检索结果-内蒙古大学图书馆

Dynamic Neural Network-Based Resource Management for Mobile Edge Computing in 6G Networks

IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING 2024年第3期10卷 953-967页

作者： Ma, Longfei Cheng, Nan Zhou, Conghao Wang, Xiucheng Lu, Ning Zhang, Ning Aldubaikhy, Khalid Alqasir, Abdullah Xidian Univ State Key Lab ISN Xian 710071 Peoples R China Xidian Univ Sch Telecommun Engn Xian 710071 Peoples R China Univ Waterloo Dept Elect & Comp Engn Waterloo ON N2L 3G1 Canada Queens Univ Dept Elect & Comp Engn Kingston ON Canada Univ Windsor Dept Elect & Comp Engn Windsor ON N9B 3P4 Canada Qassim Univ Dept Elect Engn Buraydah 52571 Saudi Arabia

Mobile edge computing (MEC) can be used to reduce the task delay for users with limited computing resources. However, in 6G networks, the diversity of tasks is greatly increased. For those extremely delay-sensitive small-size computing tasks, the inference delay of neural network (NN)-based algorithms such as resource allocation and task offloading cannot be ignored. As a hyperparameter, the inference cost of NN is usually difficult to adjust. Dynamic neural network (DyNN) is an emerging technique that improves the model efficiency by adjusting the network architecture on-demand according to the sample characteristics during inference. In this paper, we propose a DyNN-based resource management method for MEC that dynamically adjusts the depth and width of the NN according to the features of the task, improving computational efficiency and achieving a balance between inference delay and the management performance of computational and communication resources. Furthermore, to reduce the training cost of DyNN, a new training method is proposed in this paper, where all the blocks in DyNN are gradually trained in the order of size. Simulation results demonstrate that the proposed DyNN-based resource management method outperforms the traditional optimization algorithm and the static-NN-based method.

关键词： Delays Task analysis Artificial neural networks Resource management Training inference algorithms Heuristic algorithms Mobile edge computing inference delay dynamic neural network training cost

来源：评论

学校读者我要写书评

暂无评论

Traffic-Aware Lightweight Hierarchical Offloading Toward Adaptive Slicing-Enabled SAGIN

引用

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS 2024年第12期42卷 3536-3550页

作者： Chen, Zheyi Zhang, Junjie Min, Geyong Ning, Zhaolong Li, Jie Fuzhou Univ Coll Comp & Data Sci Fuzhou 350116 Peoples R China Fuzhou Univ Fujian Key Lab Network Comp & Intelligent Informat Fuzhou 350116 Peoples R China Minist Educ Engn Res Ctr Big Data Intelligence Fuzhou 350002 Peoples R China Univ Exeter Fac Environm Sci & Econ Dept Comp Sci Exeter EX4 4QF England Chongqing Univ Posts & Telecommun Sch Commun & Informat Engn Chongqing 400065 Peoples R China Shanghai Jiao Tong Univ Dept Comp Sci & Engn Shanghai 200240 Peoples R China

The emerging Space-Air-Ground Integrated Networks (SAGIN) empower Mobile Edge Computing (MEC) with wider communication coverage and more flexible network access. However, the fluctuating user traffic and constrained computing architecture seriously hinder the Quality-of-Service (QoS) and resource utilization in SAGIN. Existing solutions generally depend on prior knowledge or adopt static resource provisioning, lacking adaptability and resulting in serious system overheads. To address these important challenges, we propose THOAS, a novel Traffic-aware lightweight Hierarchical Offloading framework towards Adaptive Slicing-enabled SAGIN. First, we innovatively separate SAGIN into Communication Access Platforms (CAPs) and Computation Offloading Platforms (COPs). Next, we design a new self-attention-based prediction method to accurately capture the traffic changes on each platform, enabling adaptive slice resource adjustments. Finally, we develop an improved deep reinforcement learning method based on proximal clipping with dynamic confidence intervals to reach optimal offloading. Notably, we employ knowledge distillation to compress offloading policies into lightweight networks, enhancing their adaptability in resource-limited SAGIN. Using real-world datasets of user traffic, extensive experiments are conducted. The results show that the THOAS can accurately predict traffic and make adaptive resource adjustments and offloading decisions, which outperforms other benchmark methods on multiple metrics under various scenarios.

关键词： Resource management Satellites Computational modeling inference algorithms Quality of service Adaptation models Space-air-ground integrated networks Heuristic algorithms Fluctuations Delays computation offloading slice resource allocation deep reinforcement learning model compression

来源：评论

学校读者我要写书评

暂无评论

Acceleration algorithms in GNNs: A Survey

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2025年第6期37卷 3173-3192页

作者： Ma, Lu Sheng, Zeang Li, Xunkai Gao, Xinyi Hao, Zhezheng Yang, Ling Nie, Xiaonan Jiang, Jiawei Zhang, Wentao Cui, Bin Peking Univ Sch CS Beijing 100871 Peoples R China Peking Univ Sch CS Beijing 100811 Peoples R China Univ Queensland Brisbane Qld 4072 Australia Northwestern Polytech Univ Sch AI Xian 710060 Peoples R China Wuhan Univ Sch Comp Sci Wuhan 430072 Peoples R China Peking Univ Ctr Machine Learning Res Beijing 100871 Peoples R China

Graph Neural Networks have demonstrated remarkable effectiveness in various graph-based tasks, but their inefficiency in training and inference poses significant challenges for scaling to real-world, large-scale applications. To address these challenges, a plethora of algorithms have been developed to accelerate GNN training and inference, garnering substantial interest from the research community. This paper presents a systematic review of these acceleration algorithms, categorizing them into three main topics: training acceleration, inference acceleration, and execution acceleration. For training acceleration, we discuss techniques like graph sampling and GNN simplification. In inference acceleration, we focus on knowledge distillation, GNN quantization, and GNN pruning. For execution acceleration, we explore GNN binarization and graph condensation. Additionally, we review several libraries related to GNN acceleration, including our Scalable Graph Learning library, and propose future research directions.

关键词： Training Graph neural networks inference algorithms Electronic mail Complexity theory Surveys Time complexity Libraries Taxonomy Social networking (online) scalability acceleration algorithms graph learning library

来源：评论

学校读者我要写书评

暂无评论

Non-Gaussian Process Dynamical Models

IEEE OPEN JOURNAL OF SIGNAL PROCESSING

引用

IEEE OPEN JOURNAL OF SIGNAL PROCESSING 2025年 6卷 213-221页

作者： Kindap, Yaman Godsill, Simon Univ Cambridge Dept Engn Cambridge CB2 1TN England

Probabilistic dynamical models used in applications in tracking and prediction are typically assumed to be Gaussian noise driven motions since well-known inference algorithms can be applied to these models. However, in many real world examples deviations from Gaussianity are expected to appear, e.g., rapid changes in speed or direction, which cannot be reflected using processes with a smooth mean response. In this work, we introduce the non-Gaussian process (NGP) dynamical model which allow for straightforward modelling of heavy-tailed, non-Gaussian behaviours while retaining a tractable conditional Gaussian process (GP) structure through an infinite mixture of non-homogeneous GPs representation. We present two novel inference methodologies for these new models based on the conditionally Gaussian formulation of NGPs which are suitable for both MCMC and marginalised particle filtering algorithms. The results are demonstrated on synthetically generated data sets.

关键词： Stochastic processes Kernel Mathematical models Predictive models Standards Adaptation models Probabilistic logic inference algorithms Q measurement Heavily-tailed distribution Non-Gaussian stochastic process L & eacute vy process particle filtering infinite mixtures

来源：评论

学校读者我要写书评

暂无评论

OPT-GCN: A Unified and Scalable Chiplet-Based Accelerator for High-Performance and Energy-Efficient GCN Computation

引用

IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS 2024年第12期43卷 4827-4840页

作者： Zhao, Yingnan Wang, Ke Louri, Ahmed George Washington Univ Dept Elect & Comp Engn Washington DC 20052 USA Univ North Carolina Charlotte Dept Elect & Comp Engn Charlotte NC 28223 USA

As the size of real-world graphs continues to grow at an exponential rate, performing the graph convolutional network (GCN) inference efficiently is becoming increasingly challenging. Prior works that employ a unified computing engine with a predefined computation order lack the necessary flexibility and scalability to handle diverse input graph datasets. In this article, we introduce OPT-GCN, a chiplet-based accelerator design that performs GCN inference efficiently while providing flexibility and scalability through an architecture-algorithm co-design. On the architecture side, the proposed design integrates a unified computing engine in each chiplet and an active interposer, both of which are adaptable to efficiently perform the GCN inference and facilitate data communication. On the algorithm side, we propose dynamic scheduling and mapping algorithms to optimize memory access and on-chip computations for diverse GCN applications. Experimental results show that the proposed design provides a memory access reduction by a factor of 11.3x, 3.4x, and 1.4x, and energy savings of 15.2x, 3.7x, and 1.6x on average compared to HyGCN, AWB-GCN, and GCNAX, respectively.

关键词： Engines System-on-chip Vectors inference algorithms Computer architecture Energy efficiency Design automation Chiplet-based design graph convolutional network (GCN) hardware accelerator hardware-algorithm co-design

来源：评论

学校读者我要写书评

暂无评论

Constrained Stein Variational Trajectory Optimization

引用

IEEE TRANSACTIONS ON ROBOTICS 2024年 40卷 3602-3619页

作者： Power, Thomas Berenson, Dmitry Univ Michigan Robot Dept Ann Arbor MI 48109 USA

In this article, we present constrained Stein variational trajectory optimization (CSVTO), an algorithm for performing trajectory optimization with constraints on a set of trajectories in parallel. We frame constrained trajectory optimization as a novel form of constrained functional minimization over trajectory distributions, which avoids treating the constraints as a penalty in the objective and allows us to generate diverse sets of constraint-satisfying trajectories. Our method uses Stein variational gradient descent to find a set of particles that approximates a distribution over low-cost trajectories while obeying constraints. CSVTO is applicable to problems with differentiable equality and inequality constraints and includes a novel particle resampling step to escape local minima. By explicitly generating diverse sets of trajectories, CSVTO is better able to avoid poor local minima and is more robust to initialization. We demonstrate that CSVTO outperforms baselines in challenging highly constrained tasks, such as a 7-DoF wrench manipulation task, where CSVTO outperforms all baselines both in success and constraint satisfaction.

关键词： Trajectory optimization Robots Optimization Task analysis Planning inference algorithms Manifolds Motion and path planning optimization and optimal control probability and statistical methods trajectory optimization

来源：评论

学校读者我要写书评

暂无评论

An Unbiased Symmetric Matrix Estimator for Topology inference Under Partial Observability

引用

IEEE SIGNAL PROCESSING LETTERS 2022年 29卷 1257-1261页

作者： Chen, Yupeng Wang, Zhiguo Shen, Xiaojing Sichuan Univ Coll Math Chengdu 610064 Sichuan Peoples R China

Network topology inference is a fundamental problem in many applications of network science, such as locating the source of fake news and brain connectivity network detection. Many real-world situations suffer from a critical problem in which only a limited number of observed nodes are available. In this work, the problem of network topology inference under the framework of partial observability is considered. Based on the vector autoregression model, we propose a novel unbiased estimator for symmetric network topology with Gaussian noise and the Laplacian combination rule. Theoretically, we prove that this estimator converges in probability to the network combination matrix. Furthermore, by utilizing the Gaussian mixture model algorithm, an effective algorithm called the network inference Gauss algorithm is developed to infer the network structure. Finally, compared with state-of-the-art methods, numerical experiments demonstrate that better performance is obtained in the case of small sample sizes when using the proposed algorithm.

关键词： Network topology Symmetric matrices inference algorithms Clustering algorithms Observability Signal processing algorithms Laplace equations Topology inference symmetric matrix unbiased estimator partial observation

来源：评论

学校读者我要写书评

暂无评论

A Review on Generative Adversarial Networks: algorithms, Theory, and Applications

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2023年第4期35卷 3313-3332页

作者： Gui, Jie Sun, Zhenan Wen, Yonggang Tao, Dacheng Ye, Jieping Southeast Univ Sch Cyber Sci & Engn Nanjing 211100 Jiangsu Peoples R China Purple Mt Labs Nanjing 210000 Peoples R China Univ Michigan Dept Computat Med & Bioinformat Ann Arbor MI USA Chinese Acad Sci Ctr Res Intelligent Percept & Comp Beijing 100190 Peoples R China Nanyang Technol Univ Sch Comp Sci & Engn Singapore 639798 Singapore JD Explore Acad Beijing Peoples R China Univ Sydney Sch Comp Sci Camperdown Australia Beike Beijing 100085 Peoples R China Univ Michigan Ann Arbor MI 48109 USA

Generative adversarial networks (GANs) have recently become a hot research topic;however, they have been studied since 2014, and a large number of algorithms have been proposed. Nevertheless, few comprehensive studies explain the connections among different GAN variants and how they have evolved. In this paper, we attempt to provide a review of the various GAN methods from the perspectives of algorithms, theory, and applications. First, the motivations, mathematical representations, and structures of most GAN algorithms are introduced in detail, and we compare their commonalities and differences. Second, theoretical issues related to GANs are investigated. Finally, typical applications of GANs in image processing and computer vision, natural language processing, music, speech and audio, the medical field, and data science are discussed.

关键词： Generators Generative adversarial networks Data models Linear programming Natural language processing Machine learning algorithms inference algorithms Deep learning generative adversarial networks algorithm theory applications

来源：评论

学校读者我要写书评

暂无评论

A Secure and Distributed Placement for Quality of Service-Aware IoT Requests in Fog-Cloud of Things: A Novel Joint Algorithmic Approach

引用

IEEE ACCESS 2024年 12卷 56730-56748页

作者： Srichandan, Suresh Kumar Majhi, Santosh Kumar Jena, Sudarson Mishra, Kaushik Bhat, Radhakrishna Sambalpur Univ Inst Informat Technol Burla 768016 Orissa India Veer Surendra Sai Univ Technol Dept Informat Technol Burla 768018 Romania Guru Ghasidas Vishwavidyalaya Dept Comp Sci & Informat Technol Bilaspur 495009 Chhattisgarh India Gandhi Inst Technol & Management Visakhapatnam 530045 Andhra Pradesh India Manipal Inst Technol Manipal Acad Higher Educ Dept Comp Sci & Engn Manipal 576104 India

The fast proliferation of internet-enabled devices generates massive amounts of data every day from every aspect of life. These internet-enabled devices lack the storage, processing power, and capacity necessary to handle and store this massive amount of accurate and volumetric data. Cloud computing has been proposed as a compelling substitute to process these requests. However, the ingress traffic to the Cloud is huge which causes latency overhead due to the gap that exists between end devices and the Cloud datacentre. Additionally, processing these dynamic and heterogeneous requests with disparate requirements is a computationally NP-hard problem. In this regard, Fog computing appears to be an appealing solution to surpass the aforementioned challenges as a complementary to Cloud. Therefore, this research integrated a Fog layer between the end devices and Cloud datacenters enabling a collaborative computation framework. For the classification of requests and determining the target layers for processing, this research suggests an Adaptive Neuro-Fuzzy inference System (ANFIS). Furthermore, an improved Honey Badger Algorithm (IHBA) is implemented for scheduling those requests at the target layer. To improve the convergence rate of the traditional HBA, a chaos mapping function has been implemented with an Opposition-based Learning (OBL) method. The proposed task consolidation approach has been validated using extensive simulations for QoS parameters on real-world benchmark datasets. With percentage improvements of 13.69%, 28.4%, 33.85%, 7.66%, 26.48%, and 5.63% for makespan, resource utilization, energy consumption, service delay, service cost, and delay violation, respectively, the obtained simulation results show that the suggested algorithm works better than the current state-of-the-art.

关键词： Internet of Things Cloud computing Quality of service Costs Edge computing Computational modeling Biological system modeling Fuzzy neural networks inference algorithms Resource management Task analysis Scheduling Adaptive neuro-fuzzy inference system (ANFIS) cloud computing improved honey badger algorithm resource management tasks scheduling and offloading

来源：评论

学校读者我要写书评

暂无评论

Deterministic inference of Topic Models via Maximal Latent State Replication

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2022年第4期34卷 1684-1695页

作者： Rugeles, Daniel Hai, Zhen Dash, Manoranjan Cong, Gao Nanyang Technol Univ Sch Comp Sci & Engn Singapore 639798 Singapore Natl Univ Singapore Sch Comp Singapore 119077 Singapore ASTAR Inst Infocomm Res Singapore 138632 Singapore

Probabilistic topic models, such as latent dirichlet allocation (LDA), are often used to discover hidden semantic structure of a collection of documents. In recent years, various inference algorithms have been developed to cope with learning of topic models, among which Gibbs sampling methods remain a popular choice. In this paper, we aim to improve the inference of topic models based on the Gibbs sampling framework. We extend a state augmentation based Gibbs sampling method by maximizing the replications of latent states, and propose a new generic deterministic inference method, named maximal latent state replication (MAX), for learning of a family of probabilistic topic models. One key benefit of the proposed method lies in the deterministic nature for inference, which may help to improve its running efficiency as well as predictive perplexity. We have conducted extensive experiments on real-life publicly available datasets, and the results have validated that our proposed method MAX significantly outperforms state-of-the-art baselines for inference of existing well-known topic models.

关键词： inference algorithms Computational modeling Sampling methods Probabilistic logic Mathematical model Resource management Convergence Topic models gibbs sampling deterministic inference distributable inference latent state replication

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：