IEEE Transactions on Machine Learning in Communications and Networking最新文献

{"title":"Signal Whisperers: Enhancing Wireless Reception Using DRL-Guided Reflector Arrays","authors":"Hieu Le;Oguz Bedir;Mostafa Ibrahim;Jian Tao;Sabit Ekin","doi":"10.1109/TMLCN.2025.3650440","DOIUrl":"https://doi.org/10.1109/TMLCN.2025.3650440","url":null,"abstract":"This paper presents a multi-agent reinforcement learning (MARL) approach for controlling adjustable metallic reflector arrays to enhance wireless signal reception in non-line-of-sight (NLOS) scenarios. Unlike conventional reconfigurable intelligent surfaces (RIS) that require complex channel estimation, our system employs a centralized training with decentralized execution (CTDE) paradigm where individual agents corresponding to reflector segments autonomously optimize reflector element orientation in three-dimensional space using spatial intelligence based on user location information. Through extensive ray-tracing simulations with dynamic user mobility, the proposed multi-agent beam-focusing framework demonstrates substantial performance improvements over single-agent reinforcement learning baselines, while maintaining rapid adaptation to user movement within one simulation step. Comprehensive evaluation across varying user densities and reflector configurations validates system scalability and robustness. The results demonstrate the potential of learning-based approaches for adaptive wireless propagation control.","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"4 ","pages":"265-281"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11322690","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145929653","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ICT-META: In-Context Aware Few-Shot Learner for Encrypted Traffic Classification","authors":"Chengxiang Chang;Ying Li;Suranga Seneviratne;Xingquan Cai","doi":"10.1109/TMLCN.2026.3685578","DOIUrl":"https://doi.org/10.1109/TMLCN.2026.3685578","url":null,"abstract":"Encrypted traffic classification is a fundamental task in cybersecurity and network traffic management. With the popularity of deep learning, many studies have used it to achieve high accuracy in this field. However, these models rely on large amounts of labeled data and require retraining or fine-tuning when faced with new tasks, which is time-consuming and resource-intensive. Due to this limitation, few-shot traffic classification methods have emerged to reduce dependence on large labeled datasets by using only a few samples. However, these models often still require pre-training and fine-tuning to perform well. Meanwhile, Large Language Models (LLMs), such as ChatGPT, have attracted attention for their capacity to learn new concepts during inference without fine-tuning. Inspired by this, we propose In-Context Encrypted Traffic, a novel few-shot network traffic classification method allowing for few-shot classification without the need for fine-tuning. We use two existing encrypted traffic datasets to demonstrate the effectiveness of our method when facing new samples. We evaluate our method on a realistic 5-way few-shot classification task over encrypted traffic, and it achieves up to 5.7% higher accuracy than representative meta-learning baselines, without requiring fine-tuning.","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"4 ","pages":"733-743"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11488357","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147796126","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fine-Tuning Lightweight LLM for Enhanced Network Understanding: A Rephrase and Contrast Approach","authors":"Liujianfu Wang;Jingqi Lin;Yuyang Du;Yuchen Pan;Kexin Chen;Soung Chang Liew","doi":"10.1109/TMLCN.2026.3680410","DOIUrl":"https://doi.org/10.1109/TMLCN.2026.3680410","url":null,"abstract":"The application of Large Language Models (LLMs) to the domain of communication networks has emerged as a significant area of investigation for both academia and industry. However, progress in this field is constrained by two critical challenges: the limited generalization capabilities inherent in prompt-dependent techniques and a scarcity of efficient fine-tuning methodologies that can unlock the full potential of lightweight LLMs. To surmount these obstacles, this paper introduces Rephrase and Contrast (RaC), a novel fine-tuning framework designed to substantially enhance an LLM’s comprehension and logical reasoning abilities by systematically integrating question reformulation with a comparative evaluation of correct and incorrect responses. Our contributions are threefold. First, we present the RaC framework, whose efficacy is validated through extensive experimentation. The fine-tuned model demonstrates a 15.84% improvement in accuracy over its baseline counterpart when evaluated on a comprehensive benchmark of networking problems. Second, to facilitate robust model training, we developed a GPT-assisted data mining pipeline to generate high-fidelity question-answer (QA) pairs from established networking textbooks, creating a comprehensive dataset. We further introduce ChoiceBoost-X, a data augmentation technique designed to expand this dataset while mitigating positional bias in multiple-choice formats. Third, to foster reproducible research and community-driven innovation, we are releasing our complete toolchain as open-source, including: 1) a LLaMA3.1-8B model specifically fine-tuned for networking QA; 2) the curated training dataset from textbooks; and 3) multi-difficulty test sets to serve as a standardized benchmark for future studies.","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"4 ","pages":"647-661"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11474563","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147737177","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Neural Network-Based Box-Oriented Framework for Behavioral Modeling and Digital Predistortion of Power Amplifiers","authors":"Lesthuruge Silva;S. S. Krishna Chaitanya Bulusu;Nandana Rajatheva;Marko E. Leinonen;Nuutti Tervo","doi":"10.1109/TMLCN.2026.3678149","DOIUrl":"https://doi.org/10.1109/TMLCN.2026.3678149","url":null,"abstract":"This article presents a new box-oriented framework and training strategy that integrates conventional models with neural networks (NNs) for accurate power amplifier (PA) behavioral modeling and digital predistortion (DPD). Existing NN-based approaches rely solely on real-valued networks that overlook key complex-domain characteristics, and they attempt to learn all PA nonlinear distortions within the NN itself, resulting in unnecessarily high model complexity. To address these limitations, we propose a new technique that uses a simple conventional memory polynomial-based model to characterize the dominant PA distortions and a NN to characterize the remaining residual distortions. Following the framework, we introduce three new architectures: the feature-augmented simplified real-valued time-delay NN (SRTDNN), the generalized SRTDNN, and the parallel SRTDNN, combining a lightweight complex-valued polynomial model with a real-valued time-delay NN. In addition, we propose a joint training strategy to optimize both model components under different initialization schemes. Experimental validation using a <inline-formula> <tex-math>${mathrm {100~MHz}}~5$ </tex-math></inline-formula>G-NR OFDM signal and a Skyworks commercial PA shows that the proposed architectures achieve up to 1.1 dB improvement in normalized mean square error or a 45.5 % reduction in model complexity compared to the state-of-the-art vector-decomposed long short-term memory (VDLSTM) in PA behavioral modeling. In DPD experiments, the proposed models achieve improvements up to 1.22 dB in adjacent channel power ratio and 1.07 dB in error vector magnitude over the VDLSTM. Moreover, the proposed joint training approach improves modeling performance by up to 1.6 dB compared to the fixed-training strategy employed in the state-of-the-art SARTDNN.","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"4 ","pages":"662-676"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11457050","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147737178","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Resource Allocation in Hybrid Radio-Optical IoT Networks Using GNN With Multi-Task Learning","authors":"Aymen Hamrouni;Sofie Pollin;Hazem Sallouha","doi":"10.1109/TMLCN.2026.3674017","DOIUrl":"https://doi.org/10.1109/TMLCN.2026.3674017","url":null,"abstract":"This paper addresses the problem of dual-technology scheduling in hybrid Internet-of-things (IoT) networks that integrate Optical Wireless Communication (OWC) alongside Radio Frequency (RF). We begin by presenting an optimization formulation that jointly considers throughput maximization and delivery-based Age of Information (AoI) minimization between access points and IoT nodes under energy and link availability constraints. However, given the intractability of solving such NP-hard problems at scale and the impractical assumption of full channel observability, we propose the Dual-Graph Embedding with Transformer (DGET) framework, a supervised multi-task learning architecture combining a two-stage Graph Neural Networks (GNNs) with a Transformer-based encoder. The first stage employs a transductive GNN that encodes the known graph topology and initial node and link states (e.g., energy levels, available links, and queued transmissions). The second stage introduces an inductive GNN for temporal refinement, which learns to generalize these embeddings to the evolved states of the same network, capturing changes in energy and queue dynamics over time, by aligning them with ground-truth scheduling decisions through a consistency loss. These enriched embeddings are then processed by a classifier for the communication links with a Transformer encoder that captures cross-link dependencies through multi-head self-attention via classification loss. Simulation results show that hybrid RF-OWC networks outperform standalone RF systems by handling higher traffic loads more efficiently and reducing AoI by up to 20%, all while maintaining comparable energy consumption. The proposed DGET framework, compared to traditional optimization-based methods, achieves near-optimal scheduling with over 90% classification accuracy, reduces computational complexity, and demonstrates higher robustness under partial channel observability.","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"4 ","pages":"542-561"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11433800","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147558045","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep Reinforcement Learning-Aided Strategies for Big Data Offloading in Vehicular Networks","authors":"Talha Akyıldız;Hessam Mahdavifar","doi":"10.1109/TMLCN.2026.3700557","DOIUrl":"https://doi.org/10.1109/TMLCN.2026.3700557","url":null,"abstract":"We consider vehicular networking scenarios where existing vehicle-to-vehicle (V2V) links can be leveraged for an effective uploading of large-size data to the network. In particular, we consider a group of vehicles where one vehicle can be designated as the leader and other follower vehicles can offload their data to the leader vehicle or directly upload it to the base station (or a combination of the two). In our proposed framework, a periodically reselected leader vehicle is responsible for receiving the data from other vehicles and processing it in order to remove the redundancy (deduplication) before uploading it to the base station. We present a mathematical framework of the considered network and formulate a unified optimization problem for minimizing the combined time and energy consumption by vehicles for uploading their data to the base station. We employ deep reinforcement learning (DRL) tools to obtain solutions in a dynamic vehicular network where network parameters (e.g., vehicle locations and channel coefficients) vary over time. Our results demonstrate that the application of DRL is highly beneficial, and data offloading with deduplication can significantly reduce the time and energy consumption. Furthermore, we present comprehensive numerical results to validate our findings and compare them with alternative approaches to show the benefits of the proposed DRL methods.","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"4 ","pages":"966-984"},"PeriodicalIF":4.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11552888","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148433314","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Federated Learning-Enabled Collaborative Beamforming for NGSO Direct-to-Vehicle Systems","authors":"Almoatssimbillah Saifaldawla;Eva Lagunas;Madyan Alsenwi;Symeon Chatzinotas","doi":"10.1109/TMLCN.2026.3701669","DOIUrl":"https://doi.org/10.1109/TMLCN.2026.3701669","url":null,"abstract":"Non-geostationary satellite orbit (NGSO) systems are expected to play a central role in enabling direct satellite-to-vehicle (DS2V) connectivity. However, dense spectrum reuse and the coexistence of multiple NGSO constellations introduce severe co-frequency interference (CFI), which is further exacerbated by fast satellite motion and short channel coherence times. In this paper, we propose a federated learning (FL)–enabled collaborative receive beamforming framework for DS2Vs (FedSatBF). In FedSatBF, a serving satellite aggregates locally trained beamforming models from a subset of vehicular user terminals (VUTs) via federated averaging and broadcasts a global model that can be directly applied by both participating and non-participating VUTs under similar CFI conditions. An attention-based beamforming architecture is adopted as the base model for training local models at each VUT, with estimation-free sample covariance matrices as input, thereby eliminating the need for explicit estimation of the interference channel or the direction of arrival. The local model is trained via a reward-based learning objective in which the loss is the negative measured post-beamforming signal-to-interference-plus-noise ratio (SINR), so that no ground-truth weight, no synthetic geometry-derived label, and no interferer’ channel state information (CSI) is provided or needed during training. The proposed framework is explicitly designed to operate within the limited channel coherence time imposed by NGSO mobility. We investigate the impact of key FL hyperparameters, including per-coherent block communication rounds, per-round training data, per-VUT local epochs, VUT participation, and geographical VUT clustering, on convergence speed, interference nulling capability, and computational efficiency. Simulation results demonstrate that FedSatBF achieves near-optimal signal-to-interference-plus-noise ratio (SINR) performance, within 0.1 [dB] of an optimal zero-forcing beamformer (ZFBF) used here as a perfect-CSI oracle upper bound, and significantly outperforms conventional maximum-ratio combining (MRC), all while using only a moderate FL hyperparameter setting. Moreover, the global model exhibits strong generalization to non-participating VUTs and remains effective under reduced settings, highlighting the practicality of FL-based collaborative beamforming for the next generation of DS2V systems.","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"4 ","pages":"985-1004"},"PeriodicalIF":4.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11556460","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148433342","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Learning-Aided Adaptive Beampatterns for Secure Transmission and Enhanced Sensing in DFRC","authors":"Tiep M. Hoang;Alireza Vahid","doi":"10.1109/TMLCN.2026.3694004","DOIUrl":"https://doi.org/10.1109/TMLCN.2026.3694004","url":null,"abstract":"This paper investigates a dual-function radar-communication (DFRC) system, which senses a malicious target and communicates with legitimate users simultaneously. Being aware of the possibility that the target can overhear confidential messages inherently intended for the users, the DFRC beampattern design incorporates geofencing considerations, particularly in the presence of target mobility. To this end, we design adaptive beampatterns based on Q-learning, which dynamically adjusts the beampattern to accommodate target mobility, communication, and geofencing constraints. However, under such constraints, the transmit beampattern may become suboptimal for sensing functionality due to angular mismatches between the target direction and the feasible beampattern direction. To overcome this issue, we employ Gaussian Process Regression (GPR) to infer the target’s angle of arrival, even when the transmit beam is misaligned with the target (e.g., when the target enters geofenced regions). The combination of Q-learning and GPR provides a flexible machine learning-based framework for geofencing-aware DFRC systems in dynamic and constrained scenarios.","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"4 ","pages":"830-845"},"PeriodicalIF":4.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11520955","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148492304","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Natural Transports-Inspired Differential Semantic Communications: Intelligent Transceivers Carry Just Differences as Meanings","authors":"Ali Taimori;Mathini Sellathurai;Tharmalingam Ratnarajah","doi":"10.1109/TMLCN.2026.3716920","DOIUrl":"https://doi.org/10.1109/TMLCN.2026.3716920","url":null,"abstract":"Communication is a fundamental process in the nature of interconnected entities. Conventional engineering models of information transmission and reception, namely Shannon’s bit communication and Weaver’s semantic communication, consist of a serial architecture with the elements of transmitter, channel, and receiver. However, in natural transport processes, such as human-to-human interactions, transceivers operate through bidirectional, iterative closed-loop feedback mechanisms. Inspired by this physical observation, we propose a novel generalised cognitive communication topology, called Differential Semantic Communications, abbreviated DSC. In the DSC model, only informational differences are coded for communication purposes. As a result, this intelligent strategy leads to communication efficiency by priorly suppressing redundancies. We demonstrate the concept of our architecture to visual transmission using state-of-the-art semantic computing and generative artificial intelligence techniques. For the problem of transmitting salient objects in digital images, our experiments show that DSC can appropriately balance between bandwidth usage and meanings reconstruction error, with approximately 22 % substantial improvement in the mean semantic misfit error when compared to the best lossless transmission scheme. Our model can be used in diverse applications, including: storage- and bandwidth-constrained scenarios, such as server-client communications, the Internet of Things, and edge computing. The implementation codes, datasets, and experimental results are publicly available to researchers and developers.","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"4 ","pages":"1297-1317"},"PeriodicalIF":4.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11625937","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148749134","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"RSS Map-Assisted MIMO Channel Estimation in the Upper Mid-Band Under Pilot Constraints","authors":"Alireza Javid;Nuria González-Prelcic","doi":"10.1109/TMLCN.2026.3704874","DOIUrl":"https://doi.org/10.1109/TMLCN.2026.3704874","url":null,"abstract":"Accurate wireless channel estimation is critical for next-generation wireless systems, enabling precise precoding for effective user separation, reduced interference across cells, and high-resolution sensing, among other benefits. Traditional model-based channel estimation methods suffer, however, from performance degradation in complex environments with a limited number of pilots, while purely data-driven approaches lack physical interpretability, require extensive data collection, and are usually site-specific. This paper presents a novel physics-informed neural network (PINN) framework that synergistically combines model-based channel estimation with a deep network to exploit prior information about environmental propagation characteristics and achieve superior performance under pilot-constrained scenarios. The proposed approach employs an enhanced U-Net architecture with transformer modules and cross-attention mechanisms to fuse initial channel estimates with received signal strength (RSS) maps to provide refined channel estimates. Comprehensive evaluation using realistic ray-tracing data from urban environments demonstrates significant performance improvements, achieving over 5 dB gain in normalized mean squared error (NMSE) compared to state-of-the-art methods, with particularly strong performance in pilot-limited scenarios and robustness across different frequencies and environments with only minimal fine-tuning. We further extend the decoder for multi-step temporal prediction, enabling accurate forecasting of several future channel snapshots from a single estimate—useful for proactive beamforming and scheduling in mobile scenarios. The proposed framework maintains practical computational complexity, making it viable for massive multiple-input multiple-output (MIMO) systems in upper mid-band frequencies. Unlike black-box neural approaches, the physics-informed design provides a more interpretable channel estimation method.","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"4 ","pages":"1103-1119"},"PeriodicalIF":4.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11570128","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148443394","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}