检索结果-内蒙古大学图书馆

39th IEEE International Conference on data engineering, ICDE 2023

作者： Xu, Yiming Shi, Bin Ma, Teng Dong, Bo Zhou, Haoyi Zheng, Qinghua Xi'an Jiaotong University Department of Computer Science and Technology China Xi'an Jiaotong University Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering China Xi'an Jiaotong University Department of Distance Education China Beihang University School of Software China Beihang University Advanced Innovation Center for Big Data and Brain Computing China

ISBN: (纸本)9798350322279

The graph with complex annotations is the most potent data type, whose constantly evolving motivates further exploration of the unsupervised dynamic graph representation. One of the representative paradigms is graph contrastive learning. It constructs self-supervised signals by maximizing the mutual information between the statistic graph's augmentation views. However, the semantics and labels may change within the augmentation process, causing a significant performance drop in downstream tasks. This drawback becomes greatly magnified on dynamic graphs. To address this problem, we designed a simple yet effective framework named CLDG. Firstly, we elaborate that dynamic graphs have temporal translation invariance at different levels. Then, we proposed a sampling layer to extract the temporally-persistent signals. It will encourage the node to maintain consistent local and global representations, i.e., temporal translation invariance under the timespan views. The extensive experiments demonstrate the effectiveness and efficiency of the method on seven datasets by outperforming eight unsupervised state-of-the-art baselines and showing competitiveness against four semi-supervised methods. Compared with the existing dynamic graph method, the number of model parameters and training time is reduced by an average of 2,001.86 times and 130.31 times on seven datasets, respectively. The code and data are available at: https://***/yimingxu24/CLDG. © 2023 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

LSGraph: A Locality-centric High-performance Streaming Graph Engine 24

LSGraph: A Locality-centric High-performance Streaming Graph...

引用

19th European Conference on computer Systems, EuroSys 2024

作者： Qi, Hao Wu, Yiyang He, Ligang Zhang, Yu Luo, Kang Cai, Minzhi Jin, Hai Zhang, Zhan Zhao, Jin 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 China Department of Computer Science University of Warwick United Kingdom Zhejiang Lab China

ISBN: (纸本)9798400704376

Streaming graph has been broadly employed across various application domains. It involves updating edges to the graph and then performing analytics on the updated graph. However, existing solutions either suffer from poor data locality and high computation complexity for streaming graph analytics, or need high overhead to search and move graph data to ensure ordered neighbors during streaming graph update. This paper presents a novel locality-centric streaming graph engine, called LSGraph, to enable efficient both graph analytics and graph update. The main novelty of this engine is a differentiated hierarchical indexed streaming graph representation approach to achieve efficient data search and movement for graph update and also maintain data locality and ordered neighbors for efficient graph analytics simultaneously. Besides, a locality-aware streaming graph data update mechanism is also proposed to efficiently regulate the distance of data movement, minimizing the overhead of memory access during graph update. We have implemented LSGraph and conducted a systematic evaluation on both real-world and synthetic datasets. Compared with three cutting-edge streaming graph engines, i.e., Terrace, Aspen, and PaC-tree, LSGraph achieves 2.98×-81.08×, 1.46×-12.56×, and 1.26×-10.31× speedups during graph update, while obtaining 1.02×-4.28×, 1.58×-3.55×, and 1.20×-2.72× speedups during graph analytics, respectively. © 2024 Owner/Author.

关键词： Engines

来源：评论

学校读者我要写书评

暂无评论

DE-ConvGraph 3D UNet: A Novel Deep Learning Model for Optimizing Radiotherapy Treatment Plans in Oropharyngeal Cancer

DE-ConvGraph 3D UNet: A Novel Deep Learning Model for Optimi...

引用

2023 IEEE Applied Imagery Pattern Recognition Workshop, AIPR 2023

作者： Murugadoss, Bhuvanashree Amudha, J. Sugumaran, Vijayan Amrita Vishwa Vidyapeetham School of Computing Department of Computer Science and Engineering Karnataka Bengaluru India Oakland University Center for Data Science and Big Data Analytics RochesterMI United States Oakland University Department of Decision and Information Sciences RochesterMI United States

ISBN: (纸本)9798350359527

Automated radiotherapy treatment planning aims to improve treatment accuracy and efficiency. However, the prevalent Knowledge-Based Planning (KBP) method faces issues like lengthy manual problem formulation and challenges in accurately modeling human anatomy and processing high-dimensional data. This work focuses on treatment plan optimization and considers deep learning as a potential solution. Deep learning algorithms, by virtue of their ability to learn from large quantities of data and model complex relationships, can automate the formulation of the optimization problem in KBP, saving significant time and effort. However, despite these compelling advantages, it should be noted that the current convolution-based encoder-decoder models used for radiotherapy treatment plan optimization have a limited capability in capturing long-range dependencies between distant voxels. This work aims to introduce 'DE-ConvGraph 3D UNet', a novel deep learning model, to address these limitations and optimize radiotherapy treatment plans for oropharyngeal cancer. The proposed 'DE-ConvGraph 3D UNet' model includes a Graph Convolutional Network (GCN) component to capture long-range dependencies between distant voxels. Furthermore, the dual-encoder structure of the model combines the strengths of GCN and 3D Convolutional U-Net, enabling global relationships and local pattern capturing in a 3D patient volume. Experiments were conducted using the benchmark dataset-OpenKBP-Opt. The proposed model shows improvements in performance in comparison to state-of-The-Art U-Net variants in terms of mean squared voxel-wise error, dose volume histogram points and clinical criteria satisfaction. © 2023 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Modular Extremely Large-Scale Array Communication:Near-Field Modelling and Performance Analysis

引用

China Communications 2023年第4期20卷 132-152页

作者： Xinrui Li Haiquan Lu Yong Zeng Shi Jin Rui Zhang National Mobile Communications Research Laboratory Frontiers Science Center for Mobile Information Communication and SecuritySoutheast UniversityNanjing 210096China Purple Mountain Laboratories Nanjing 211111China The Chinese University of Hong Kong Shenzhen Research Institute of Big DataShenzhen 518172China Department of Electrical and Computer Engineering National University of SingaporeSingapore 117583Singapore

This paper investigates the wireless communication with a novel architecture of antenna arrays,termed modular extremely large-scale array(XLarray),where array elements of an extremely large number/size are regularly mounted on a shared platform with both horizontally and vertically interlaced *** module consists of a moderate/flexible number of array elements with the inter-element distance typically in the order of the signal wavelength,while different modules are separated by the relatively large inter-module distance for convenience of practical *** accurately modelling the signal amplitudes and phases,as well as projected apertures across all modular elements,we analyse the near-field signal-to-noise ratio(SNR)performance for modular XL-array *** on the non-uniform spherical wave(NUSW)modelling,the closed-form SNR expression is derived in terms of key system parameters,such as the overall modular array size,distances of adjacent modules along all dimensions,and the user's three-dimensional(3D)*** addition,with the number of modules in different dimensions increasing infinitely,the asymptotic SNR scaling laws are ***,we show that our proposed near-field modelling and performance analysis include the results for existing array architectures/modelling as special cases,e.g.,the collocated XL-array architecture,the uniform plane wave(UPW)based far-field modelling,and the modular extremely large-scale uniform linear array(XL-ULA)of *** simulation results are presented to validate our findings.

关键词： modular extremely large-scale array practical deployment projected apertures non-uniform spherical wave near-field modelling

来源：评论

学校读者我要写书评

暂无评论

How Graph Neural Networks Learn: Lessons from Training Dynamics 41

How Graph Neural Networks Learn: Lessons from Training Dynam...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Yang, Chenxiao Wu, Qitian Wipf, David Sun, Ruoyu Yan, Junchi School of Artificial Intelligence Department of Computer Science and Engineering MoE Lab of AI Shanghai Jiao Tong University China Amazon Web Services United States School of Data Science The Chinese University of Hong Kong Shenzhen China Shenzhen International Center for Industrial and Applied Mathematics Shenzhen Research Institute of Big Data China

A long-standing goal in deep learning has been to characterize the learning behavior of black-box models in a more interpretable manner. For graph neural networks (GNNs), considerable advances have been made in formalizing what functions they can represent, but whether GNNs will learn desired functions during the optimization process remains less clear. To fill this gap, we study their training dynamics in function space. In particular, we find that the gradient descent optimization of GNNs implicitly leverages the graph structure to update the learned function, as can be quantified by a phenomenon which we call kernel-graph alignment. We provide theoretical explanations for the emergence of this phenomenon in the overparameterized regime and empirically validate it on real-world GNNs. This finding offers new interpretable insights into when and why the learned GNN functions generalize, highlighting their limitations in heterophilic graphs. Practically, we propose a parameter-free algorithm that directly uses a sparse matrix (i.e. graph adjacency) to update the learned function. We demonstrate that this embarrassingly simple approach can be as effective as GNNs while being orders-of-magnitude faster. Copyright 2024 by the author(s)

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Strong Multimodal Representation Learner through Cross-domain Distillation for Alzheimer's Disease Classification

Strong Multimodal Representation Learner through Cross-domai...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Dai, Yulan Zou, Beiji Kui, Xiaoyan Li, Qinsong Zhao, Wei Liu, Jun López, Miguel Bordallo Central South University School of Computer Science and Engineering Changsha China Central South University Big Data Institute Changsha China Second Xiangya Hospital Department of Radiology Changsha China University of Oulu Center for Machine Vision and Signal Analysis Oulu Finland

ISBN: (纸本)9798350386226

Vision-language foundational models have achieved commendable results on related tasks. However, their application to medical tasks is still limited due to issues arising from data biases. Currently, leveraging existing foundational models to improve medical tasks remains a challenge. To this end, this paper proposes a strong multimodal representation learning method based on cross-domain distillation handling structural Magnetic Resonance Imaging (sMRI), Positron Emission Computed Tomograph (PET) images, and mini-mental state examination (MMSE) score for Alzheimer's disease (AD) classification. Specifically, we establish a text-to-image cross-domain distillation learning framework, enabling a text encoder pre-trained on general visual recognition tasks to guide the training of sMRI and PET image feature extractors. Simultaneously, positional encoding is used to extract the magnitude features of MMSE scores. Based on the multimodal representations extracted from sMRI, PET images, and MMSE scores, we perform a self-attention operation equipped with a gating mechanism for multimodal feature fusion. This mechanism controls the contribution of each modality representation to the classification decision, dynamically strengthening or weakening specific modality representations and helping construct stronger fused features for AD classification. Our method undergoes 5-fold cross-validation on the widely used ADNI dataset, and comparative experimental results demonstrate that our method achieves advanced performance in two AD-related binary classification tasks. © 2024 IEEE.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Estimating Smart Grid Stability with Hybrid RNN+LSTM Deep Learning Approach 12

Estimating Smart Grid Stability with Hybrid RNN+LSTM Deep Le...

引用

12th International Conference on Smart Grid, icSmartGrid 2024

作者： Oyucu, Saadin Sagiroglu, Seref Aksoz, Ahmet Bicer, Emre Faculty of Engineering Department of Computer Engineering Adiyaman Turkey Gazi University Artificial Intelligence and Big Data Analytics Security R&d Center Ankara Turkey Sivas Cumhuriyet University Mobilers Team Sivas Turkey Sivas University of Science and Technology Faculty of Engineering and Natural Sciences Battery Research Laboratory Sivas Turkey

ISBN: (纸本)9798350361612

Smart grids are faced with a range of challenges, such as the development of communication infrastructure, cybersecurity threats, data privacy, and the protection of user information, due to their complex structure. Another key challenge faced by smart grids is the stability issues arising from variable energy sources and consumption patterns. In these complex grid systems where energy demand and supply need to be balanced instantly, stability predictions play a significant role in foreseeing potential disruptions and optimizing energy flow. Therefore, within the scope of this study, a hybrid structure utilizing Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) networks is employed for stability classification to predict grid stability. This hybrid model combines the ability of RNN to recognize relationships between consecutive data points with LSTM's capability to preserve long-term dependencies. The results obtained indicate that the model exhibited stable performance with accuracy rates of 98.06% and 98.02% at 50 and 100 epochs, respectively. The findings of this study contribute valuable insights to research on the management and stability of smart grids, enabling energy systems to be operated more reliably and efficiently. © 2024 IEEE.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

Logical Relation Modeling and Mining in Hyperbolic Space for Recommendation 40

Logical Relation Modeling and Mining in Hyperbolic Space for...

引用

40th IEEE International Conference on data engineering, ICDE 2024

作者： Tan, Yanchao Lv, Hang Zhou, Zihao Guo, Wenzhong Xiong, Bo Liu, Weiming Chen, Chaochao Wang, Shiping Yang, Carl College of Computer and Data Science Fuzhou University Fuzhou China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China Institute for Artificial Intelligence University of Stuttgart Stuttgart Germany College of Computer Science Zhejiang University Hangzhou China Emory University Department of Computer Science Atlanta United States

ISBN: (纸本)9798350317152

The sparse interactions between users and items have aggravated the difficulty of their representations in recommender systems. Existing methods leverage tags to alleviate the sparsity problem but ignore prevalent logical relations among items and tags (e.g., membership, hierarchy, and exclusion), which can be leveraged to enhance the accuracy of modeling user preferences and conducting recommendations. To this end, we propose to extract logical relations among item tags from existing tag taxonomies and exploit the individual strengths of the Poincaré and the Lorentz models in hyperbolic space for logical relation modeling towards enhanced recommendations. Moreover, we find that the logical relations directly extracted from existing tag taxonomies can be inaccurate and coarse. Therefore, we further devise innovative consistency-based and granularity-based weighting mechanisms based on user behavior patterns for data-driven logical relation mining that can be jointly optimized along with recommendations in an end-to-end fashion. Extensive experiments on four real-world benchmark datasets show drastic performance gains brought by our proposed framework, which constantly achieves an average of 8.25% improvement over state-of-the-art competitors regarding both Recall and NDCG metrics. Insightful case studies further demonstrate that our automatically refined logical relations are highly accurate and interpretable. © 2024 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Confident Information Coverage Reliability Evaluation for Sensor Networks of Openly Deployed ICP Systems

IEEE Transactions on Industrial Cyber-Physical Systems

引用

IEEE Transactions on Industrial Cyber-Physical Systems 2024年 2卷 565-574页

作者： Chen, Suning Yi, Yuanyuan Yi, Lingzhi Liu, Shenghao Deng, Xianjun Xia, Yunzhi Fan, Xiaoxuan Yang, Laurence T. Park, Jong Hyuk Huazhong University of Science and Technology Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security The School of Cyber Science and Engineering Wuhan430074 China Huazhong University of Science and Technology School of Journalism and Information Communication Wuhan430074 China Zhongnan University of Economics and Law School of Information and Safety Engineering Wuhan430073 China Seoul National University of Technology Department of Computer Science and Engineering Seoul01811 Korea Republic of

Industrial Cyber-Physical (ICP) systems are integration of computation and physical processes to help achieve operational excellence. As sensors and actuators compose the openly deployed ICP systems and are often susceptible to interference, it puts forward higher requirements on reliability. Reliable coverage ensures sensors acquiring information and therefore coverage reliability of sensor network is studied from various perspectives. However, most existing reliability evaluation methods ignore the belief degree of coverage which influences the reliability to an extent. To evaluate the coverage reliability from the perspective of belief degree, we firstly define Confident Information Coverage Belief Reliability (CICBR) based on the Confident Information Coverage (CIC) model and D-S evidence theory, which comprehensively considers the coverage rate, interference from the environment, and belief degree of the result. Next, to evaluate the belief degree more reasonably, an Evidence-discount-based basic probability assignment generating method is proposed based on D-S theory to describe the interference in the belief degree. Moreover, a belief evaluation algorithm is proposed to calculate the belief degree of the coverage. Finally, an evidence-Discount-based Confident Information Coverage Belief Reliability Evaluation (D-CICBRE) algorithm is proposed to evaluate CICBR. The simulation result indicates that the proposed method can obtain higher and more reasonable reliability. Therefore, the proposed D-CICBRE algorithm can be used to evaluate the reliability of ICP systems more accurately and reasonably. © 2023 IEEE.

关键词： Sensor networks

来源：评论

学校读者我要写书评

暂无评论

THEF: A Privacy-Preserving Framework for Transformer Inference leveraging HE and TEE

THEF: A Privacy-Preserving Framework for Transformer Inferen...

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Zehao Li Jiachun Liao Jinhao Yu Lei Zhang Department of Computer Science and Engineering Shanghai Jiao Tong University China Big Data Research Center Nanhu Laboratory Jiaxing China

ISBN: (数字)9798331506209

ISBN: (纸本)9798331506216

The transformer has profoundly driven the development of natural language processing and computer vision tasks. However, their widespread deployment has raised concerns about the potential leakage of data privacy. To address the issue, homomorphic encryption (HE) is employed as a secure technique to process user private inputs over ciphertexts. As HE only supports linear operations, non-linear functions are required to be approximated into polynomials, which leads to heavy communication and computation overhead. In this paper, we propose THEF (Tee-And-HE-based Framework), an efficient and secure inference framework for transformer inference, which uses HE to ensure data security and leverages Trusted Execution Environment (TEE) to reduce communication and computation cost. We also design a number of optimization methods, including expanding encoding matrix multiplication scheme, batch acceleration and adaptive scheme, to improve performances of the THEF. Finally, we compare the performances of THEF and the state-of-the-art methods. The experimental results demonstrate that THEF maintains a level of accuracy close to that of plaintext model, reduces end-to-end communication cost by 80% and achieves significant improvement in end-to-end run-time.

关键词： Privacy Costs Accuracy Noise Optimization methods Transformers Encoding Polynomials Safety Homomorphic encryption

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：