IEEE Transactions on Mobile Computing最新文献_第10页

DI2SDiff++: Activity Style Decomposition and Diffusion-Based Fusion for Cross-Person Generalization in Activity Recognition DI2SDiff++：活动识别中跨人泛化的活动风格分解和基于扩散的融合

IF 9.2 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2025-03-21 DOI: 10.1109/TMC.2025.3572220

Junru Zhang;Cheng Peng;Zhidan Liu;Lang Feng;Yuhan Wu;Yabo Dong;Duanqing Xu

{"title":"DI2SDiff++: Activity Style Decomposition and Diffusion-Based Fusion for Cross-Person Generalization in Activity Recognition","authors":"Junru Zhang;Cheng Peng;Zhidan Liu;Lang Feng;Yuhan Wu;Yabo Dong;Duanqing Xu","doi":"10.1109/TMC.2025.3572220","DOIUrl":"https://doi.org/10.1109/TMC.2025.3572220","url":null,"abstract":"Existing domain generalization (DG) methods for cross-person sensor-based activity recognition tasks often struggle to capture both intra- and inter-domain style diversity, leading to significant domain gaps with the target domain. In this study, we explore a novel perspective to tackle this problem, a process conceptualized as domain padding. This proposal aims to enrich the domain diversity by synthesizing intra- and inter-domain style data while maintaining robustness to class labels. We instantiate this concept using a conditional diffusion model and introduce a style-fused sampling strategy to enhance data generation diversity, termed Diversified Intra- and Inter-domain distributions via activity Style-fused Diffusion modeling (DI2SDiff). In contrast to traditional condition-guided sampling, our style-fused sampling strategy allows for the flexible use of one or more random style representations from the same class to guide data synthesis. This feature presents a notable advancement: it allows for the maximum utilization of possible combinations among existing styles to generate a broad spectrum of new style instances. We further extend DI2SDiff into DI2SDiff++ by enhancing the diversity of style guidance. Specifically, DI2SDiff++ integrates a multi-head style conditioner to provide multiple distinct, decomposed substyles and introduces a substyle-fused sampling strategy that allows cross-class substyle fusion for broader guidance. Empirical evaluations on a wide range of datasets demonstrate that our generated data achieves remarkable diversity within the domain space. Both intra- and inter-domain generated data have been proven significant and valuable, enabling DI2SDiff and DI2SDiff++ to surpass state-of-the-art DG methods in various cross-person activity recognition tasks.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 10","pages":"10760-10777"},"PeriodicalIF":9.2,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145036222","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

FDLoRa: Scaling Downlink Concurrent Transmissions With Full-Duplex LoRa Gateways FDLoRa：用全双工LoRa网关扩展下行并发传输

IF 9.2 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2025-03-21 DOI: 10.1109/TMC.2025.3572130

Shiming Yu;Xianjin Xia;Ziyue Zhang;Ningning Hou;Yuanqing Zheng

{"title":"FDLoRa: Scaling Downlink Concurrent Transmissions With Full-Duplex LoRa Gateways","authors":"Shiming Yu;Xianjin Xia;Ziyue Zhang;Ningning Hou;Yuanqing Zheng","doi":"10.1109/TMC.2025.3572130","DOIUrl":"https://doi.org/10.1109/TMC.2025.3572130","url":null,"abstract":"Unlike traditional data collection applications which primarily rely on uplink transmissions, emerging applications (e.g., device actuation, firmware update, packet reception acknowledgment) increasingly demand robust downlink transmission capabilities. Current LoRaWAN systems struggle to support these applications due to the inherent asymmetry between downlink and uplink capabilities. While uplink transmissions can handle multiple packets simultaneously, downlink transmissions are restricted to a single logical channel at a time, significantly limiting the deployment of applications that require substantial downlink capacity. To address this challenge, <italic>FDLoRa introduces an innovative in-band full-duplex LoRa gateway design, featuring novel solutions to mitigate self-interference (i.e., the strong downlink interference to ultra-weak uplink reception). This approach enables full-spectrum in-band downlink transmissions without compromising the reception of weak uplink packets. Building on the capabilities of full-duplex gateways, <italic>FDLoRa presents a new downlink framework that supports concurrent downlink transmissions across multiple logical channels of available gateways. Evaluation results show that <italic>FDLoRa enhances downlink capacity by 5.7× compared to LoRaWAN in a three-gateway testbed and achieves 2.58× higher downlink concurrency per gateway than the current leading solutions.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 10","pages":"10668-10682"},"PeriodicalIF":9.2,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145036819","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Vehicular Edge Intelligence: DRL-Based Resource Orchestration for Task Inference in Vehicle-RSU-Edge Collaborative Networks 车辆边缘智能：基于drl的车辆- rsu -边缘协同网络任务推理资源编排

IF 9.2 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2025-03-21 DOI: 10.1109/TMC.2025.3572296

Wenhao Fan;Yang Yu;Chenhui Bao;Yuan’an Liu

{"title":"Vehicular Edge Intelligence: DRL-Based Resource Orchestration for Task Inference in Vehicle-RSU-Edge Collaborative Networks","authors":"Wenhao Fan;Yang Yu;Chenhui Bao;Yuan’an Liu","doi":"10.1109/TMC.2025.3572296","DOIUrl":"https://doi.org/10.1109/TMC.2025.3572296","url":null,"abstract":"Vehicular edge intelligence, distinct from traditional edge intelligence, exhibits unique characteristics, including the mobility of vehicles, uneven spatial and temporal distribution of vehicles, and variability in the AI models deployed on vehicles, Roadside Units (RSUs), and edge servers (ESs). In this paper, we propose a Deep Reinforcement Learning (DRL)-based resource orchestration scheme for task inference in vehicle-RSU-edge collaborative networks. In our approach, vehicles’ inference tasks can be processed on the vehicles, RSUs, or ESs, encompassing a total of 9 possible scenarios based on the cross-RSU mobility of vehicles. The scheme jointly optimizes task processing decision-making, transmission power allocation, computational resource allocation, and transmission rate allocation. The objective is to minimize the total cost, which involves a trade-off between task processing latency, energy consumption and inference error rate across all vehicle tasks. We design a DRL algorithm that decomposes the original optimization problem into sub-problems and efficiently solves them by combining the Softmax Deep Double Deterministic Policy Gradients (SD3) algorithm with multiple numerical methods. We analyzed the complexity and convergence of the algorithm. Specifically, we demonstrated its low complexity and fast, stable convergence, which prove its effectiveness in solving the problem. And we demonstrate the superiority of our scheme by comparing it with 5 benchmark schemes across 6 different scenarios.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 10","pages":"10927-10944"},"PeriodicalIF":9.2,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145021224","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

You Can Wash Hands Better: Accurate Daily Handwashing Assessment With a Smartwatch 你可以更好地洗手：使用智能手表进行准确的每日洗手评估

IF 9.2 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2025-03-20 DOI: 10.1109/TMC.2025.3571805

Fei Wang;Tingting Zhang;Xilei Wu;Pengcheng Wang;Xin Wang;Han Ding;Jingang Shi;Jinsong Han;Dong Huang

{"title":"You Can Wash Hands Better: Accurate Daily Handwashing Assessment With a Smartwatch","authors":"Fei Wang;Tingting Zhang;Xilei Wu;Pengcheng Wang;Xin Wang;Han Ding;Jingang Shi;Jinsong Han;Dong Huang","doi":"10.1109/TMC.2025.3571805","DOIUrl":"https://doi.org/10.1109/TMC.2025.3571805","url":null,"abstract":"Hand hygiene is among the most effective daily practices for preventing infectious diseases such as influenza, malaria, and skin infections. While professional guidelines emphasize proper handwashing to reduce the risk of viral infections, surveys reveal that adherence to these recommendations remains low. To address this gap, we propose UWash, a wearable solution leveraging smartwatches to evaluate handwashing procedures, aiming to raise awareness and cultivate high-quality handwashing habits. We frame the task of handwashing assessment as an action segmentation problem, similar to those in computer vision, and introduce a simple yet efficient two-stream UNet-like network to achieve this goal. Experiments involving 51 subjects demonstrate that UWash achieves 92.27% accuracy in handwashing gesture recognition, an error of <inline-formula><tex-math>$< $</tex-math></inline-formula>0.5 seconds in onset/offset detection, and an error of <inline-formula><tex-math>$< $</tex-math></inline-formula>5 points in gesture scoring under user-dependent settings. The system also performs robustly in user-independent and user-independent-location-independent evaluations. Remarkably, UWash maintains high performance in real-world tests, including evaluations with 10 random passersby at a hospital 9 months later and 10 passersby in an in-the-wild test conducted 2 years later. UWash is the first system to score handwashing quality based on gesture sequences, offering actionable guidance for improving daily hand hygiene.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 10","pages":"10900-10913"},"PeriodicalIF":9.2,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145027967","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Maximizing Service Provider’s Profit in Multi-UAV 5G Network Via Deep Reinforcement Learning and Graph Coloring 基于深度强化学习和图着色的多无人机5G网络中服务提供商利润最大化

IF 9.2 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2025-03-20 DOI: 10.1109/TMC.2025.3571804

Shilpi Kumari;Ajay Pratap

{"title":"Maximizing Service Provider’s Profit in Multi-UAV 5G Network Via Deep Reinforcement Learning and Graph Coloring","authors":"Shilpi Kumari;Ajay Pratap","doi":"10.1109/TMC.2025.3571804","DOIUrl":"https://doi.org/10.1109/TMC.2025.3571804","url":null,"abstract":"The current 5G network is expected to have a densely populated architecture comprising radio-enabled Service Provider (SP) and heterogeneous User Equipment (UE). Addressing the real-time service demands of UEs with strict deadlines is a critical challenge. Uncrewed Aerial Vehicle (UAV) assisted service provisioning is emerging as an efficient solution for timely service transfers. Therefore, SPs are interested in offering UAV-assisted service transmission to get profited by deploying UAVs. However, this introduces challenges like optimizing the locations of UAVs and Power Level (PL) along with interference management within limited available radio resources. Hence, we proposed a novel framework for multi-UAV-assisted service provisioning, consisting of Base Station (BS), UAVs, and heterogeneous UEs in 5G network. We formulate the SP’s profit maximization problem, optimizing UAVs’ location, PL, and resource allocation while considering service latency, interference management, and UAVs’ energy constraints collectively as an optimization problem. Furthermore, we propose a semi-centralized sub-optimal solution utilizing Multi-agent Deep Reinforcement Learning (MaDRL) and a Graph Coloring-based approach. Extensive simulation analysis demonstrates the proposed algorithm’s effectiveness, achieving an average of 99.05% profit compared to the optimal value.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 10","pages":"10377-10388"},"PeriodicalIF":9.2,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145021427","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

PACIFISTA: Conflict Evaluation and Management in Open RAN pacificsta：开放式RAN中的冲突评估与管理

IF 9.2 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2025-03-20 DOI: 10.1109/TMC.2025.3570632

Pietro Brach del Prever;Salvatore D’Oro;Leonardo Bonati;Michele Polese;Maria Tsampazi;Heiko Lehmann;Tommaso Melodia

{"title":"PACIFISTA: Conflict Evaluation and Management in Open RAN","authors":"Pietro Brach del Prever;Salvatore D’Oro;Leonardo Bonati;Michele Polese;Maria Tsampazi;Heiko Lehmann;Tommaso Melodia","doi":"10.1109/TMC.2025.3570632","DOIUrl":"https://doi.org/10.1109/TMC.2025.3570632","url":null,"abstract":"The O-RAN ALLIANCE is defining architectures, interfaces, operations, and security requirements for cellular networks based on Open Radio Access Network (RAN) principles. In this context, O-RAN introduced the RAN Intelligent Controllers (RICs) to enable dynamic control of cellular networks via data-driven applications referred to as rApps and xApps. RICs enable for the first time truly intelligent and self-organizing cellular networks. However, enabling the execution of many Artificial Intelligence (AI) algorithms making autonomous control decisions to fulfill diverse (and possibly conflicting) goals poses unprecedented challenges. For instance, the execution of one xApp aiming at maximizing throughput and one aiming at minimizing energy consumption would inevitably result in diametrically opposed resource allocation strategies. Therefore, conflict management becomes a crucial component of any functional intelligent O-RAN system. This article studies the problem of conflict mitigation in O-RAN and proposes PACIFISTA, a framework to detect, characterize, and mitigate conflicts generated by O-RAN applications that control RAN parameters. PACIFISTA leverages a profiling pipeline to tests O-RAN applications in a sandbox environment, and combines hierarchical graphs with statistical models to detect the existence of conflicts and evaluate their severity. Experiments on Colosseum and OpenRAN Gym demonstrate PACIFISTA’s ability to predict conflicts and provide valuable information before potentially conflicting xApps are deployed in production systems. We use PACIFISTA to demonstrate that users can experience a 16% throughput loss even in the case of xApps with similar goals, and that applications with conflicting goals might cause severe instability and result in up to 30% performance degradation. We also show that PACIFISTA can help operators to identify conflicting applications and maintain performance degradation below a tolerable threshold.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 10","pages":"10590-10605"},"PeriodicalIF":9.2,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145036755","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Distributionally Robust Optimization for Aerial Multi-Access Edge Computing via Cooperation of UAVs and HAPs 基于无人机和HAPs协同的空中多址边缘计算分布鲁棒优化

IF 9.2 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2025-03-19 DOI: 10.1109/TMC.2025.3571023

Ziye Jia;Can Cui;Chao Dong;Qihui Wu;Zhuang Ling;Dusit Niyato;Zhu Han

{"title":"Distributionally Robust Optimization for Aerial Multi-Access Edge Computing via Cooperation of UAVs and HAPs","authors":"Ziye Jia;Can Cui;Chao Dong;Qihui Wu;Zhuang Ling;Dusit Niyato;Zhu Han","doi":"10.1109/TMC.2025.3571023","DOIUrl":"https://doi.org/10.1109/TMC.2025.3571023","url":null,"abstract":"With an extensive increment of computation demands, the aerial multi-access edge computing (MEC), mainly based on uncrewed aerial vehicles (UAVs) and high altitude platforms (HAPs), plays significant roles in future network scenarios. In detail, UAVs can be flexibly deployed, while HAPs are characterized with large capacity and stability. Hence, in this paper, we provide a hierarchical model composed of an HAP and multi-UAVs, to provide aerial MEC services. Moreover, considering the errors of channel state information from unpredictable environmental conditions, we formulate the problem to minimize the total energy cost with the chance constraint, which is a mixed-integer nonlinear problem with uncertain parameters and intractable to solve. To tackle this issue, we optimize the UAV deployment via the weighted K-means algorithm. Then, the chance constraint is reformulated via the distributionally robust optimization (DRO). Furthermore, based on the conditional value-at-risk mechanism, we transform the DRO problem into a mixed-integer second order cone programming, which is further decomposed into two subproblems via the primal decomposition. Moreover, to alleviate the complexity of the binary subproblem, we design a binary whale optimization algorithm. Finally, we conduct extensive simulations to verify the effectiveness and robustness of the proposed schemes by comparing with baseline mechanisms.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 10","pages":"10853-10867"},"PeriodicalIF":9.2,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145036774","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fast Robustness Enhancement for Dynamic IIoT Topology With Adaptive Bayesian Learning 基于自适应贝叶斯学习的动态工业物联网拓扑快速鲁棒性增强

IF 9.2 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2025-03-19 DOI: 10.1109/TMC.2025.3571431

Ning Chen;Songwei Zhang;Xiaobo Zhou;Song Cao;Tie Qiu

{"title":"Fast Robustness Enhancement for Dynamic IIoT Topology With Adaptive Bayesian Learning","authors":"Ning Chen;Songwei Zhang;Xiaobo Zhou;Song Cao;Tie Qiu","doi":"10.1109/TMC.2025.3571431","DOIUrl":"https://doi.org/10.1109/TMC.2025.3571431","url":null,"abstract":"In resource-constrained and dynamic Industrial Internet of Things (IIoT) environments, ensuring robust and adaptable network topologies remains a significant challenge. Existing reinforcement learning-based approaches tackle topology optimization but face scalability issues due to high computational complexity and latency under strict time constraints. To address these challenges, we propose FRED-ABL (<italic>Fast Robustness Enhancement for Dynamic IIoT topology optimization with Adaptive Bayesian Learning), a novel paradigm that delivers lightweight topology solutions within a constrained time frame. FRED-ABL introduces an innovative topology structure compression method leveraging auxiliary continuous coding, enabling lossless representation of network structures as model inputs. It further defines a new robustness performance metric that integrates considerations of node failures and connection capabilities, serving as a comprehensive evaluation function. By developing an adaptive Bayesian learning model, FRED-ABL efficiently maps the relationship between topology structures and robustness metrics, enabling rapid optimization while significantly reducing computational overhead. Extensive experiments demonstrate that FRED-ABL consistently outperforms state-of-the-art methods, delivering superior robustness and optimization efficiency even in large-scale IIoT deployments.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 10","pages":"10886-10899"},"PeriodicalIF":9.2,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145027952","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

CSIPose: Unveiling Human Poses Using Commodity WiFi Devices Through the Wall CSIPose：揭开人类姿势使用商品WiFi设备穿墙

IF 9.2 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2025-03-19 DOI: 10.1109/TMC.2025.3571469

Yangyang Gu;Jing Chen;Congrui Chen;Kun He;Ju Jia;Yebo Feng;Ruiying Du;Cong Wu

{"title":"CSIPose: Unveiling Human Poses Using Commodity WiFi Devices Through the Wall","authors":"Yangyang Gu;Jing Chen;Congrui Chen;Kun He;Ju Jia;Yebo Feng;Ruiying Du;Cong Wu","doi":"10.1109/TMC.2025.3571469","DOIUrl":"https://doi.org/10.1109/TMC.2025.3571469","url":null,"abstract":"The popularity of WiFi devices and the development of WiFi sensing have alerted people to the threat of WiFi sensing-based privacy leakage, especially the privacy of human poses. Existing work on human pose estimation is deployed in indoor scenarios or simple occlusion (e.g., a wooden screen) scenarios, which are less privacy-threatening in attack scenarios. To reveal the risk of leakage of the pose privacy to users from commodity WiFi devices, we propose CSIPose, a privacy-acquisition attack that passively estimates dynamic and static human poses in through-the-wall scenarios. We design a three-branch network based on transfer learning, auto-encoder, and self-attention mechanisms to realize the supervision of video frames over CSI frames to generate human pose skeleton frames. Notably, we design <italic>AveCSI, a unified framework for preprocessing and feature extraction of CSI data corresponding to dynamic and static poses. This framework uses the average of CSI measurements to generate CSI frames to mitigate the instability of passively collected CSI data, and utilizes a self-attention mechanism to enhance key features. We evaluate the performance of CSIPose across different room layouts, subjects, devices, subject locations, and device locations. Evaluation results emphasize the generalizability of CSIPose. Finally, we discuss measures to mitigate this attack.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 10","pages":"10914-10926"},"PeriodicalIF":9.2,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145021338","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Reads: A Personalized Federated Learning Framework With Fine-Grained Layer Aggregation and Decentralized Clustering 阅读：具有细粒度层聚合和分散聚类的个性化联邦学习框架

IF 7.7 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2025-03-19 DOI: 10.1109/TMC.2025.3552982

Haoyu Fu;Fengsen Tian;Guoqiang Deng;Lingyu Liang;Xinglin Zhang

{"title":"Reads: A Personalized Federated Learning Framework With Fine-Grained Layer Aggregation and Decentralized Clustering","authors":"Haoyu Fu;Fengsen Tian;Guoqiang Deng;Lingyu Liang;Xinglin Zhang","doi":"10.1109/TMC.2025.3552982","DOIUrl":"https://doi.org/10.1109/TMC.2025.3552982","url":null,"abstract":"The heterogeneity of local data and client performance, along with real-world system risks, is driving the evolution of federated learning (FL) towards personalized, model-heterogeneous, and decentralized approaches. However, due to the differing structures of heterogeneous models, it is hard to use them to identify clients with similar data distributions and further enhance the personalization of local models. Therefore, how to deal with data heterogeneity to obtain superior personalized local models for clients, while simultaneously addressing model heterogeneity and system risks is a challenging problem. In this paper, we propose a novel personalized FL framework with fine-gRained layEr aggregAtion and Decentralized cluStering (<inline-formula><tex-math>${sf Reads}$</tex-math></inline-formula>), which integrates four key components: (1) deep mutual learning with privacy guarantee for model training and privacy preservation, (2) fine-grained layer similarity computation among heterogeneous model layers, (3) fully decentralized clustering for soft clustering of clients based on layer similarities, and (4) personalized layer aggregation for capturing common knowledge from other clients. Through <inline-formula><tex-math>${sf Reads}$</tex-math></inline-formula>, clients obtain personalized models that accommodate model heterogeneity, while the system ensures robustness against a single point of failure. Extensive experiments demonstrate the efficacy of <inline-formula><tex-math>${sf Reads}$</tex-math></inline-formula> in achieving these goals.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 8","pages":"7709-7725"},"PeriodicalIF":7.7,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144550754","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0