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":"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":"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":"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":"Graph Neural Network-Aided Online Calibration of Phase Shifter Networks","authors":"Idan Roth;Lutz Lampe","doi":"10.1109/TMLCN.2026.3679501","DOIUrl":"https://doi.org/10.1109/TMLCN.2026.3679501","url":null,"abstract":"Large-scale antenna systems with hybrid analog and digital beamforming for millimeter-wave (mmWave) communications play an essential role in enabling reliable, high data-rate transmissions for 5G and beyond wireless networks. However, their phase shifter networks (PSNs), which steer and shape the radiation patterns, are highly susceptible to phase deviations resulting from manufacturing defects, hardware degradation, and temperature shifts. Periodic calibration of PSNs is necessary to maintain operational effectiveness. To overcome the challenges associated with model-based iterative algorithm approaches, this paper introduces the first machine learning-based method for in situ online calibration of PSNs in mmWave hybrid beamforming systems. Specifically, we demonstrate that graph neural networks (GNNs) are well suited to effectively parameterize the mapping from the received pilots to PSN phase deviation estimates. To benchmark the performance of learning-based methods, we also derive the hybrid Cramér-Rao bound (HCRB) for the phase deviation estimates. Simulation results validate the effectiveness of our approach, showing that the GNN achieves performance close to the HCRB, outperforms traditional optimization-based methods, and exhibits robustness in dynamically changing environments.","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"4 ","pages":"629-646"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11458880","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147665556","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":"MF-Pnet: Deep Learning-Based Multi-Narrowband FM Signal Fusion for Enhanced Positioning","authors":"Shilian Zheng;Xinjiang Qiu;Luxin Zhang;Quan Lin;Keqiang Yue;Zhijin Zhao","doi":"10.1109/TMLCN.2026.3672679","DOIUrl":"https://doi.org/10.1109/TMLCN.2026.3672679","url":null,"abstract":"This paper proposes MF-Pnet, a deep learning-based positioning method designed to address the limited utilization of informative features in existing FM signal positioning approaches. Unlike prior methods that process the wideband FM signal as a whole, MF-Pnet extracts and fuses multiple narrowband IQ signals that carry potentially complementary information across different frequency bands. A multi-branch parallel feature extraction network is constructed to independently model the features from each narrowband signal, and an attention mechanism is introduced to adaptively weight their relative contributions. This design significantly enhances the overall feature representation and improves positioning accuracy. Comprehensive experiments conducted on a real-world FM dataset demonstrate that MF-Pnet outperforms the state-of-the-art FM-Pnet in both indoor and outdoor environments, exhibiting significant advantages in terms of accuracy, stability, and cross-day generalization capability. Furthermore, MF-Pnet maintains practical inference efficiency, making it well suited for deployment on resource-constrained devices.","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"4 ","pages":"562-574"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11429040","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147558044","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":"Digital Twin-Driven Continual Deep Reinforcement Learning for Coexistence of Multiple Radio Access Technology IoT Links With Nonlinear Receivers","authors":"Nahed Belhadj Mohamed;Georges Kaddoum;Md. Zoheb Hassan","doi":"10.1109/TMLCN.2026.3669837","DOIUrl":"https://doi.org/10.1109/TMLCN.2026.3669837","url":null,"abstract":"This article investigates the coexistence of downlink Internet-of-Things (IoT) links enabled by multiple radio access technologies (RATs), including long-term evolution (LTE) and 5G new radio (NR). The coexistence of multiple RAT IoT links is significantly challenged by adjacent channel interference (ACI) and hardware impairments (HWI) that arise from practical low-complexity radio-frequency front ends. To mitigate these challenges, we propose a radio resource optimization scheme that dynamically adjusts link adaptation parameters (transmit power, modulation, and coding rate) to maximize overall throughput while explicitly accounting for ACI and HWI. However, the proposed optimization is an NP-hard mixed-integer non-linear programming problem that requires global channel state information and centralized optimization, making it impractical for large-scale, dynamic multi-RAT IoT networks. To enable distributed optimization under ACI and HWI, we reformulate the problem as a Markov game and develop a multi-agent deep reinforcement learning (MADRL) framework that derives equilibrium link adaptation policies from local observations. Direct deep reinforcement learning (DRL) training in real networks, however, incurs high communication overhead and can create adverse effects due to the random explorations. To overcome these limitations, we introduce a context-aware digital twin network (DTN) that provides a safe and efficient virtual environment for training. In particular, we propose a novel DTN-empowered MADRL scheme that employs a replay memory-based continual model updating strategy, enabling policies to be learned from DT-generated experiences and periodically refined with real network data. This approach alleviates the need for frequent physical network interactions and significantly reduces communication overhead. Extensive simulations demonstrate that the proposed framework is scalable, computationally efficient, and robust in dynamic IoT environments, while outperforming 3GPP-standardized link adaptation in the presence of non-negligible ACI and HWI.","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"4 ","pages":"591-611"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11419167","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147558083","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":"Reinforcement Learning-Driven Honeypots: Tactic-Based Defense for Industrial Control Systems","authors":"Ying-Dar Lin;Rasul Mankaev;Didik SUDYANA;Yuan-Cheng Lai;Ren-Hung Hwang","doi":"10.1109/TMLCN.2026.3684465","DOIUrl":"https://doi.org/10.1109/TMLCN.2026.3684465","url":null,"abstract":"Traditional honeypots in Industrial Control Systems (ICS) often fail to sustain attacker engagement, exposing their deception after a few predictable responses and limiting visibility to early reconnaissance. This weakness reduces their value for defenders seeking insight into later stages of the kill chain. To address this, we propose an adaptive honeypot that embeds reinforcement learning (RL) into an ICS honeypot, enabling it to shape responses in real time based on attacker behavior. Guided by the MITRE ATT&CK for ICS framework, each network interaction is mapped to a tactic, and the RL agent applies tabular Q-learning to select deception strategies such as delaying, modifying, or blocking ICS protocol messages to drive sessions deeper into the attack chain. We evaluated the system using scripted Metasploit-based attacks derived from MITRE Campaigns across three honeypot configurations: Static0 (default ICS honeypot), Static1 (modified Modbus handler to support uncommon but valid function codes), and Dynamic (RL-driven honeypot). Results show that while static honeypots stall at tactic levels 4 and 7, the RL-driven honeypot reaches the latest tactic within 700 attack–response cycles and more than doubles the average engagement time. Even in the first 400 sessions, a small portion of attacks already reach the final tactic, providing early threat intelligence. These findings show that an RL-enhanced honeypot can adapt autonomously, extract deeper threat intelligence, and give defenders broader visibility across ICS tactics.","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"4 ","pages":"760-779"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11482844","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147796127","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":"Erratum to “Graph Neural Network-Aided Online Calibration of Phase Shifter Networks”","authors":"Idan Roth;Lutz Lampe","doi":"10.1109/TMLCN.2026.3684074","DOIUrl":"https://doi.org/10.1109/TMLCN.2026.3684074","url":null,"abstract":"Presents corrections to the paper, (Erratum to “Graph Neural Network-Aided Online Calibration of Phase Shifter Networks”).","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"4 ","pages":"758-759"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11500116","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147796124","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}