IEEE Transactions on Network Science and Engineering最新文献_第10页

OD Traffic Maps Recovery for Web 3.0 by Network Tomography in Hankel Tensor Space 基于Hankel张量空间的网络层析恢复Web 3.0 OD流量图

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-02-25 DOI: 10.1109/TNSE.2025.3542603

Chao Wang;Jiuzhen Zeng;Laurence T. Yang;Xiangli Yang;Xianjun Deng;Hao Wang

{"title":"OD Traffic Maps Recovery for Web 3.0 by Network Tomography in Hankel Tensor Space","authors":"Chao Wang;Jiuzhen Zeng;Laurence T. Yang;Xiangli Yang;Xianjun Deng;Hao Wang","doi":"10.1109/TNSE.2025.3542603","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3542603","url":null,"abstract":"In the emerging Web 3.0, origin-destination (OD) traffic maps play a crucial role in network maintenance and management. However, increasing network size and complexity, as well as insufficient or invalid NetFlow protocol-based measurements pose numerous challenges to recovering traffic maps for Web 3.0. This paper therefore proposes RNT-HTT, a robust Network Tomography model based on Hankel time-structured tensor, to accurately recover OD traffic maps with link loads and a fraction of NetFlow counts in Hankel tensor space. More specifically, we propose to Hankelize both OD traffic and link load matrices to three-way tensors along time direction, which fully exploits time-structured correlations concealed in network data. OD pairs-mode product is also designed to model the relation between the Hankelized OD traffic and link load tensors. On the basis of these, RNT-HTT formulates the recovery problem as a convex optimization program with tensor nuclear and <inline-formula><tex-math>${{ell }_{1}}$</tex-math></inline-formula>-norms to respectively effect traffic low-rank and noise sparsity characteristics. In addition, the block-iteration alternating direction method of multipliers (ADMM) and bidirectional pre-sampling schemes are developed to solve RNT-HTT reliably and efficiently. Extensive experiments on three real-world datasets verify effectiveness of RNT-HTT, and corroborate its superior performance over state-of-the-art methods in terms of the recovery accuracy.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 3","pages":"1981-1993"},"PeriodicalIF":6.7,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143871014","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

Knowledge Efficient Federated Continual Learning for Industrial Edge Systems 面向工业边缘系统的知识高效联邦持续学习

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-02-24 DOI: 10.1109/TNSE.2025.3544614

Jiao Chen;Jiayi He;Jianhua Tang;Weihua Li;Zihang Yin

{"title":"Knowledge Efficient Federated Continual Learning for Industrial Edge Systems","authors":"Jiao Chen;Jiayi He;Jianhua Tang;Weihua Li;Zihang Yin","doi":"10.1109/TNSE.2025.3544614","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3544614","url":null,"abstract":"Recent advances in federated learning (FL) primarily focus on addressing inter-client data heterogeneity, implicitly assuming static data within each client. However, this assumption is inadequate for industrial edge systems (IES), which operate in dynamically changing environments and require real-time processing and analysis of voluminous time-series data generated by the Internet of Things. To bridge this gap, we propose MeCo, a novel federated continual learning (FCL) method for IES, designed to avoid forgetting past knowledge while continuously adapting to new task data. MeCo distinguishes itself from traditional FL by effectively addressing both inter-client and intra-client data heterogeneity through a knowledge-efficient strategy. Specifically, it includes: <italic>Meta task-invariant knowledge consolidation, which helps capture shared features across tasks to alleviate forgetting; <italic>Consistent task-specific knowledge transfer, which allows edge clients to extract relevant knowledge from a server-side knowledge pool, providing a jump-starting for the current task. Experimental results demonstrate that MeCo significantly outperforms other federated and/or continual learning approaches in real-world industrial fault diagnosis, achieving approximately 2% higher Mean Average Accuracy and being 1.74 times more cost-effective in server-to-client communication. These advantages, along with its robust performance in IES, indicate the potential of MeCo for facilitating edge-cloud collaborative learning in the future.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 3","pages":"2107-2120"},"PeriodicalIF":6.7,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870957","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

Mechanism Design for Blockchain Order Books Against Selfish Miners 区块链订单对自私矿工的机制设计

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-02-24 DOI: 10.1109/TNSE.2025.3544686

Yunshu Liu;Lingjie Duan

{"title":"Mechanism Design for Blockchain Order Books Against Selfish Miners","authors":"Yunshu Liu;Lingjie Duan","doi":"10.1109/TNSE.2025.3544686","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3544686","url":null,"abstract":"In blockchain-based order book systems, buyers and sellers trade assets, while it is miners to match them and include their transactions in the blockchain. It is found that many miners behave selfishly and myopically, prioritizing transactions with high fees and ignoring many desirable matches that could enhance social welfare. Existing blockchain mechanisms fail to address this issue by overlooking miners' selfish behaviors. To our best knowledge, this work presents the first analytical study to quantify and understand buyer and seller transaction fee choices and selfish miners' transaction matching strategies, proving an infinitely large price of anarchy (PoA) for social welfare loss. To mitigate this, we propose an adjustable block size mechanism that is easy to implement without altering the existing decentralized protocols and still allows buyers and sellers to freely decide transaction fees and miners to selfishly match. The analysis is challenging, as pure strategy Nash equilibria do not always exist, requiring the analysis of many buyers' or sellers' interactive mixed-strategy distributions. Moreover, the system designer may even lack information about each buyer's or seller's bid/ask prices and trading quantities. Nevertheless, our mechanism achieves a well-bounded PoA, and under the homogeneous-quantity trading for non-fungible tokens (NFT), it attains a PoA of 1 with no social welfare loss. We implement our mechanism on a local instance of Ethereum to demonstrate the feasibility of our approach. Experiments based on the realistic dataset demonstrate that our mechanism achieves social optimum for homogeneous-quantity trading like NFT. It can enhance social welfare up to 3.7 times compared to the existing order book benchmarks for heterogeneous-quantity trading of Bitcoin tokens. It exhibits robustness against random variations in buyers and sellers.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 3","pages":"2121-2134"},"PeriodicalIF":6.7,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870952","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

Outage Probability Analysis of MISO-NOMA Downlink Communications in UAV-Assisted Agri-IoT With SWIPT and TAS Enhancement 具有SWIPT和TAS增强的无人机辅助农业物联网中MISO-NOMA下行通信中断概率分析

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-02-24 DOI: 10.1109/TNSE.2025.3545148

Yixin He;Fanghui Huang;Dawei Wang;Ruonan Zhang

{"title":"Outage Probability Analysis of MISO-NOMA Downlink Communications in UAV-Assisted Agri-IoT With SWIPT and TAS Enhancement","authors":"Yixin He;Fanghui Huang;Dawei Wang;Ruonan Zhang","doi":"10.1109/TNSE.2025.3545148","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3545148","url":null,"abstract":"In the agricultural Internet of Things (Agri-IoT), the uncrewed aerial vehicle (UAV) can serve as a mobile relay to facilitate line-of-sight transmissions for agricultural sensors, especially in farmlands with complex terrain or numerous obstructions. Additionally, the integration of techniques such as simultaneous wireless information and power transfer (SWIPT) and multiple-input single-output (MISO), combined with non-orthogonal multiple access (NOMA) communications, not only supports a higher number of device connections but also provides an essential power supply to cell-edge sensors. Motivated by the above, we propose a collaborative MISO-NOMA communication mechanism in UAV-assisted Agri-IoT. Specifically, the UAV functions as a static relay, and the NOMA-enhanced decode-and-forward relay protocol and SWIPT technique are used in the cell-center relaying UAV. The selection combining technique is employed for cell-edge sensors to obtain the optimal quality signal from multiple antennas of the base station (BS). To further improve the channel capacity, we propose a transmit antenna selection (TAS) strategy for the base station equipped with multiple antennas. Different from existing strategies (such as maximizing harvested energy or direct-link performance), the proposed TAS strategy aims to achieve optimal outage performance at cell-edge sensors, rather than suboptimal performance. Then, we derive closed-form and approximate solutions for the outage probability of cell-edge sensors. These solutions can provide significant insights into the impact of MISO-NOMA communications in UAV-assisted Agri-IoT. Finally, the simulation results indicate that the proposed TAS strategy outperforms current state-of-the-art schemes in reducing the outage probability. Moreover, our simulation experiments verify that the derived approximate solution closely aligns with the closed-form solution.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 3","pages":"2151-2164"},"PeriodicalIF":6.7,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870954","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

Spatial Disease Propagation With Hubs 具有枢纽的空间疾病传播

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-02-24 DOI: 10.1109/TNSE.2025.3545386

Ke Feng;Martin Haenggi

引用次数: 0

Cyber-Physical Defense for Heterogeneous Multi-Agent Systems Against Exponentially Unbounded Attacks on Signed Digraphs 异构多智能体系统对签名有向图指数无界攻击的网络物理防御

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-02-24 DOI: 10.1109/TNSE.2025.3545280

Yichao Wang;Mohamadamin Rajabinezhad;Yi Zhang;Shan Zuo

{"title":"Cyber-Physical Defense for Heterogeneous Multi-Agent Systems Against Exponentially Unbounded Attacks on Signed Digraphs","authors":"Yichao Wang;Mohamadamin Rajabinezhad;Yi Zhang;Shan Zuo","doi":"10.1109/TNSE.2025.3545280","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3545280","url":null,"abstract":"Cyber-physical systems (CPSs) are subjected to attacks on both cyber and physical spaces. In reality, attackers could launch any time-varying signals. Existing literature generally addresses bounded attack signals and/or bounded-first-order-derivative attack signals. In contrast, this paper proposes a privacy-preserving fully-distributed attack-resilient bilayer defense framework to address the bipartite output containment problem for heterogeneous multi-agent systems (MASs) on signed digraphs, in the presence of exponentially unbounded false data injection (EU-FDI) attacks on both the cyber-physical layer (CPL) and observer layer (OL). First, we design attack-resilient dynamic compensators that utilize data communicated on the OL to estimate the convex combinations of the states and negative states of the leaders. To enhance the security of transmitted data, a privacy-preserving mechanism is incorporated into the observer design. The privacy-preserving attack-resilient observers address the EU-FDI attacks on the OL and guarantee the uniformly ultimately bounded (UUB) estimation of the leaders' states in the presence of the eavesdroppers. Then, by using the observers' states, fully-distributed attack-resilient controllers are designed on the CPL to further address the EU-FDI attacks on the actuators. The theoretical soundness of the proposed bilayer resilient defense framework is proved by Lyapunov stability analysis. Finally, a comparative case study for heterogeneous MASs and the application in DC microgrids as a specific case study validate the enhanced resilience of the proposed defense strategies.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 3","pages":"2165-2179"},"PeriodicalIF":6.7,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143871018","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

Enhancing Network Abnormal Detection With NMF-SECNN: Leveraging Deep Feature Learning for High-Precision Traffic Analysis 利用NMF-SECNN增强网络异常检测：利用深度特征学习进行高精度流量分析

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-02-21 DOI: 10.1109/TNSE.2025.3544251

Yazhou Yuan;Ning Yu;Zhuolin Zheng;Yong Yang;Kai Ma;Zhixin Liu;Cailian Chen;Jianmin Zhang

{"title":"Enhancing Network Abnormal Detection With NMF-SECNN: Leveraging Deep Feature Learning for High-Precision Traffic Analysis","authors":"Yazhou Yuan;Ning Yu;Zhuolin Zheng;Yong Yang;Kai Ma;Zhixin Liu;Cailian Chen;Jianmin Zhang","doi":"10.1109/TNSE.2025.3544251","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3544251","url":null,"abstract":"Detection of abnormalities in industrial network traffic plays a crucial role in maintaining network system security. However, current abnormal detection models suffer from low precision, and extracting deep-level feature information from industrial network traffic is difficult. This leads to the loss of partial feature information during the detection process, thereby affecting detection efficiency. To address this issue, this paper proposes an abnormal traffic detection framework for industrial networks. By employing a Non-negative Matrix Factorization (NMF)-based method for extracting abnormal traffic features and optimizing the NMF decomposition process through constructing label consistency constraints, we facilitate effective feature extraction. Additionally, the Squeeze-and-Excitation attention mechanism is introduced into a Convolutional Neural Network (CNN) to construct a classifier that enhances detection precision without increasing complexity, enabling efficient identification of complex network traffic patterns. This results in the NMF-Squeeze-and-Excitation-CNN (NMF-SECNN) model, which combines effective feature extraction capability with a lightweight structural design, achieving superior detection performance in industrial network environments. The proposed method achieves a detection accuracy of 99.4%, representing a 5.6% improvement over baseline methods, and a recall rate of 98.2%, showcasing the model's capability to identify abnormalities across diverse scenarios. Various classification metrics confirm the model's robustness and effectiveness, demonstrating its significant advantages over traditional methods.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 3","pages":"2069-2080"},"PeriodicalIF":6.7,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870985","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

Noncooperative Game-Based Composite Voltage Regulation for Microgrid With Switching Topologies and Prescribed Performance 具有开关拓扑和规定性能的微电网非合作博弈复合电压调节

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-02-21 DOI: 10.1109/TNSE.2025.3538603

Yuezhi Liu;Yong Chen;Longjie Zhang;Hongru Wang;Esam Hafez

{"title":"Noncooperative Game-Based Composite Voltage Regulation for Microgrid With Switching Topologies and Prescribed Performance","authors":"Yuezhi Liu;Yong Chen;Longjie Zhang;Hongru Wang;Esam Hafez","doi":"10.1109/TNSE.2025.3538603","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3538603","url":null,"abstract":"In this paper, the voltage regulation issue of the microgrid with the switching topologies, nonlinear coupling and prescribed performance is investigated. Firstly, to remove the requirement of the global topology information, a noncooperative game layer with the fully distributed Nash equilibrium seeking (FDNES) approach is devised. In this study, the noncooperative game is performed over the switching communication topologies. Furthermore, the voltage regulation layer is formulated, which integrates the adaptive coupling observer (ACO) and prescribed performance based composite voltage regulation (PPCVR) methods. Specifically, in the ACO, an adaptive observer gain is devised to attenuate the damaging peak dynamics. For the PPCVR, the prescribed performance function based dynamic surface control strategy is formulated such that the voltage tracking error can be restrained according to the specified constraints, which will enhance the voltage regulation performance. Additionally, the PPCVR utilizes the coupling estimation by the ACO to compensate the nonlinear coupling dynamics. It is shown that the signals of the closed-loop system are semi-global uniformly and ultimately bounded (SGUUB). Finally, comparative studies and hardware-in-loop experiment by RT-LAB platform are performed to illustrate the effectiveness of the proposed voltage regulation strategy.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 3","pages":"1720-1731"},"PeriodicalIF":6.7,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870913","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

Progressive Community Merging Cooperative Coevolution Algorithm for Influence Blocking Maximization in Social Networks 社交网络中影响块最大化的渐进式社区融合协同进化算法

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-02-21 DOI: 10.1109/TNSE.2025.3544429

Ming Gu;Tian-Fang Zhao;Jinghui Zhong;Wei-Neng Chen

{"title":"Progressive Community Merging Cooperative Coevolution Algorithm for Influence Blocking Maximization in Social Networks","authors":"Ming Gu;Tian-Fang Zhao;Jinghui Zhong;Wei-Neng Chen","doi":"10.1109/TNSE.2025.3544429","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3544429","url":null,"abstract":"The widespread adoption of online social networks (OSNs) has facilitated social interaction and knowledge dissemination while raising concerns about extensive negative information propagation. Competitive propagation of positive and negative information can mitigate negative impacts. Influence blocking maximization (IBM) identifies a set of nodes initiating positive information propagation in OSNs to maximize blocking negative influence. This paper first introduces an effective influence blocking estimator (DPADV) that replaces computationally expensive Monte Carlo simulations. DPADV can calculate the approximate diffusion value for nodes activated by negative information in any hop neighborhood. Meanwhile, to address the challenges of complexity and computational efficiency brought about by the continuous expansion of OSNs, we propose the progressive community merging cooperative coevolution (PCMCC) algorithm. PCMCC divides the search space into communities and initializes a subpopulation for each community. Each subpopulation is responsible for optimizing a community, thereby implementing a divide-and-conquer approach. To enhance collaboration among communities and global exploration, we employed a progressive community merging strategy, supplemented by multi-population evolution strategies to guide the search towards global optima. Additionally, we developed an efficient heuristic metric for evaluating node importance, which is used to design population crossover and local search in the evolutionary scheme. Experimental results on six real-world and four synthetic networks demonstrate that PCMCC exhibits competitive performance compared to state-of-the-art algorithms, achieving near-greedy performance with lower time complexity.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 3","pages":"2093-2106"},"PeriodicalIF":6.7,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143871003","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

Training Latency Minimization for Model-Splitting Allowed Federated Edge Learning 允许联邦边缘学习的模型分割训练延迟最小化

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-02-20 DOI: 10.1109/TNSE.2025.3544313

Yao Wen;Guopeng Zhang;Kezhi Wang;Kun Yang

{"title":"Training Latency Minimization for Model-Splitting Allowed Federated Edge Learning","authors":"Yao Wen;Guopeng Zhang;Kezhi Wang;Kun Yang","doi":"10.1109/TNSE.2025.3544313","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3544313","url":null,"abstract":"To alleviate the shortage of computing power faced by clients in training deep neural networks (DNNs) using federated learning (FL), we leverage the <italic>edge computing and <italic>split learning to propose a model-splitting allowed FL (<monospace>SFL</monospace>) framework, with the aim to minimize the training latency without loss of test accuracy. Under the <italic>synchronized global update setting, the latency to complete a round of global training is determined by the maximum latency for the clients to complete a local training session. Therefore, the training latency minimization problem (TLMP) is modelled as a minimizing-maximum problem. To solve this mixed integer nonlinear programming problem, we first propose a <italic>regression method to fit the quantitative-relationship between the <italic>cut-layer and other parameters of an AI-model, and thus, transform the TLMP into a continuous problem. Considering that the two subproblems involved in the TLMP, namely, the <italic>cut-layer selection problem for the clients and the <italic>computing resource allocation problem for the parameter-server are relative independence, an alternate-optimization-based algorithm with polynomial time complexity is developed to obtain a high-quality solution to the TLMP. Extensive experiments are performed on a popular DNN-model <italic>EfficientNetV2 using dataset MNIST, and the results verify the validity and improved performance of the proposed <monospace>SFL</monospace> framework.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 3","pages":"2081-2092"},"PeriodicalIF":6.7,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870950","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