检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Yao, Dezhong Shi, Yuexin Liu, Tongtong Xu, Zhiqiang National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates

Federated Learning (FL) is increasingly adopted in edge computing scenarios, where a large number of heterogeneous clients operate under constrained or sufficient resources. The iterative training process in conventional FL introduces significant computation and communication overhead, which is unfriendly for resource-constrained edge devices. One-shot FL has emerged as a promising approach to mitigate communication overhead, and model-heterogeneous FL solves the problem of diverse computing resources across clients. However, existing methods face challenges in effectively managing model-heterogeneous one-shot FL, often leading to unsatisfactory global model performance or reliance on auxiliary datasets. To address these challenges, we propose a novel FL framework named FedMHO, which leverages deep classification models on resource-sufficient clients and lightweight generative models on resource-constrained devices. On the server side, FedMHO involves a two-stage process that includes data generation and knowledge fusion. Furthermore, we introduce FedMHO-MD and FedMHO-SD to mitigate the knowledge-forgetting problem during the knowledge fusion stage, and an unsupervised data optimization solution to improve the quality of synthetic samples. Comprehensive experiments demonstrate the effectiveness of our methods, as they outperform state-of-the-art baselines in various experimental setups. Our code is available at https://***/YXShi2000/FedMHO. © 2025, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Working Smarter Not Harder: Hybrid Cooling for Deep Learning in Edge datacenters

IEEE Transactions on Sustainable Computing

引用

IEEE Transactions on Sustainable Computing 2025年

作者： Pei, Qiangyu Yuan, Yongjie Hu, Haichuan Wang, Lin Zhang, Dong Yan, Bingheng Yu, Chen Liu, Fangming Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology 1037 Luoyu Road Wuhan430074 China Paderborn University TU Darmstadt Germany Jinan Inspur Data Co. Ltd. China Huazhong University of Science and Technology Peng Cheng Laboratory China

The proliferation of deep-learning-based mobile and IoT applications has driven the increasing deployment of edge datacenters equipped with domain-specific accelerators. The unprecedented computing power offered by these accelerators puts a heavy burden on the cooling system, motivating more potent cooling techniques like cold water cooling. However, we observe that cold water cooling results in significant energy waste in edge datacenters due to the fluctuating resource utilization both spatially and temporally. To tackle this issue, we propose the concept of "working smarter"by slowing down accelerators deliberately whenever possible and enabling warm water cooling during these times to achieve cooling efficiency. Based on this concept, we develop Hyco - a hybrid water cooling system tailored for edge datacenters running deep learning workloads. First, Hyco features a zone-based cooling architecture enabling dynamic switching between cold water and warm water cooling. Then, based on a lightweight latency estimation method, Hyco incorporates a learning-based scheduling scheme to determine "which"accelerator workers and "when"to slow down through an adaptive and intelligent power-latency trade-off for deep learning models. The simulation with real-world traces shows that Hyco reduces the cooling energy consumption by up to 34.74× while satisfying latency constraints more than 99% of the time for deep-learning-based applications. © 2016 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Five-user quantum virtual local area network with an AlGaAs entangled photon source

引用

Science China(Physics,Mechanics & Astronomy) 2025年第3期68卷 61-73页

作者： Cheng Qian Hongkai Tian Xu Jing Yichen Liu Zhe Chen Huiran Luo Yuan Du Xiaodong Zheng Tangsheng Chen Yuechan Kong Hua-Lei Yin Dong Jiang Bin Niu Liangliang Lu Key Laboratory of State Manipulation and Advanced Materials in Provincial Universities School of Physical Science and TechnologyNanjing Normal UniversityNanjing210023China School of Internet Anhui UniversityHefei230039China National Key Laboratory of Solid-State Microwave Devices and Circuits Nanjing Chip Valley Industrial Technology InstituteNanjing Electronic Devices InstituteNanjing210016China Research Center for Quantum Optics and Quantum Communication School of ScienceQingdao University of TechnologyQingdao266520China Department of Physics and Beijing Key Laboratory of Opto-electronic Functional Materials and Micro-nano Devices Key Laboratory of Quantum State Construction and Manipulation(Ministry of Education)Renmin University of ChinaBeijing100872China Beijing Academy of Quantum Information Sciences Beijing100193China National Engineering Research Center of Agro-Ecological Big Data Analysis and Application Anhui UniversityHefei230601China National Laboratory of Solid-State Microstructures and School of Physics Nanjing UniversityNanjing210093China Hefei National Laboratory Hefei230088China

The promotion of quantum network applications demands the scalable connection of quantum *** is preferable to set up multiple logical networks coexisting on a single physical network infrastructure to accommodate a larger number of *** we present a quantum virtual network architecture that offers this level of scalability,without being constrained to a fixed physical-layer network relying solely on passive multiplexing *** architecture can be understood as arising from the superposition of a fully connected entanglement distribution network and port-based virtual local area network,which group multiusers by access *** terms of hardware,we leverage a semiconductor chip with a high figure-of-merit modal overlap to directly generate high-quality polarization entanglement,and a streamlined polarization analysis module,which requires only one single-photon detector for each end *** experimentally perform the BBM92 QKD protocol on the five-user quantum virtual network and demonstrate voice and image encryption on a campus area *** results may provide insights into the realization of large-scale quantum networks with integrated and cost-efficient photonic architecture.

关键词： quantum network quantum entanglement distribution integrated photonics image and voice encryption

来源：评论

学校读者我要写书评

暂无评论

Energy-efficient and Privacy-preserving Edge Intelligence for 6G-Empowered Intelligent Transportation systems

引用

IEEE Network 2025年

作者： Zhu, Chenlu Fan, Xiaoxuan Deng, Xianjun Xiao, Ziheng Guo, Tingting Liu, Shenghao Sun, Jiaqi Park, Jong Hyuk Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Wuhan Kedao Geographic Information Engineering Co. Wuhan China Department of Computer Science and Engineering Seoul National University of Science and Technology Seoul Korea Republic of

6G-empowered Intelligent Transportation systems (ITS) generate large amounts of data through millions of devices and sensors at the terminal and network edge. Edge intelligence advances the frontier of data-driven artificial intelligence (AI) to the network edge, which enables AI applications to better utilize edge data. Broader connectivity, higher device density, and stronger data exchange present challenges for reliable device communication and privacy data protection in 6G-empowered ITS. To address these challenges, this paper proposes an energy-efficient and privacy-preserving edge intelligence framework named EP-EI. EP-EI deploys a deep reinforcement learning-based cluster head selection model at the edge to ensure energy-efficient communication for terminal devices. Meanwhile, EP-EI designs a privacy-aware hierarchical computing framework for terminal-edge-cloud to prevent privacy leakage. Furthermore, the application scenarios, challenges, and future directions of EP-EI are discussed. Finally, simulation experiments in a specific intelligent transportation case study demonstrate that EP-EI can provide energy-efficient and privacy-protecting services. © 2025 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

CMD: A Cache-Assisted GPU Memory Deduplication Architecture

引用

IEEE Transactions on Computer-Aided Design of Integrated Circuits and systems 2025年

作者： Zhao, Wei Feng, Dan Tong, Wei Wei, Xueliang Wu, Bing Ministry of Education of China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of data storage systems and Technology China

Massive off-chip accesses in GPUs are the main performance bottleneck. We find that many writes are duplicate, and the duplication can be inter-dup and intra-dup. While inter-dup means different memory blocks are identical, and intra-dup means all the 4B elements in a line are the same. In this work, we propose a cache-assisted GPU memory deduplication architecture named CMD to reduce the off-chip accesses via utilizing the data duplication in GPU applications. CMD includes three key design contributions which aim to reduce the three kinds of accesses: (1) A novel GPU memory deduplication architecture that removes the intra-dup and inter-dup lines. We design several techniques to manage duplicate blocks, reducing massive off-chip writes. (2) We propose a cache-assisted read scheme to reduce the reads to duplicate data. When an L2 cache miss wants to read the duplicate block, if the reference block has been fetched to L2 and it is clean, we can copy it to the L2 missed block without accessing off-chip DRAM. As for the reads to intra-dup data, CMD uses the on-chip metadata cache to get the data. (3) When a cache line is evicted, the clean sectors in the line are invalidated while the dirty sectors are written back. However, most read-only victims are re-referenced from DRAM more than twice. Therefore, we add a full-associate FIFO to accommodate the read-only (it is also clean) victims to reduce the re-reference counts. Experiments show that CMD can decrease the off-chip accesses by 31.01%, reduce the energy by 32.78% and improve performance by 42.53%. Besides, CMD can improve the performance of memory-intensive workloads by 57.56%. © 2025 IEEE.

关键词： Cache memory

来源：评论

学校读者我要写书评

暂无评论

Mining User–Item Interactions via Knowledge Graph for Recommendation

引用

ACM Transactions on Recommender systems 2025年第3期3卷 1-19页

作者： Shenghao Liu Lingyun Lu Bang Wang Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Hubei Key Laboratory of Smart Internet Technology School of Electronic Information and Communications Huazhong University of Science and Technology (HUST) Wuhan China

Introducing a Knowledge Graph (KG) to facilitate a recommender system has become a tendency in recent years. Many existing methods leverage KGs to obtain side information of items to promote item representation learning for enhancing recommendation performance. However, they ignore that KGs also may contribute to better user representation learning. To solve this issue, we propose a novel algorithm, the KIGR (Knowledge-aware Interaction Graph for Recommendation), to mine user–item interactions via KGs for assisting user representation learning. Specifically, a user–item interaction is encoded by attentively summing up the relation embedding about the item in the KG. Then, an unsupervised learning method is used to group the user–item interactions into different latent types. Further, a user–item interaction graph is divided into several subgraphs, which is referred to as a Knowledge-aware Interaction Graph, making each subgraph only contain one latent type of interaction. Finally, user representation is the fusion of user interest embedding, which is learned on the knowledge-aware interaction graph, whereas item representation is learned on the KG. Experimental results on MovieLens, LastFM and Amazon-Book validate that the proposed KIGR has a superior performance compared with the state-of-the-art algorithms.

关键词： Recommendation system knowledge graph graph neural network

来源：评论

学校读者我要写书评

暂无评论

Regularized Total Least Squares Broad Learning system for Regression

引用

Journal of Computers (Taiwan) 2025年第1期36卷 89-112页

作者： Xiong, Ke-Jia Yang, Guan-Ci Zhou, Tao Xie, Zhen-Qiang State Key Laboratory of Public Big Data Guizhou University Guizhou Province Guiyang City550025 China Key Laboratory of Advanced Manufacturing Technology of the Ministry of Education Guizhou University Guizhou Province Guiyang City550025 China National Engineering Research Center of Big Data Application to The Improvement of Governance Capacity Guizhou Province Guiyang City550000 China

The Broad Learning system (BLS) has been extensively developed and applied across various fields due to its significant advantages, including high efficiency, strong generality, and scalability. However, in practical applications where both inputs and outputs are contaminated by noise, traditional BLS demonstrates suboptimal performance in handling sample data. This study introduces a novel regularized total least squares broad learning system (RTLS-BLS) designed to enhance the robustness of BLS when noisy values are present in both the input and the output of the training set. Initially, the k-support norm is integrated into the BLS-based autoencoder (BLS-AE), embedded within BLS, to extract robust features from the original input data. The BLS-AE equipped with the k-support norm effectively addresses or mitigates issues related to overly sparse (based on L1-norm) or overly dense (based on L2-norm) regularization of extracted features. Subsequently, regularized total least squares (RTLS) are employed to assess the output weights of BLS, further enhancing its robustness. Moreover, simultaneous perturbation measures for the coefficient matrix and the output are provided. Experimental results from two function approximation tasks, eight benchmark regression tasks, and two network interface flow datasets demonstrate that the proposed RTLS-BLS achieves significantly robust performance under noisy conditions compared to other methods. © 2025 Codon Publications. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Triangular Stable Node Network based on Self-supervised Learning for personalized prediction

A Triangular Stable Node Network based on Self-supervised Le...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Liu, Qing Gao, Qian Fan, Jun Zhang, Zhiqiang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Qilu University of Technology Shandong Academy of Sciences Jinan250014 China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology Shandong Academy of Sciences Jinan250353 China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan250014 China China Telecom Digital Intelligence Techonology Co Ltd. No.1999 Shunhua road Shandong Jinan250101 China

ISBN: (纸本)9798350368741

In recent years, research has illuminated the potency of implicit data processing in enhancing user preferences. Nevertheless, barriers remain in breaking through the constraints of implicit information. This study aims to bridge this gap by firstly constructing a triangular stable node network model, tailored to manage implicit information with precision. Recognizing the challenge of pinpointing novel structures within large-scale graphs, we propose SLTSNN-a triangular stable node network based on self-supervised learning for personalized prediction. SLTSNN innovates by maximizing mutual information between graph-level and patch-level representations, while augmenting graph representations through extended enhanced representations. Additionally, it incorporates triangular data associations and introduces a triangular allocation attention network, which emphasizes strongly correlated preference features among similar users. Furthermore, SLTSNN employs contrastive learning to maximize mutual information between graph vectors and hidden representations, distinguishing between high-order global and local representations. The model's effectiveness in enhancing user preferences and capturing new graph structures is evidenced by its performance on hit rate and normalized discounted cumulative gain metrics across three datasets. © 2025 IEEE.

关键词： graph contrastive learning graph neural networks recommender systems self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

MCT-Net: a multi-branch hybrid CNN-transformer model for medical image segmentation

引用

Pattern Analysis and Applications 2025年第2期28卷 1-21页

作者： Shen, Longfeng Diao, Liangjin Peng, Rui Chen, Jiacong Lu, Zhengtian Ge, Fangzhen Anhui Engineering Research Center for Intelligent Computing and Application on Cognitive Behavior (ICACB) College of Computer Science and Technology Huaibei Normal University Huaibei China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China Anhui Big-Data Research Center on University Management Huaibei Normal University Huaibei China

In recent years, neural networks have demonstrated substantial progress in medical image segmentation. However, accurately segmenting objects in medical images is often restricted by edge blurring, which complicates the delineation of structures of interest. The purpose of this study is to develop a multi-branch hybrid CNN-transformer model to address the issue of edge blurring in medical image segmentation. This approach enables more precise edge detection and segmentation. Integrating hybrid CNN and transformer decoders facilitates detailed recovery while preserving global structures, thus minimizing errors in regions with blurred edges. Additionally, we incorporate a hybrid attention mechanism at the model’s bottleneck to enhance feature transfer between the encoder and decoder. The model was trained using the ACDC, Synapse, and polyp datasets, with a focus on improving segmentation accuracy in regions with blurry edges. Experimental results reveal that the proposed model surpasses existing state-of-the-art methods on the ACDC, Synapse, and polyp datasets, demonstrating its superior performance and effectiveness. These results suggest that the proposed model offers a significant improvement in handling edge blurring, with potential applications in enhancing medical image analysis and diagnostics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On time slices, time complexity, and energy increase in implementing quantum adiabatic evolution by circuit model

引用

The European Physical Journal D 2025年第5期79卷 1-6页

作者： Sun, Jie Qian, Ling Cai, Dunbo Huang, Zhiguo Lu, Songfeng School of Internet Anhui University Hefei China National Engineering Research Center of Agro-Ecological Big Data Analysis and Application Anhui University Hefei China Fin China-Anhui University Joint Laboratory for Financial Big Data Research Hefei Financial China Information & Technology Co. Ltd. Hefei China China Mobile (Suzhou) Software Technology Company Limited Suzhou China School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China

In this paper, motivated by previous related works on a kind of quantum local adiabatic evolution, we mainly study the circuit model of its corresponding quantum global adiabatic search algorithm, in which the evolving paths functions in the system Hamiltonian have a general form instead of the usual linear interpolating ones which are widely investigated in the literature. The main conclusion found here can be summarized as follows. Though this quantum adiabatic computation can demonstrate various algorithmic performances, when considering implementing it by a quantum circuit, the time slices thus produced always keep as an invariant which is proportional to inverse square of the overlap between the initial and final states in the problem of interest and also equal to that of multiplying the time complexity and the energy together, by noting that compared with the usual adiabatic evolutions, there is being a great increase of energy of the system. As far as we know, the result exposed here is new and is hoped to be useful for further understanding the kind of quantum adiabatic evolution itself and its connection with the quantum circuit model. Also, we hope the main conclusion here will be ubiquitous when considering applying this kind of quantum adiabatic evolution to solve the problems beyond quantum search.

关键词：

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：