R., & Zhang, P. (2026) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2026.3723124 · Cited by 5
“To address this issue, recent studies in [11], [18], and [19] focused on incorporating quantization and constellation mapping modules into the DNN-based JSCC schemes.”
Du, S., Zhang, Y., Tao, Z., Li, H., & Mei, H. (2026) · Sensors · doi:10.3390/s26020675 · Cited by 5
“In [20,21], the authors all pointed out that distributed computing using edge intelligence is a promising technology to realize SC in systems with no consistent infrastructures, like UAV communications or IoT systems.”
Semantic communication-based detection of False Data Injection Attacks in 6G-enabled smart grids
Alwaisi, Z., & Soderi, S. (2026) · International Journal of Electrical Power & Energy Systems · doi:10.1016/j.ijepes.2026.111649 · Cited by 5
Shi, J., Zhang, Q., Xu, Y., Zeng, W., Li, S., Guan, Z., & Qin, Z. (2026) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2026.3666519 · Cited by 5
“During the model training process, potential perturbations may arise due to untrainable and random channel gains [9].”
Self-citationDeep Reinforced Feature Compression and Channel Equalization for Semantic Communications
Seon, J., Lee, S., Kim, S. H., Sun, Y. G., Seo, H., Kim, D. I., & Kim, J. Y. (2025) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2025.3549782 · Cited by 5
“Unlike static end-to-end SC methods [16], [17], [18], [19], the proposed method leverages the DRL agent to adaptively optimize feature selection.”
A Resource Allocation Scheme for Intelligent Tasks in Vehicular Networks
Jiujiu, C., Guo, C., Feng, C., Liu, C., Sun, X., & Liu, J. (2022) · Wireless Communications and Mobile Computing · doi:10.1155/2022/6136944 · Cited by 5
“Recently, some works focus on intelligent endto-end semantic communication systems based on deep learning [18, 19].”
BackgroundPilot-Free Semantic Communication Systems for Frequency-Selective Fading Channels
Cao, Z., Zhang, H., Liang, L., & Wang, H. (2023) · IEEE International Conference on Communications workshops · doi:10.1109/iccworkshops57953.2023.10283499 · Cited by 5
“Recently, many DL-based semantic communication systems have been proposed [4]–[8].”
BackgroundMethodEnergy Efficiency in Semantic Networks: A Heuristic Optimization Approach for Resource Allocation
Xiao, A., Zhao, K., Liu, Z., & Liang, C. (2023) · Asia-Pacific Conference on Communications (APCC) · doi:10.1109/apcc60132.2023.10460718 · Cited by 5
“Drawing on the findings of [8], a lite distributed semantic communication system intended for low-complexity text transmission is proposed in [9].”
BackgroundSamarathunga, P., Ganearachchi, Y., Fernando, T., Thanippulige, L., & Fernando, A. (2024) · IEEE Gaming, Entertainment, and Media Conference (GEM) · doi:10.1109/gem61861.2024.10585490 · Cited by 5
“…attracting wide research interest, semantic communications have been identified as one of the key enablers for the next generation of mobile communication system (6G) with applications in the Metaverse [11], IoT [12] and even for infrastructure capabilities such as mobile edge computing (MEC) [13].”
BackgroundZeybek, M., Çetin, B. K., & Engın, E. Z. (2025) · Electronics · doi:10.3390/electronics14061130 · Cited by 5
Understanding Before Transmission (UBT): Hashing-based Semantic Communication Model
Pokhrel, S. R., & Choi, J. (2023) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc55385.2023.10119110 · Cited by 5
“Weng and Qin [33] proposed a mechanism to recreate the source message by constructing the speech signal.”
BackgroundSemantic optical fiber communication systemPreprint
Yu, Z., Huang, H., Cheng, L., Zhang, W., Mu, Y., & Xu, K. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2212.14739 · Cited by 5
“Efficient transmission of semantic information is then on the point of upgrading to the second level of communication [21, 22].”
BackgroundKnowledge-Driven Semantic Communication Enabled by the Geometry of MeaningPreprint
Wheeler, D., & Natarajan, B. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2306.02917 · Cited by 5
“However, many works taking this approach (including DeepSC) train the system with the goal of exactly reproducing the initial data [25], [30], i.”
BackgroundChannel-Aware Vector Quantization for Robust Semantic Communication on Discrete ChannelsPreprint
Meng, Z., Li, Q., Tang, W., Yan, M., & Ge, X. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.18604 · Cited by 5
Verifying DNN-based Semantic Communication Against Generative Adversarial NoisePreprint
Le, T. T., Duong, H., Nguyen, T. H., & Matsumura, T. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.08801 · Cited by 5
“In industrial IoT applications [39], these attacks could result in incorrect sensor readings or control decisions, compromising the integrity of critical infrastructure.”
Implementation and Evaluation of Semantic Communication on SDR Based LoRa Platform
Ma, J., Xu, D., Zhang, T., & Yu, K. (2024) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc57260.2024.10571323 · Cited by 4
“Authors in [8] proposed L-DeepSC, a distributed system for semantic communication.”
BackgroundImage Compression for Resource-Constrained AIoT System With Compressed Sensing
Chen, B., Huang, Y., Qiu, H., Xia, S., Wei, F., Wang, X., & Qiu, M. (2025) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2025.3571480 · Cited by 4
“It is a common way to compress the overparameterized DNN models by pruning, quantizing the weights, and knowledge distillation [6], [31].”
An overview of 6G wireless networks
Tashan, W., Pekdemir, A. I., Shayea, I. A. M., Alnakhli, M. A., Ergen, M., & Saad, S. A. (2025) · Physical Communication · doi:10.1016/j.phycom.2025.102790 · Cited by 4
Adaptive Semantic Speech Transmission for High-Speed Scenarios
Liu, F., Jiang, P., Wang, W., Zhou, X., Zhang, J., Wen, C.-K., & Jin, S. (2025) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2025.3601158 · Cited by 4
“Inspired by [47], we devised the quantization and dequantization (Q-deQ) structure shown in Fig.”
Backdoor Attacks on Large Language Model Based Semantic Communication Systems
Hoang, D., & Le, L. B. (2025) · IEEE International Conference on Communications workshops · doi:10.1109/iccworkshops67674.2025.11162215 · Cited by 4
“To address this issue, we could estimate the channel gain matrix H ′ using Least Squares, Minimum Mean Squared Error, Deep Learning-based Estimation, etc. ADNet has been used to estimate channel gain H ′ through a de-noising process in previous work [10].”
Highly Efficient Direct Analytics on Semantic-Aware Time Series Data Compression
Sun, G., Karras, P., & Zhang, Q. (2025) · International Conference on Communications · doi:10.1109/icc52391.2025.11162086 · Cited by 4
“Semantic communication has recently emerged as a novel communication paradigm to address the challenges of ever-increasing diverse data traffic, which focuses on transmitting task-relevant information, referred to as Semantics , instead of reliably transmitting sequence of bits [1].”
Alice-SLAM: Accurate and Lite-Communication Collaborative SLAM for Resource-Constrained Multi-Agent
Liu, J., Chen, K., Liu, R., Cheng, X., Zhang, J., Chen, S., Zhang, H., & Ajoudani, A. (2025) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2025.3623177 · Cited by 4
“Other approaches aim to reduce communication delays and data loss by minimizing transmitted data, thus improving system reliability through techniques like data compression [3], [4] and the exclusion of Inertial Measurement Unit (IMU) data for lossless mapping [5].”
Unequal Error Protection for Digital Semantic Communication with Channel Coding
Kim, S., Oh, Y., Kim, Y., Lee, N., & Jeon, Y.-S. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3740131 · Cited by 4
“Owing to its capability to reduce both communication overhead and local processing burden, semantic communication is particularly attractive for Internet of Things (IoT) applications, where resource-constrained devices collaboratively perform remote reconstruction or inference tasks [5], [6].”
Task-Oriented Semantic Communication Via Federated Learning
Xiang, Z., Li, Y., Yu, F., Wang, Y., Li, Y., & Rao, Z. (2025) · IEEE International Performance, Computing, and Communications Conference · doi:10.1109/ipccc66453.2025.11304693 · Cited by 4
“Although prior works like L-DeepSC [15] and FedLol [9] address parts of this problem, they often assume homogeneous models, stable channel conditions, or static task environments.”
Joint Optimization of Trajectory and Image Transmission in Multi-UAV Semantic Communication Networks
Yao, X., Zheng, J., Zheng, X., Dai, H., & Yang, X. (2023) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads60453.2023.00263 · Cited by 4
“Additionally, a lightweight distributed semantic communication system was proposed for the Internet of Things (IoT) in [7], which extends semantic communication users to multiple users.”
BackgroundEnhanced semantic communication schemes for speech signals
Yeo, Y., Kim, J., & Song, H. (2024) · Electronics Letters · doi:10.1049/ell2.13183 · Cited by 4
Design of a turbo-based deep semantic autoencoder for marine Internet of Things
Han, X., Lin, B., Wu, N., Wang, P., Na, Z., & Zhang, M. (2024) · Internet of Things · doi:10.1016/j.iot.2024.101393 · Cited by 4
“L-DeepSC, developed by the same team, is a lightweight distributed semantic communication system that emphasizes low-complexity text transmission, improving semantic-level transmission efficiency and promoting data transfer from IoT devices to the cloud or edge [19].”
Super-Resolution Semantic Communication System for Satellite Image
Do, T. S., Truong, T. P., Do, Q. T., Won, D., Wondmagegn, A. B., & Cho, S. (2025) · International Conference on Artificial Intelligence in Information and Communication (ICAIIC) · doi:10.1109/icaiic64266.2025.10920675 · Cited by 4
“This was followed by LiteDeepSC [2], which offered a more resource-efficient solution for IoT applications.”
Federated Learning for Semantic Communication Based on CNNs and Transformer
Li, S., Cai, Y., Deng, Z., Ba, X., Zheng, Q., Zhang, X., & Su, B. (2025) · International Journal of Intelligent Systems · doi:10.1155/int/3750087 · Cited by 4
“Xie et al. introduced a text transmission methodology known as deep learning-based semantic communication (DeepSC), utilizing Transformer technology to identify semantic information at the sentence level for the frst time [11].”
Xia, L., Sun, Y., Sun, H., Hu, R. Q., Niyato, D., & Imran, M. A. (2025) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2025.3612327 · Cited by 4
“For example, Xie et al. [7] devised a Transformer-based SemCom transceiver for reliable text transmission, which was then upgraded to be lightweight in [8].”
Large Generative Model Assisted 3D Semantic Communication
Peng, Y., 江沸菠, Dong, L., Wang, K., Yang, K., Pan, C., & You, X. (2025) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2025.3624573 · Cited by 4
“(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].”
BackgroundLayered Semantic Communication System for Dynamic Scenarios
Zhang, Y., Zhao, H., Cao, K., Zhang, Y., & Wei, J. (2024) · IEEE Signal Processing Letters · doi:10.1109/lsp.2024.3415967 · Cited by 4
“Additionally, we utilize a 4-bits constellation in [17] to quantify the extracted features for transmission, denoted as D-LSCS + CosEmb Loss.”
MethodPerformance Optimization for Task-Oriented Communications
Liu, C., Guo, C., & Yang, Y. (2024) · International Conference on Communications · doi:10.1109/icc51166.2024.10622483 · Cited by 4
“Based on [3], the authors in [4] further proposed a lite distributed semantic communication system, making the model easier to deploy at the Internet of things (IoT) devices.”
BackgroundEfficient Design for NOMA Enabled Integrated Sensing and Semantic Communication
Zhao, Z., Tang, Y., Yang, Y., Dong, Y., Xu, L., Yang, Z., & Zhang, Z. (2024) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2024-spring62846.2024.10683200 · Cited by 4
“For instance, et al. proposed DeepSC, a deep learning-based semantic communication system tailored for text transmission, while also introducing L-DeepSC, a lite distributed semantic communication system designed for IoT applications [17].”
BackgroundContract-Inspired Contest Theory for Controllable Image Generation in Mobile Edge Metaverse
Liu, G., Du, H., Wang, J., Niyato, D. T., & Kim, D. I. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3550815 · Cited by 4
Zaghouani, K., Djamaa, B., Yachir, A., & Mahmoudi, S. (2025) · Internet of Things · doi:10.1016/j.iot.2025.101591 · Cited by 4
Adversarial Learning for Implicit Semantic-Aware Communications
Lu, Z., Xiao, Y., Sun, Z., Li, Y., Shi, G., Chen, X., Bennis, M., & Poor, H. V. (2023) · International Conference on Communications · doi:10.1109/icc45041.2023.10279317 · Cited by 4
“A lite distributed semantic communication system, named L-DeepSC, was proposed in [10] also for text transmission.”
BackgroundTask-Oriented Semantic Communications for Multimodal Data.Preprint
Xie, H., Qin, Z., & Li, G. Y. (2021) · arXiv (Cornell University) · Cited by 4
Self-citationSemantic Satellite Communications for Synchronized Audiovisual ReconstructionPreprint
Liu, F., Jiang, P., Wang, W., Li, X., & Jin, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.10791 · Cited by 4
“Prior studies have successfully applied semantic communication to text [8] and images [9].”
A Survey on Semantic Communications System Based on Multi-modal Data
Win, T. T., Won, D., Do, Q. T., Oh, J., Hien, P. T. T., Paek, J., & Cho, S. (2024) · International Conference on Information Networking · doi:10.1109/icoin59985.2024.10572067 · Cited by 3
“In [2], the research addresses various challenges Fig.”
BackgroundShi, Y., Yu, L., & Zhu, Q. (2025) · Journal on Wireless Communications and Networking · doi:10.1186/s13638-025-02547-9 · Cited by 3
“Furthermore, a lightweight distributed semantic communication framework, termed L-DeepSC [13], was specifically developed for IoT scenarios, achieving efficient semantic compression and reliable transmission of text data from cloud devices through low-complexity implementation.”
Semantic HARQ: Joint Source–Channel Coding-Powered Reliable Retransmissions for IoT Networks
Li, Y., Wang, X., Shi, Z., Wang, D., & Fu, Y. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3661088 · Cited by 3
“For instance, Xie and Qin [14] developed a lightweight deep learning-based semantic communication system that maintains robustness for IoT devices even in low-SNR conditions.”
Resource Optimization for Semantic Communication in 6G Networks: A Survey
Sharif, S., Khandaker, F., Naeem, M., & Ejaz, W. (2026) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2026.3664496 · Cited by 3
“In SemCom, researchers have explored various performance metrics, such as semantic metrics for text [49], [50], [51], [52], [53], [54], [55], [56], speech [57], [58], [59], image [60], [61], [62], and video communication [63], [64].”
Cheng, R.-Z., Sun, Y., Taha, A., Liu, X., Flynn, D., & Imran, M. (2026) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2026.3671446 · Cited by 3
“Unlike traditional source encoding, which focuses on bit-level compression, semantic encoding prioritizes extracting goal-oriented or task-relevant semantics while discarding redundant or irrelevant binary bits [70].”
Anchor-Aided Multi-User Semantic Communication with Adaptive Decoders
Nguyen, L., Tran, P.-N., Pham, T. T., Raha, A. D., Huh, E., Han, Z., & Hong, C. S. (2026) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2026.3750303 · Cited by 3
Mustafovski, R., Qehaja, B., & Hajrizi, E. (2026) · Goce Delchev University Repository (Goce Delčev University of Štip) · Cited by 3
Xu, C., Yang, H., Yang, X., & Zhan, C. (2025) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2025.3591032 · Cited by 3
“The work in [33] proposed a low-complexity SemCom system for text transmission, which improved the transmission efficiency from devices to edge servers in edge computing-assisted Internet of things (IoT) systems.”
InfluentialZhou, L., Gaurav, A., Attar, R. W., Alhomoud, A., Arya, V., & Gupta, B. B. (2025) · IEEE Communications Standards Magazine · doi:10.1109/mcomstd.2025.3592778 · Cited by 3
“Hence, we overlook the potential distortions introduced by real-world environments [6], [7].”
A Deep Semantic Autoencoder for Maritime Wireless Communications
Han, X., Lin, B., Wu, N., Shao, S., & Wang, H. (2023) · IEEE/CIC International Conference on Communications in China (ICCC) · doi:10.1109/iccc57788.2023.10233675 · Cited by 3
“Xie introduced a DL-based simplified distributed semantic communication system for low-complexity text transmission named L-DeepSC [9].”
BackgroundSemantic Communication in the Metaverse
Lin, Y., Gao, Z., Du, H., Wang, J., & Zheng, J. (2024) · Wiley eBooks · doi:10.1002/9781394223336.ch8 · Cited by 3
Multi-level semantic-aware communication for multi-task image transmission
Zhang, Z., Yang, Q., He, S., & Chen, J. (2025) · Journal of the Franklin Institute · doi:10.1016/j.jfranklin.2025.107598 · Cited by 3
Xiao, J., Qu, Y., She, B., Lv, L., Song, C., Sun, Z., & Chen, F. (2022) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-022-07213-6 · Cited by 3
“In addition to the real network applications above, critical flow also has application prospects in big data [43, 44] and internet of things (IoT) systems [45, 46].”
BackgroundJoint Transmission and Understanding of Semantics with Edge Intelligence
He, Q., Zhang, Y., & Chen, Z. (2023) · International Conference on Communications · doi:10.1109/icc45041.2023.10279072 · Cited by 3
“Deep learning (DL)-based semantic communication systems have shown great potential in the transmission of multimedia data, such as images [5], [6], texts [7]–[9], and speech [10].”
BackgroundN-epitomizer: Enabling Semantic Offloading for Neural Network Inferences
Lee, S., Nam, W., Lee, J., Ha, S., & Lee, K. (2023) · IEEE International Conference on Mobile Ad-Hoc and Sensor Systems (MASS) · doi:10.1109/mass58611.2023.00017 · Cited by 3
“Semantic offloading can be understood as a representative instantiation of semantic communications [11], [12], [13], which aim at sending only the meaningful bytes sufficient to achieve the goal of communications instead of sending the entire bytes.”
BackgroundEconomics of Semantic Communication System in Wireless Powered Internet of ThingsPreprint
Liew, Z. Q., Cheng, Y., Lim, W. Y. B., Niyato, D. T., Miao, C., & Sun, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.01423 · Cited by 3
“Recent works showed that the semantic communication sys-tem is robust at low signal-to-noise (SNR) region [6], [7], which helps to increase the reliability of IoT services.”
Collaborative Edge-to-Server Inference for Vision-Language ModelsPreprint
Song, S., & Kim, Y. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.16349 · Cited by 3
SEMUAV: A Cooperative Semantic Communication Method in SATIN
Ma, S., Liang, W., Zhang, B., Xue, X., & Gao, A. (2023) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshps58843.2023.10464908 · Cited by 2
“At the same time, many studies have proved that semantic communication could greatly reduce the data volume while maintaining communication quality [6]–[8].”
BackgroundMethodNOMA-Enhanced Intelligent Semantic Communication Networks using Deep Reinforcement Learning
Truong, T. P., Hur, D., Oh, J., Lee, D.-H., Won, D., Paek, J., & Cho, S. (2024) · International Conference on Information Networking · doi:10.1109/icoin59985.2024.10572204 · Cited by 2
Tang, L. D., Sun, Y., Yao, S., Xu, X., Chen, H., & Luo, Z. (2025) · Electronics · doi:10.3390/electronics14081666 · Cited by 2
Fast Multimodal Edge Inference via Selective Feature Distillation
Chen, J., Xu, W.-C., Fan, Y.-F., Wang, H.-Z., Chen, Q., & Li, J. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3580102 · Cited by 1
“Similarly, [39] explores deep learning-enabled semantic text transmission within IoT networks, addressing the challenges posed by limited computational resources on IoT devices and constrained bandwidth between devices and the cloud.”
Cognitive semantic communications with codebook-based adaptive correction for image classification
Weng, Y., Sun, J., & Wu, J. (2025) · Physical Communication · doi:10.1016/j.phycom.2025.102764 · Cited by 2
Convolutional Neural Network-enabled Semantic Communication Approach for Image Classification Tasks
Güler, N., Hazem, Z. B., & Güneş, A. (2024) · International Conference on Open Innovation and Digital Transformation (OIDT) · doi:10.1109/oidt59407.2024.11082691 · Cited by 2
Niu, H., Wang, L., Lu, Z., Wen, X., & Marques, P. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3592241 · Cited by 2
“This approach effectively overcomes the cliff-effect of conventional bit-based systems and improves the reliability and accuracy of IoT data transmission under adverse wireless channel conditions [12], [13], [14].”
Lightweight Semantic Segmentation Network for End-to-End Learning-based Communication
Dai, S., Yu, Y., Wang, Z., Liu, C., & Zhou, Y. (2025) · International Conference on Computer Communications and Networks (ICCCN) · doi:10.1109/icccn65249.2025.11133815 · Cited by 2
“Also, several works have proposed lightweight and effective semantic communication models [8], [9] to minimize computational overhead while preserving their system robustness, nevertheless, they cannot address multi-modal image data.”
Guo, J., Jia, X., Zhu, J., Li, X., Liu, Y., Feng, W., & Xue, W. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.131347 · Cited by 2
Liu, C., Wei, Z., Chen, Y., & Sun, H. (2025) · IEEE/CIC International Conference on Communications in China (ICCC) · doi:10.1109/icccworkshops67136.2025.11147223 · Cited by 2
“To enable lightweight architectures and reduce computational overhead, SemCom systems are optimized for deployment on edge devices [3], [4].”
Xu, Y., Gao, R., Zhang, Q., & Yang, Z. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3609792 · Cited by 2
“…has limited power, the authors 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 in [43].”
A Goal-Oriented Context-Aware Adaptive Semantic Communication Scheme Using a Semantic Mask Module
Ogunjimi, O., Chen, F., Fang, F., & Wang, X. (2025) · IEEE International Conference on Communications workshops · doi:10.1109/iccworkshops67674.2025.11162417 · Cited by 2
“Furthermore, [11] introduced L-DeepSC, a framework employing a pruning strategy to create sparse network structures.”
Zhang, H., Hu, Y., Yuan, X., & Schmeink, A. (2025) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2025.3623178 · Cited by 2
“In the existing literature, there are only a few works, e.g., [29], [30], considering latency effects on semantic communications.”
Toward Intelligent Bandwidth Prioritization in Distributed 6G ISAC: An Agentic AI Perspective
Alshalwi, F., Nawaz, M. W., Kaushik, A., Mohjazi, L., Popoola, O., & Imran, M. A. (2025) · IEEE Conference on Standards for Communications and Networking · doi:10.1109/cscn67557.2025.11230734 · Cited by 2
“Furthermore, Xie and Qin introduced L-DeepSC for IoT semantic compression with significant bandwidth savings [13].”
Channel Denoising in Digital Semantic Communication Systems via Discrete Diffusion
Tang, W., Meng, Z., Li, Q., Yan, M., & Ge, X. (2025) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2025.3646169 · Cited by 2
“To address the conflict between analog JSCC assumptions and digital systems, a quantizer is employed to map the continuous semantic features into discrete constellation symbols [4], [5], [6], with quantization serving as a digital modulation.”
NOMA Enhanced Semantic Communication with Swin Transformer in STINs
Li, D., Wang, K., Wang, X., & Liu, J. (2025) · IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) · doi:10.1109/infocomwkshps65812.2025.11152887 · Cited by 2
“In semantic communication, the source of information can take various modalities, including text [14], [15], audio [16], images, video [17], and holographic point clouds [18], [19].”
Optimal and Robust Beamforming Design for Multiuser Semantic Interference Networks
Ma, S., Shen, B., Chuanhui, Z., Li, H., Li, N., Chai, J., Huang, C., Li, S., & Shi, G. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3621691 · Cited by 2
“By exploiting various joint source–channel coding (JSCC) schemes, semantic communication has attracted increasing research attention for di ff erent data modalities, such as text [5], [6], [7], speech [8], [9], [10], image [11], [12], [13], and video [14], [15], [16].”
BidDeepSC-1.58b: 1.58-Bit Bidirectional Slimmable Semantic Communication System
Do, T. S., Truong, T. P., Do, Q. T., Won, D., Noh, W., & Cho, S. (2025) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2025.3622754 · Cited by 2
“(cid:2) Resource-Efficient Edge Deployment: Previous studies have proposed several methods such as pruning and neural network quantization to reduce resource consumption [4], [26], [27].”
InfluentialZhuang, J., Li, L., Long, Y., Gu, B., Yi, C., & Gong, S. (2026) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2026.3657116 · Cited by 2
“The authors in [15] established foundational frameworks for semantic communication by leveraging centralized model training on MEC servers.”
Mai, T., Yao, H., Zhu, G., Jin, C., & Xin, X. (2026) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2026.3662333 · Cited by 2
“Xie and Qin showed that an SC system for the Internet of Things (IoT) can cut transmission volume by up to 40 times compared to conventional bit-level communication approaches [12].”
TAHENNI, A., Ouameur, M. A., Bagaa, M., Massicotte, D., salmi, S., Figueiredo, F. A. P. D., & Ksentini, A. (2026) · Computer Networks · doi:10.1016/j.comnet.2026.112143 · Cited by 2
Yashu, K., Gogi, V. J., & Azarudheen, S. (2025) · IEEE DELCON - International Conference on Recent Smart Technologies in Engineering for Sustainable Development (DELCON) · doi:10.1109/delcon68055.2025.11400330 · Cited by 2
From Bits to Meaning: A Survey of Semantic Communications for 6G Networks
Ansere, J. A., Le, Q. N., & Nguyen, T. T. (2026) · EAI Endorsed Transactions on Tourism Technology and Intelligence · doi:10.4108/eettti.11434 · Cited by 2
“This approach supports energy-e ffi cient, low-latency, and carbon-aware operation, which is essential for massive-scale 6G connectivity [16].”
Huang, C. X., Chen, G., Zhu, J., Luo, Q., Xiao, P., Huang, W., & Tafazolli, R. (2025) · Globecom · doi:10.1109/globecom59602.2025.11432006 · Cited by 2
“It can effectively alleviate link budget constraints and substantially enhance the overall performance and reliability of future communication systems.”
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.