IEEE Transactions on Network Science and Engineering最新文献

Curvature on Graphs with Negative Edge Weights. 负边权图上的曲率。

IF 7.9 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2026-04-09 DOI: 10.1109/tnse.2026.3682565

Daniel Grange, Yifan Sun, Corey Weistuch, Rena Elkin, Sean Phillips, Joseph O Deasy, Tryphon Georgiou

{"title":"Curvature on Graphs with Negative Edge Weights.","authors":"Daniel Grange, Yifan Sun, Corey Weistuch, Rena Elkin, Sean Phillips, Joseph O Deasy, Tryphon Georgiou","doi":"10.1109/tnse.2026.3682565","DOIUrl":"https://doi.org/10.1109/tnse.2026.3682565","url":null,"abstract":"Discrete notions of curvature have yielded important insights into the fragility of networks, including financial, gene regulatory, and social networks. These quantitative measures help identify critical nodes and pathways whose failure may cause disruption to the network's overall functionality. One such measure, the Ollivier-Ricci (OR) curvature, which is the focus of this paper, extends this inherently geometric concept into the setting of graphs by evaluation via the cost of transporting node distributions. However, a previously unstudied and salient feature of graphs is that links between nodes may reflect more than a spatial - separation links may be inhibitory or antagonistic, a quality that is not captured in the geometry of continuous spaces. To this end, we present the notions of a balanced graph and of graph frustration, to capture antagonistic effects of signed edge weights modeling promotion (+) or inhibition (-); a balanced graph is one where every cycle has an even number of negative edge weights, and frustration quantifies the degree of deviation from a balanced graph. Based on these concepts, we introduce modified Ollivier-Ricci-inspired fragility indices that point to pathways that magnify frustration in unbalanced graphs. We study two types of networks, gene regulatory and social networks, to demonstrate the utility of the fragility indices to impede or enhance functionality with respect to graph frustration. Our results demonstrate that, indeed, these new indices better identify critical edges, as quantified by several global measures, than other commonly used indices.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":" ","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13128017/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147823451","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Distance-Aware Hypergraph and Attention Network With Unimodal Assistance for Multimodal Sentiment Analysis 基于单模态辅助的距离感知超图和注意网络用于多模态情感分析

IF 7.9 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2026-02-26 DOI: 10.1109/TNSE.2026.3668198

Yibing Wang;Wupeng Xie;Zhutian Yang;Linhan Wang;Mingqian Liu;Yushi Chen;Yue Gao

{"title":"Distance-Aware Hypergraph and Attention Network With Unimodal Assistance for Multimodal Sentiment Analysis","authors":"Yibing Wang;Wupeng Xie;Zhutian Yang;Linhan Wang;Mingqian Liu;Yushi Chen;Yue Gao","doi":"10.1109/TNSE.2026.3668198","DOIUrl":"https://doi.org/10.1109/TNSE.2026.3668198","url":null,"abstract":"Multimodal sentiment analysis (MSA) has advanced with deep learning, yet some limitations persist. Early methods can capture intra-sample patterns but fail to model inter-sample structural correlations. While Transformers improved inter-modal modeling, their high computational cost and confinement to pairwise relationships prevent them from capturing the complex, group-wise cues inherent in human expression. To address these gaps, we propose a novel Distance-Aware Hypergraph and Attention Network with Unimodal Assistance (DHAN-UA). Our framework's core is a semantic-proximity-aware hypergraph hybrid convolution. We first introduce an inverse-distance weighting strategy to redefine the hypergraph incidence matrix, ensuring a node's influence within a hyperedge is proportional to its semantic closeness to the hyperedge's conceptual center. This approach embeds crucial categorical and semantic priors into the unimodal features. Building upon this, a synergistic hierarchical attention framework first applies intra-modal self-attention to capture long-range dependencies in the topologically-aware features, then uses an inter-modal attention module for efficient weighted fusion. This design achieves both feature refinement and effective fusion. Finally, to enhance model stability, a unimodal-assisted training strategy acts as a regularizer, ensuring the model retains essential information from all modalities. Extensive experiments demonstrate that our model achieves competitive performance on benchmark datasets while maintaining superior computational efficiency.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"13 ","pages":"7322-7342"},"PeriodicalIF":7.9,"publicationDate":"2026-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147440535","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

FLSC-CI: Federated Learning and Semantic Communication Empowered Multimodal Terminal Collaborative Inferencing Framework for IoT Businesses FLSC-CI：支持物联网业务的联邦学习和语义通信的多模态终端协同推理框架

IF 7.9 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2026-02-24 DOI: 10.1109/TNSE.2026.3667621

Siya Xu;Yonghao Qi;Feng Qi;Shaoyong Guo;Ziyu Zhao

{"title":"FLSC-CI: Federated Learning and Semantic Communication Empowered Multimodal Terminal Collaborative Inferencing Framework for IoT Businesses","authors":"Siya Xu;Yonghao Qi;Feng Qi;Shaoyong Guo;Ziyu Zhao","doi":"10.1109/TNSE.2026.3667621","DOIUrl":"https://doi.org/10.1109/TNSE.2026.3667621","url":null,"abstract":"Inference tasks based on multimodal data from the Internet of Things (IoT) play an important role in intelligent management. Due to the limited resources of IoT devices, existing edge frameworks struggle to achieve low-energy, high-efficiency accurate inference. This paper introduces a Federated Learning (FL) and semantic communication empowered multimodal terminal collaborative inferencing framework for IoT businesses (FLSC-CI). Firstly, we propose an FL-based Customized model Training Algorithm (FL-CTA) for semantic encoder-decoder models and business inference models. In the semantic extraction phase, high-quality terminals perform local model training, model aggregation, and semantic extraction, while low-quality terminals perform only local model training or semantic extraction. In the business inference model training phase, the edge server synchronously performs multimodal model training by utilizing semantics transmitted from terminals. Furthermore, this paper proposes a Heterogeneous Resource Dynamic Allocation Strategy (HRDAS) for FLSC-CI based on multi-agent deep deterministic policy gradient to manage FL training process. Intelligent agents at cluster heads make customized allocation decisions of system bandwidth and power according to terminals’ service capabilities and model features within the cluster. Simulation results demonstrate that FLSC-CI significantly improves resource utilization and communication efficiency while maintaining high inference accuracy, making it suitable for large-scale heterogeneous IoT deployments.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"13 ","pages":"7191-7208"},"PeriodicalIF":7.9,"publicationDate":"2026-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147440539","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 Intrusion Detection via Interpretable Inter-Flow Spatio-Temporal Graphs and Intra-Flow Features 利用可解释的流间时空图和流内特征增强入侵检测

IF 7.9 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2026-02-24 DOI: 10.1109/TNSE.2026.3664905

Xiaowei Zhao;Mingshu He;Liu Yang;Jianjin Zhao;Xiaojuan Wang

{"title":"Enhancing Intrusion Detection via Interpretable Inter-Flow Spatio-Temporal Graphs and Intra-Flow Features","authors":"Xiaowei Zhao;Mingshu He;Liu Yang;Jianjin Zhao;Xiaojuan Wang","doi":"10.1109/TNSE.2026.3664905","DOIUrl":"https://doi.org/10.1109/TNSE.2026.3664905","url":null,"abstract":"The performance of network intrusion detection systems (IDS) critically depends on the completeness of traffic feature representation. Existing methods predominantly focus either on intra-flow features (e.g., packet length sequences) or single-dimensional inter-flow relationships, limiting optimal classification. To address this restriction, we propose IF<inline-formula><tex-math>$^{2}$</tex-math></inline-formula>-STG to enhance intrusion detection via interpretable inter-flow spatio-temporal graphs and intra-flow features. The key innovation of our scheme is the construction of an Inter-flow Spatio-Temporal relationship Graph (ISTG), with two-dimensional edges explicitly quantifying the correlation strength between flows. On this basis, a GNN learns the inter-flow context. In parallel, a CNN extracts fine-grained intra-flow features from raw bytes of individual flows. Finally, the two modal features are fused to acquire a comprehensive representation. This representation can effectively capture both intrinsic behavior patterns of flows and contextual inter-flow relationships, thereby significantly enhancing the detection performance and robustness of model. Experimental results show that the proposed IF<inline-formula><tex-math>$^{2}$</tex-math></inline-formula>-STG achieves over 99% accuracy on three real-world datasets, outperforming existing approaches. The constructed ISTG provides explicit visual interpretation of flow dependencies. More importantly, IF<inline-formula><tex-math>$^{2}$</tex-math></inline-formula>-STG-Inter, using only inter-flow features, maintains 97.78% detection accuracy in cross-dataset tests involving time-disparate datasets, validating superior generalization of inter-flow spatio-temporal features. This advantage renders it particularly promising for practical intrusion detection applications.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"13 ","pages":"7118-7137"},"PeriodicalIF":7.9,"publicationDate":"2026-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147362421","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

Underwater Target Tracking Based on Acoustic-Optical Fusion for Multi-AUV Systems 基于声光融合的多auv系统水下目标跟踪

IF 7.9 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2026-02-24 DOI: 10.1109/TNSE.2026.3667901

Yang Yang;Yichen Li;Wenbin Yu;Xinping Guan

{"title":"Underwater Target Tracking Based on Acoustic-Optical Fusion for Multi-AUV Systems","authors":"Yang Yang;Yichen Li;Wenbin Yu;Xinping Guan","doi":"10.1109/TNSE.2026.3667901","DOIUrl":"https://doi.org/10.1109/TNSE.2026.3667901","url":null,"abstract":"Multi-source fusion technologies have emerged as a critical approach for underwater target tracking, where acoustic-optical fusion demonstrates significant potential for tracking highly-maneuvering targets in small-scale scenarios, particularly in terms of continuity and stability. Different from existing studies that focus on image fusion, this work addresses the limitations of acoustic measurements, such as low update frequency and time delays. By leveraging high-frequency optical observations, an acoustic-optical fusion mechanism has been proposed for multi-autonomous underwater vehicle (multi-AUV) systems, which alleviates the time-lagged effect of traditional single-acoustic tracking for highly-maneuvering targets and, accordingly, improves the tracking accuracy. Specifically, an acoustic-optical fusion target tracking framework is designed based on the different characteristics of optical and acoustic measurements, which consists of the following two parts. In the “high-frequency optical estimation”, the inter-frame changes of the target on the image plane are used to mitigate the impact of acoustic measurement delays. For the multiplicative noise from the optical observation, bias compensation strategies have been designed to reduce the estimation error. As for the “acoustic-optical fusion”, this article integrates measurements from multiple AUVs to obtain higher tracking accuracy. The collaborative effort of multiple AUVs overcomes individual measurement limitations and ensures more reliable tracking in dynamic underwater environments. Extensive simulations and experiments are conducted to validate the proposed algorithms in terms of tracking accuracy and real-time performance.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"13 ","pages":"7226-7243"},"PeriodicalIF":7.9,"publicationDate":"2026-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147440540","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

A Graph Neural Network-Based Approach for Critical Node Detection in Dynamic Satellite Networks 基于图神经网络的动态卫星网络关键节点检测方法

IF 7.9 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2026-02-24 DOI: 10.1109/TNSE.2026.3667784

Hengyi Lv;Lifeng Cao;Xiaohan Wang;Xingchen Li

{"title":"A Graph Neural Network-Based Approach for Critical Node Detection in Dynamic Satellite Networks","authors":"Hengyi Lv;Lifeng Cao;Xiaohan Wang;Xingchen Li","doi":"10.1109/TNSE.2026.3667784","DOIUrl":"https://doi.org/10.1109/TNSE.2026.3667784","url":null,"abstract":"To address the challenges in critical node identification within complex satellite networks, such as difficulties in dynamic modeling and limited computational resources, this study proposes an innovative spatiotemporal feature learning-based identification scheme. First, by coupling a dynamic geographic constraint mechanism with complex network modeling, a generative satellite network model (BS-TN) incorporating satellite orbit characteristics was developed, enabling generation of controllable simulation datasets. Second, a spatiotemporal fusion node importance evaluation model (ST-FNIM) was introduced. A lightweight L-GAT network was designed by incorporating nonlinear attenuation into the attention mechanism and pruning the multi-head attention to reduce the computational overhead, thereby extracting the multi-dimensional spatial features of satellite nodes across time steps. An event-driven ET-LSTM architecture was also proposed, enabling responsive sequential analysis of node behaviors via an optimized gating mechanism. By fusing spatiotemporal features, the model enabled the accurate dynamic identification of critical nodes. The experimental results demonstrated that compared with conventional centrality algorithms and existing deep learning methods, the proposed approach significantly improved computational efficiency and dynamic adaptability, while increasing identification accuracy by approximately 10%. It enabled real-time assessment and response to sudden events such as link failures and traffic surges, offering a novel technical framework for satellite network management, resource optimization, and security assurance.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"13 ","pages":"7209-7225"},"PeriodicalIF":7.9,"publicationDate":"2026-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147440572","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

Random Walk Based Hierarchical Collaborative Filtering for Directed Network Embedding 基于随机行走的有向网络嵌入分层协同过滤

IF 7.9 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2026-02-24 DOI: 10.1109/TNSE.2026.3667739

Zhihong Fang;Shaolin Tan;Yao Chen;Hui Liu

{"title":"Random Walk Based Hierarchical Collaborative Filtering for Directed Network Embedding","authors":"Zhihong Fang;Shaolin Tan;Yao Chen;Hui Liu","doi":"10.1109/TNSE.2026.3667739","DOIUrl":"https://doi.org/10.1109/TNSE.2026.3667739","url":null,"abstract":"The asymmetricsemantic information within directionality makes directed network embedding essentially different from undirected network embedding. Existing directed network embedding methods, explicitly or implicitly, are established by preserving pairwise interactions yet distinguishing in-direction and out-direction. Noticing that the inherent semantic connotation of edge directions is still seldom leveraged to enhance directed network embedding, in this work, we propose a novel random walk embedding framework named RW4CF to encode hierarchical collaborative filtering features within directed networks. In detail, we interpret the directed link as a type of user-item interaction and formulate the concept of hierarchical collaborative filtering matrices as a heuristic structural feature for directed network embedding. Specifically, we incorporate a collaborative filtering window in the random walk scheme to encode collaborative filtering information. Theoretical analysis is given to prove that the obtained embedding by RW4CF is indeed a factorization of the hierarchical collaborative filtering matrices of the directed network. Moreover, to validate the efficiency of RW4CF, we conduct extensive experiments on directed network datasets and demonstrate the superior performances of RW4CF than the state-of-the-arts.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"13 ","pages":"7173-7190"},"PeriodicalIF":7.9,"publicationDate":"2026-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147440593","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

A Generative Model for Spatial Complex Networks: Applications to Power Grids and Brain Networks 空间复杂网络的生成模型：在电网和脑网络中的应用

IF 7.9 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2026-02-24 DOI: 10.1109/TNSE.2026.3668009

Alessandra Corso;Lucia Valentina Gambuzza;Ludovico Minati;Mattia Frasca

{"title":"A Generative Model for Spatial Complex Networks: Applications to Power Grids and Brain Networks","authors":"Alessandra Corso;Lucia Valentina Gambuzza;Ludovico Minati;Mattia Frasca","doi":"10.1109/TNSE.2026.3668009","DOIUrl":"https://doi.org/10.1109/TNSE.2026.3668009","url":null,"abstract":"In this work, we propose a generative model for spatial networks. The central idea of the model is to use empirical data from real-world spatial networks as a foundation for the network structure that is constructed starting from a set of disconnected nodes and assigning the node positions and the links between them based on key topological and spatial features. In particular, for each node, the number of links to add is determined by sampling values from the degree distribution of real-world networks, while the nodes to connect with are randomly selected based on a probability that depends on the distance between the node positions. For the node positions, we propose either leaving them unconstrained or applying one of four physical constraints with varying levels of strictness. The model can be applied to both two- and three-dimensional spaces. As an example of the former, we consider power grids, while for the latter, we study brain networks. In both cases, we show that the model can be effectively applied to generate surrogate networks, providing a useful tool when spatial network data is limited.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"13 ","pages":"7303-7321"},"PeriodicalIF":7.9,"publicationDate":"2026-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147440574","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

QoE-Oriented Task Offloading in SAG Integrated IoT: An Interactive Dual-Agent PPO Approach 面向qos的SAG集成物联网任务卸载：一种交互式双agent PPO方法

IF 7.9 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2026-02-17 DOI: 10.1109/TNSE.2026.3665911

Zihao Zhang;Haixia Peng;Zhou Su;Yuntao Wang;Tom H. Luan;Nan Cheng

{"title":"QoE-Oriented Task Offloading in SAG Integrated IoT: An Interactive Dual-Agent PPO Approach","authors":"Zihao Zhang;Haixia Peng;Zhou Su;Yuntao Wang;Tom H. Luan;Nan Cheng","doi":"10.1109/TNSE.2026.3665911","DOIUrl":"https://doi.org/10.1109/TNSE.2026.3665911","url":null,"abstract":"Space-air-ground integrated Internet of things (IoT) networks can enable seamless global coverage for IoT devices and effectively alleviate the burden on terrestrial IoT data transmission. However, due to the complexity of network architecture and the wide geographical distribution of IoT nodes, significant discrepancies may occur in the timing of control information reception among certain nodes. New challenges arise accordingly for the unified management of multi-dimensional resources and task offloading in the network. To mitigate this, in this paper, we propose a dynamic two time-scales resource management framework that simultaneously takes task types, requirements, and priorities into account. Moreover, quality of experience (QoE) models are designed for the IoT users generating data-transmission and computation-intensive tasks, and an optimization problem is formulated to maximize the overall QoE. Given the multi-scale coupling constraints and mixed-integer program of the formulated problem, we decouple it into two Markov decision process-based subproblems and develop an interactive dual-agent proximal policy optimization algorithm to address them. Numerical results demonstrate the superiority of our proposed algorithm compared to benchmark algorithms.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"13 ","pages":"7138-7155"},"PeriodicalIF":7.9,"publicationDate":"2026-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147362347","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

Online Model Retraining, Compression, and Instance Allocation in Edge Computing Networks 边缘计算网络中的在线模型再训练、压缩和实例分配

IF 7.9 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2026-02-17 DOI: 10.1109/TNSE.2026.3665761

Shijia Huang;Fan Yang;Qian Ma;Shimin Gong

{"title":"Online Model Retraining, Compression, and Instance Allocation in Edge Computing Networks","authors":"Shijia Huang;Fan Yang;Qian Ma;Shimin Gong","doi":"10.1109/TNSE.2026.3665761","DOIUrl":"https://doi.org/10.1109/TNSE.2026.3665761","url":null,"abstract":"The adoption of artificial intelligence models (e.g., DNN models) in Internet of Things has boosted computing demands in edge computing. Frequent model retraining, necessitated by concept drift, further increases resource usage, while model compression sacrifices model performance for computing efficiency. However, few works study computing instance allocation problem considering dynamic model retraining and compression, especially under varying workloads and model performance degradation. In this work, we model the problem as a joint online model retraining, compression, and instance allocation problem in edge computing networks considering model performance and instance cost. Solving the online problem is challenging since it is a non-linear binary programming problem with time-coupling instance switching cost. We first solve the online problem under fixed compression and propose an efficient online algorithm. Specifically, we first linearize the non-linear term, then regularize the time-coupling switching cost to decouple the problem, and finally use a randomization rounding method to derive the integral solution. We prove that our algorithm achieves a constant optimality gap. We then solve the online problem under flexible compression and propose a lightweight online algorithm. We extend the linearization method and decouple the problem into each time slot, and demonstrate our algorithm achieves an optimality gap depending on the time period. Simulations demonstrate that our algorithm can achieve a balance between instance cost and model performance in both fixed compression and flexible compression scenarios.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"13 ","pages":"7156-7172"},"PeriodicalIF":7.9,"publicationDate":"2026-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147440529","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