Pub Date : 2025-06-30DOI: 10.1109/JSAC.2025.3584502
Haiyang Miao;Jianhua Zhang;Pan Tang;Lei Tian;Weirang Zuo;Hongbo Xing;Guangyi Liu
Multiple-input-multiple-output (MIMO) has been a promising technology in wireless communication systems. Channel models are of great importance for the development and assessment of system. With the increase of carrier frequency and MIMO size, the channel model needs to consider near-field spherical wave and spatial non-stationary characteristics, which is different from conventional far-field planar-wave-based geometry-based stochastic model (GBSM) in the 3rd Generation Partnership Project (3GPP). This paper focuses on comparing the channel characteristics and modeling in the far- and near-field region. In this work, we design the measurement campaign in the 6 GHz band (5.9-6.1 GHz) involving the unlicensed spectrum. The uniform planar array (UPA) is adopted from far-field to near-field, where the communication distance is decreasing from 21 m to 6 m (Rayleigh distance is about 14.8 m). Compared to the far-field, the spatial non-stationary phenomenon of channel parameters can be more clearly observed along the array in the near-field region. Then, we propose the extension channel model based on the channel modeling of 3GPP TR 38.901. The array domain is introduced to characterize the spatial non-stationarity of channel parameters (e.g., power, delay, angle). Subsequently, the channel characteristic parameters along the array are analyzed in the near-field range, and the non-stationary model related to the antenna array is established, including power, path loss, delay spread, angular spread, and Ricean K-factor. Finally, the model validation and parametrization are presented in detail with the actual indoor near-field MIMO channel measurements in the 6 GHz band, such as power, angle, and so on. The design and scheme of antenna array spacing are given under the influence of spatial non-stationary characteristics. These work will be helpful for the development and operation of MIMO technology in unlicensed spectra for wireless communication systems.
{"title":"Far-Field to Near-Field: Experimental Studies of MIMO Channel Characterization and Modeling in the 6 GHz Band","authors":"Haiyang Miao;Jianhua Zhang;Pan Tang;Lei Tian;Weirang Zuo;Hongbo Xing;Guangyi Liu","doi":"10.1109/JSAC.2025.3584502","DOIUrl":"10.1109/JSAC.2025.3584502","url":null,"abstract":"Multiple-input-multiple-output (MIMO) has been a promising technology in wireless communication systems. Channel models are of great importance for the development and assessment of system. With the increase of carrier frequency and MIMO size, the channel model needs to consider near-field spherical wave and spatial non-stationary characteristics, which is different from conventional far-field planar-wave-based geometry-based stochastic model (GBSM) in the 3rd Generation Partnership Project (3GPP). This paper focuses on comparing the channel characteristics and modeling in the far- and near-field region. In this work, we design the measurement campaign in the 6 GHz band (5.9-6.1 GHz) involving the unlicensed spectrum. The uniform planar array (UPA) is adopted from far-field to near-field, where the communication distance is decreasing from 21 m to 6 m (Rayleigh distance is about 14.8 m). Compared to the far-field, the spatial non-stationary phenomenon of channel parameters can be more clearly observed along the array in the near-field region. Then, we propose the extension channel model based on the channel modeling of 3GPP TR 38.901. The array domain is introduced to characterize the spatial non-stationarity of channel parameters (e.g., power, delay, angle). Subsequently, the channel characteristic parameters along the array are analyzed in the near-field range, and the non-stationary model related to the antenna array is established, including power, path loss, delay spread, angular spread, and Ricean K-factor. Finally, the model validation and parametrization are presented in detail with the actual indoor near-field MIMO channel measurements in the 6 GHz band, such as power, angle, and so on. The design and scheme of antenna array spacing are given under the influence of spatial non-stationary characteristics. These work will be helpful for the development and operation of MIMO technology in unlicensed spectra for wireless communication systems.","PeriodicalId":73294,"journal":{"name":"IEEE journal on selected areas in communications : a publication of the IEEE Communications Society","volume":"43 11","pages":"3889-3902"},"PeriodicalIF":17.2,"publicationDate":"2025-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144520660","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-06-18DOI: 10.1109/JSAC.2025.3576465
{"title":"IEEE Journal on Selected Areas in Communications Publication Information","authors":"","doi":"10.1109/JSAC.2025.3576465","DOIUrl":"https://doi.org/10.1109/JSAC.2025.3576465","url":null,"abstract":"","PeriodicalId":73294,"journal":{"name":"IEEE journal on selected areas in communications : a publication of the IEEE Communications Society","volume":"43 7","pages":"C2-C2"},"PeriodicalIF":0.0,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11039755","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144314798","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}
Pub Date : 2025-06-18DOI: 10.1109/JSAC.2025.3557932
Jun Chen;Alexandros G. Dimakis;Yong Fang;Ashish Khisti;Ayfer Özgür;Nir Shlezinger
{"title":"Guest Editorial: Rethinking the Information Identification, Representation, and Transmission Pipeline: New Approaches to Data Compression and Communication","authors":"Jun Chen;Alexandros G. Dimakis;Yong Fang;Ashish Khisti;Ayfer Özgür;Nir Shlezinger","doi":"10.1109/JSAC.2025.3557932","DOIUrl":"https://doi.org/10.1109/JSAC.2025.3557932","url":null,"abstract":"","PeriodicalId":73294,"journal":{"name":"IEEE journal on selected areas in communications : a publication of the IEEE Communications Society","volume":"43 7","pages":"2328-2332"},"PeriodicalIF":0.0,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11039751","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144314678","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}
Pub Date : 2025-06-18DOI: 10.1109/JSAC.2025.3576467
{"title":"IEEE Communications Society Information","authors":"","doi":"10.1109/JSAC.2025.3576467","DOIUrl":"10.1109/JSAC.2025.3576467","url":null,"abstract":"","PeriodicalId":73294,"journal":{"name":"IEEE journal on selected areas in communications : a publication of the IEEE Communications Society","volume":"43 7","pages":"C3-C3"},"PeriodicalIF":0.0,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11039750","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144319843","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}
Pub Date : 2025-06-10DOI: 10.1109/JSAC.2025.3574624
Dezhao Chen;Tongxin Huang;Jianghong Shi;Xuemin Hong;Yang Yang
The converging trends of reinforcement learning (RL) control and cloud-fog automation in industrial cyber-physical systems impose multiple challenges for communications to cope with stringent requirements in latency, reliability, control effectiveness and bifurcating user demands. Progressive goal-oriented (GO) communication is a promising technology to tackle the above challenges. This paper takes a two-step approach to design the first progressive codec of GO communications tailored for RL control tasks. The first step is to design a variable-rate coding scheme that extends the boundaries of rate regimes. This step is achieved by empowering the hierarchical variational autoencoder (HVAE) framework with novel algorithms such as mutual information based soft state abstraction (MISA). The second step is to transform variable-rate encoding into progressive encoding. This is achieved by applying residual-based encoding techniques upon latent representations learned by deep neural networks. Experiments on the Cartpole Swingup task demonstrate that the proposed progressive codec can facilitate smooth transitions from the ultra-low rate regime to regular rate regime, while achieving the state-of-the-art performance in terms of rate-distortion-effectiveness tradeoff.
{"title":"Progressive Goal-Oriented Communications for Reinforcement Learning Control Over Multi-Tier Computing Systems","authors":"Dezhao Chen;Tongxin Huang;Jianghong Shi;Xuemin Hong;Yang Yang","doi":"10.1109/JSAC.2025.3574624","DOIUrl":"10.1109/JSAC.2025.3574624","url":null,"abstract":"The converging trends of reinforcement learning (RL) control and cloud-fog automation in industrial cyber-physical systems impose multiple challenges for communications to cope with stringent requirements in latency, reliability, control effectiveness and bifurcating user demands. Progressive goal-oriented (GO) communication is a promising technology to tackle the above challenges. This paper takes a two-step approach to design the first progressive codec of GO communications tailored for RL control tasks. The first step is to design a variable-rate coding scheme that extends the boundaries of rate regimes. This step is achieved by empowering the hierarchical variational autoencoder (HVAE) framework with novel algorithms such as mutual information based soft state abstraction (MISA). The second step is to transform variable-rate encoding into progressive encoding. This is achieved by applying residual-based encoding techniques upon latent representations learned by deep neural networks. Experiments on the Cartpole Swingup task demonstrate that the proposed progressive codec can facilitate smooth transitions from the ultra-low rate regime to regular rate regime, while achieving the state-of-the-art performance in terms of rate-distortion-effectiveness tradeoff.","PeriodicalId":73294,"journal":{"name":"IEEE journal on selected areas in communications : a publication of the IEEE Communications Society","volume":"43 9","pages":"3056-3071"},"PeriodicalIF":17.2,"publicationDate":"2025-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144260013","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the era of smart cyber-physical grid, dynamic insecurity risk has become a significant concern due to the increasing integration of renewable energy sources and the inherent uncertainties in smart grid. Dynamic security assessment (DSA) has been adopted to hedge against such risks by estimating the stability of large-scale smart grids. Existing DSA approaches often involve complex high dimensional models which incur high communication and computational costs, hindering their practical adoption. In this paper, we address these limitations with the Quantum Federated Ensembled Variational Adaptive Learning (QFEVAL) approach for smart grid DSA. QFEVAL is designed to combine quantum machine learning and federated learning to handle the differential-algebraic equations that describe smart grid stability, providing an efficient way to deal with high-dimensional data and uncertainties. QFEVAL enables the training of the hybrid quantum-classical neural networks on distributed DSA datasets located at different nodes in smart grids, without requiring large numbers of parameters to be transmitted. QFEVAL accurately predicts the stability of the smart grid under various conditions, enabling the implementation of preventive stability control measures. Through extensive experiments, we demonstrate that QFEVAL achieves comparable performance to 9 state-of-the-art DSA approaches with more than 2 orders of magnitude fewer model parameter transmissions. QFEVAL paves the way for reliable, secure, and continuous electricity supply, offering a robust solution to the challenges of DSA in smart grids.
{"title":"QFEVAL: Quantum Federated Ensembled Variational Adaptive Learning for Dynamic Security Assessment in Cyber-Physical Systems","authors":"Chao Ren;Ying-Peng Tang;Yulan Gao;Xian Sun;Kun Fu;Mikael Skoglund;Zhao Yang Dong;Han Yu;Anran Li;Ming Xiao","doi":"10.1109/JSAC.2025.3574588","DOIUrl":"10.1109/JSAC.2025.3574588","url":null,"abstract":"In the era of smart cyber-physical grid, dynamic insecurity risk has become a significant concern due to the increasing integration of renewable energy sources and the inherent uncertainties in smart grid. Dynamic security assessment (DSA) has been adopted to hedge against such risks by estimating the stability of large-scale smart grids. Existing DSA approaches often involve complex high dimensional models which incur high communication and computational costs, hindering their practical adoption. In this paper, we address these limitations with the <underline>Q</u>uantum <underline>F</u>ederated <underline>E</u>nsembled <underline>V</u>ariational <underline>A</u>daptive <underline>L</u>earning (QFEVAL) approach for smart grid DSA. QFEVAL is designed to combine quantum machine learning and federated learning to handle the differential-algebraic equations that describe smart grid stability, providing an efficient way to deal with high-dimensional data and uncertainties. QFEVAL enables the training of the hybrid quantum-classical neural networks on distributed DSA datasets located at different nodes in smart grids, without requiring large numbers of parameters to be transmitted. QFEVAL accurately predicts the stability of the smart grid under various conditions, enabling the implementation of preventive stability control measures. Through extensive experiments, we demonstrate that QFEVAL achieves comparable performance to 9 state-of-the-art DSA approaches with more than 2 orders of magnitude fewer model parameter transmissions. QFEVAL paves the way for reliable, secure, and continuous electricity supply, offering a robust solution to the challenges of DSA in smart grids.","PeriodicalId":73294,"journal":{"name":"IEEE journal on selected areas in communications : a publication of the IEEE Communications Society","volume":"43 9","pages":"3200-3213"},"PeriodicalIF":17.2,"publicationDate":"2025-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144260093","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-06-06DOI: 10.1109/JSAC.2025.3577249
Jian Wang;Chunxi Li;Yongxiang Zhao;Zonghui Li
With the rapid growth of Industry 4.0, time-sensitive networking (TSN) has emerged as the new infrastructure for future industrial Internet of Things (IoT) communication. Ensuring the compatibility between TSN and legacy networks is inevitable. The ideal compatibility is to achieve deterministic interconnection and interoperability without changes in hardware and communication protocols, in other words, only using standard devices with software management. This paper targets the ideal compatibility of TSN and Profinet Isochronous Real Time (IRT). First, we propose an inter-domain multiple transmission opportunity mechanism (MTOM) to enable the asynchronous converged network of TSN and Profinet. The mechanism reserves multiple transmission time slots for cross-domain data flows to reduce their end-to-end delay and jitter. Second, we formulate an asynchronous scheduling model (ASM) based on MTOM to co-schedule flows in inter-and-intra domains. Finally, a case study is performed on a typical industrial network. The experiment results demonstrate that the proposed MTOM can only use standard devices to achieve deterministic transmission of Profinet and TSN converged networks. Compared with previous asynchronous converged networks, the delay and jitter are reduced by 86% and 80% on average, respectively.
{"title":"Deterministic Transmission for the Asynchronous Converged Networks of Profinet and TSN","authors":"Jian Wang;Chunxi Li;Yongxiang Zhao;Zonghui Li","doi":"10.1109/JSAC.2025.3577249","DOIUrl":"10.1109/JSAC.2025.3577249","url":null,"abstract":"With the rapid growth of Industry 4.0, time-sensitive networking (TSN) has emerged as the new infrastructure for future industrial Internet of Things (IoT) communication. Ensuring the compatibility between TSN and legacy networks is inevitable. The ideal compatibility is to achieve deterministic interconnection and interoperability without changes in hardware and communication protocols, in other words, only using standard devices with software management. This paper targets the ideal compatibility of TSN and Profinet Isochronous Real Time (IRT). First, we propose an inter-domain multiple transmission opportunity mechanism (MTOM) to enable the asynchronous converged network of TSN and Profinet. The mechanism reserves multiple transmission time slots for cross-domain data flows to reduce their end-to-end delay and jitter. Second, we formulate an asynchronous scheduling model (ASM) based on MTOM to co-schedule flows in inter-and-intra domains. Finally, a case study is performed on a typical industrial network. The experiment results demonstrate that the proposed MTOM can only use standard devices to achieve deterministic transmission of Profinet and TSN converged networks. Compared with previous asynchronous converged networks, the delay and jitter are reduced by 86% and 80% on average, respectively.","PeriodicalId":73294,"journal":{"name":"IEEE journal on selected areas in communications : a publication of the IEEE Communications Society","volume":"43 9","pages":"3014-3023"},"PeriodicalIF":17.2,"publicationDate":"2025-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144237188","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-06-03DOI: 10.1109/JSAC.2025.3574590
Ignas Laurinavicius;Huiling Zhu;Yijin Pan;Changrun Chen;Jiangzhou Wang
As an evolution of cloud radio access network (C-RAN), fog radio access network (F-RAN) becomes promising for future mobile communications by enabling processing and caching at fog access points (FAPs). Different from the centralised C-RAN, F-RAN has a semi-distributed architecture, aiming to alleviate traffic load on the fronthaul links in C-RAN. Under the semi-distributed architecture in F-RAN, which employs a cell-free multiple input multiple output (MIMO) access technique, decisions on the joint user-FAP association and transmit power allocation are made at individual FAPs. To mitigate strong interference, FAPs will need to exchange cooperative status information, such as CSI, user association details or transmission power levels. However, this can lead to significant communication overhead within the network and introduce high complexity in the decision-making process. In this paper, accounting for the semi-distributed nature of the F-RAN architecture, reinforcement learning is leveraged as a potential solution to this kind of problem, and a novel multi-agent dual deep Q-network (MA-DDQN) algorithm is proposed by introducing experience exchange in partially observable Markov decision process environments. The simulation results show that the proposed reinforcement learning based algorithm outperforms the DDQN algorithm as well as the existing low-complexity algorithms.
{"title":"Novel Deep Reinforcement Learning for User Association in Fog Radio Access Networks","authors":"Ignas Laurinavicius;Huiling Zhu;Yijin Pan;Changrun Chen;Jiangzhou Wang","doi":"10.1109/JSAC.2025.3574590","DOIUrl":"10.1109/JSAC.2025.3574590","url":null,"abstract":"As an evolution of cloud radio access network (C-RAN), fog radio access network (F-RAN) becomes promising for future mobile communications by enabling processing and caching at fog access points (FAPs). Different from the centralised C-RAN, F-RAN has a semi-distributed architecture, aiming to alleviate traffic load on the fronthaul links in C-RAN. Under the semi-distributed architecture in F-RAN, which employs a cell-free multiple input multiple output (MIMO) access technique, decisions on the joint user-FAP association and transmit power allocation are made at individual FAPs. To mitigate strong interference, FAPs will need to exchange cooperative status information, such as CSI, user association details or transmission power levels. However, this can lead to significant communication overhead within the network and introduce high complexity in the decision-making process. In this paper, accounting for the semi-distributed nature of the F-RAN architecture, reinforcement learning is leveraged as a potential solution to this kind of problem, and a novel multi-agent dual deep Q-network (MA-DDQN) algorithm is proposed by introducing experience exchange in partially observable Markov decision process environments. The simulation results show that the proposed reinforcement learning based algorithm outperforms the DDQN algorithm as well as the existing low-complexity algorithms.","PeriodicalId":73294,"journal":{"name":"IEEE journal on selected areas in communications : a publication of the IEEE Communications Society","volume":"43 9","pages":"3024-3040"},"PeriodicalIF":17.2,"publicationDate":"2025-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144210861","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Accurate estimation and detection, along with phase shift optimization, are vital for implementing reconfigurable intelligent surface (RIS)-enabled multi-antenna systems in highly disruptive industrial IoT environments. Motivated by the remarkable capabilities of deep learning (DL) techniques, this paper introduces a pioneering approach to address challenges in channel estimation, channel correlation prediction, and symbol detection for industrial IoT. We develop an optimization framework for large-scale IoT deployments to maximize the signal-to-interference-plus-noise ratio (SINR) while minimizing transmit power. We also propose a transformer-based channel correlation predictor for IoT devices, which enables adaptive pilot retransmissions and reduces training overhead through a co-design approach that integrates communication, computation, and control. Extensive simulations under realistic, time-varying industrial IoT channel conditions demonstrate the superiority of our DL-driven approach, achieving significant improvements in detection accuracy and SINR.
{"title":"Deep Learning-Enabled RIS Massive MIMO Systems for Industrial IoT: A Joint Communication and Computation Approach","authors":"Wei Xiang;Muhammad Umer Zia;Jameel Ahmad;Peng Cheng;Kan Yu;Tao Huang","doi":"10.1109/JSAC.2025.3574603","DOIUrl":"10.1109/JSAC.2025.3574603","url":null,"abstract":"Accurate estimation and detection, along with phase shift optimization, are vital for implementing reconfigurable intelligent surface (RIS)-enabled multi-antenna systems in highly disruptive industrial IoT environments. Motivated by the remarkable capabilities of deep learning (DL) techniques, this paper introduces a pioneering approach to address challenges in channel estimation, channel correlation prediction, and symbol detection for industrial IoT. We develop an optimization framework for large-scale IoT deployments to maximize the signal-to-interference-plus-noise ratio (SINR) while minimizing transmit power. We also propose a transformer-based channel correlation predictor for IoT devices, which enables adaptive pilot retransmissions and reduces training overhead through a co-design approach that integrates communication, computation, and control. Extensive simulations under realistic, time-varying industrial IoT channel conditions demonstrate the superiority of our DL-driven approach, achieving significant improvements in detection accuracy and SINR.","PeriodicalId":73294,"journal":{"name":"IEEE journal on selected areas in communications : a publication of the IEEE Communications Society","volume":"43 9","pages":"2981-2996"},"PeriodicalIF":17.2,"publicationDate":"2025-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144201844","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Federated learning (FL) model marketplaces require qualified workers to collaboratively train customized models. However, recruiting optimal workers on a limited budget in non-independent and identically distributed (non-IID) data settings remains a fundamental issue. Moreover, inadequate quality verification exposes the marketplace to spoofing and poisoning attacks, while verifying data and model quality without accessing local storage remains a significant dilemma. To bridge the research gap, this paper proposes a knowledge-aware model customization scheme in FL model marketplaces, to facilitate zero-trust worker recruitment and verification while ensuring privacy preservation. Specifically, (i) we design a knowledge-aware quality evaluation mechanism by leveraging the knowledge of workers, i.e., soft-label predictions of their local models on a privacy-free reference dataset (provided by the customer), to assess their data quality in a privacy-preserving manner. (ii) We formulate the optimal worker recruitment problem under budget constraints as an NP-hard integer programming problem and design a dynamic programming-based optimal worker recruitment algorithm with budget feasibility and computational efficiency. (iii) We devise a two-stage zero-trust quality verification mechanism by utilizing zero-knowledge proof (ZKP) to exclude distrustful workers, thereby preventing spoofing and poisoning attacks. Extensive experimental results demonstrate that the proposed scheme enhances model customization performance by up to 34.3% on label-skewed non-IID data and 36.2% on feature-skewed non-IID data compared with existing representatives.
{"title":"Knowledge-Aware Privacy-Preserving Model Customization in Zero-Trust Federated Learning Model Marketplaces","authors":"Yanghe Pan;Zhou Su;Yuntao Wang;Han Liu;Ruidong Li;Abderrahim Benslimane","doi":"10.1109/JSAC.2025.3560010","DOIUrl":"10.1109/JSAC.2025.3560010","url":null,"abstract":"Federated learning (FL) model marketplaces require qualified workers to collaboratively train customized models. However, recruiting optimal workers on a limited budget in non-independent and identically distributed (non-IID) data settings remains a fundamental issue. Moreover, inadequate quality verification exposes the marketplace to spoofing and poisoning attacks, while verifying data and model quality without accessing local storage remains a significant dilemma. To bridge the research gap, this paper proposes a knowledge-aware model customization scheme in FL model marketplaces, to facilitate zero-trust worker recruitment and verification while ensuring privacy preservation. Specifically, (i) we design a knowledge-aware quality evaluation mechanism by leveraging the knowledge of workers, i.e., soft-label predictions of their local models on a privacy-free reference dataset (provided by the customer), to assess their data quality in a privacy-preserving manner. (ii) We formulate the optimal worker recruitment problem under budget constraints as an NP-hard integer programming problem and design a dynamic programming-based optimal worker recruitment algorithm with budget feasibility and computational efficiency. (iii) We devise a two-stage zero-trust quality verification mechanism by utilizing zero-knowledge proof (ZKP) to exclude distrustful workers, thereby preventing spoofing and poisoning attacks. Extensive experimental results demonstrate that the proposed scheme enhances model customization performance by up to 34.3% on label-skewed non-IID data and 36.2% on feature-skewed non-IID data compared with existing representatives.","PeriodicalId":73294,"journal":{"name":"IEEE journal on selected areas in communications : a publication of the IEEE Communications Society","volume":"43 6","pages":"1923-1937"},"PeriodicalIF":0.0,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143884481","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：